system

Abstract

We provide the system. [Solution] Means for acquiring data from data collection source, A means for preprocessing the acquired data, A means for training a generative artificial intelligence model using preprocessed data, A means of generating a response to a query from a user, Means for providing the generated response to the user, A system that includes this.

Description

Technical Field

[0005] ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] There are inefficiencies in business operations due to vertical fragmentation of information within an enterprise and insufficient cooperation between departments. In particular, since a large amount of data is dispersed among departments, it is difficult to utilize data across the entire company. Also, in order to uniformly process data collected from multiple data sources and obtain important insights, specialized knowledge and labor are required, and there are situations where quick decision-making is difficult. There is a need for a system to solve these problems and improve the business efficiency of enterprises. <​​​​​The present invention is a system that includes means for acquiring data from data sources, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for generating responses to user queries, and means for providing the generated responses to the user. Furthermore, by including means for centralizing preprocessed data and converting it into a unified format, even if the data sources span multiple departments, the system enables company-wide data integration and effective data utilization. This eliminates information silos, strengthens inter-departmental collaboration, and supports rapid decision-making.

[0006] "Data source" refers to information sources such as departments or databases that generate or hold data and from which the system can obtain the information it needs.

[0007] "Means of acquiring data" refers to the process or technology for collecting necessary data from specific sources.

[0008] "Means of preprocessing acquired data" refers to the process or technique of analyzing collected data and performing actions such as imputing missing values, removing outliers, and standardizing the format.

[0009] "Means for training generative artificial intelligence models" refers to the process or technique of using pre-processed data to train an AI model and improve its predictive and analytical capabilities for specific tasks.

[0010] "Means of generating responses to user queries" refers to the process or technology for generating appropriate answers to user questions or requests.

[0011] "Means of providing the generated response to the user" refers to the process or technology for presenting system-generated answers or information to the user in an easily understandable manner.

[0012] "Unification" refers to the process of integrating data obtained from multiple sources and combining it into a single dataset or format.

[0013] A "unified format" refers to a data format that converts data with different forms and structures into a single format, making it usable in a consistent manner. [Brief explanation of the drawing]

[0014] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when combined with an emotion engine.

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0022] [First Embodiment]

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

[0024] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0027] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0031] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0034] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0035] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of three components: a server, terminals, and users.

[0036] 1. Processing by the server

[0037] The server first has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server collects the latest monthly reports from the accounting department's database.

[0038] Because acquired data may contain inconsistencies, preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in employee evaluation data with the average value.

[0039] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0040] 2. Processing by the terminal

[0041] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0042] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user.

[0043] 3. User Operation

[0044] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0045] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data broken down by region?"

[0046] In this way, this system works in cooperation with the server, terminal, and user to effectively utilize internal company data, enabling business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, training of the AI ​​model, provision of a user interface by the terminal, and query input and result confirmation by the user.

[0047] The following describes the processing flow.

[0048] Step 1:

[0049] The server accesses each department's database and collects the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0050] Step 2:

[0051] The server preprocesses the acquired data. Specifically, it imputes missing values, removes outliers, and standardizes the data format. For example, the server fills in blanks in the evaluation data with the average value.

[0052] Step 3:

[0053] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0054] Step 4:

[0055] The server trains a generative artificial intelligence model. Using pre-processed data, it trains the AI ​​model to improve its predictive and analytical capabilities for specific tasks. For example, the server uses sales data to train a sales forecast model for the next quarter.

[0056] Step 5:

[0057] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0058] Step 6:

[0059] The device sends the user's question to the server. The question data is sent to the server in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0060] Step 7:

[0061] The server searches for the appropriate data in response to a user query. The server searches the database and extracts the relevant data. For example, the server searches the sales database and extracts data related to the sales forecast for the next quarter.

[0062] Step 8:

[0063] The server uses an AI model to generate responses to user queries. For example, the server uses extracted data and the AI ​​model to calculate and generate a sales forecast for the next quarter in text format.

[0064] Step 9:

[0065] The server sends the generated response to the terminal. For example, the server sends sales forecast results back to the terminal.

[0066] Step 10:

[0067] The device receives responses from the server and displays them in a user-friendly format. For example, the device displays sales forecast data to the user in graph and text format.

[0068] Step 11:

[0069] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please show me the data that supports the prediction." In this case, the process from step 5 onwards is repeated.

[0070] (Example 1)

[0071] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0072] Internal company data is often scattered across different departments, and its format and content are frequently inconsistent. This makes data sharing between departments difficult, hindering integrated analysis. Furthermore, incomplete or outlier data prevents accurate analysis and prediction. A system is needed to address these issues and effectively utilize internal company data.

[0073] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0074] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, and means for training a generative artificial intelligence model using the preprocessed data. This enables means for imputing missing values ​​in the collected data, removing outliers, standardizing the data format, and visually displaying the response to the query.

[0075] "Data source" refers to the organization or system that provides data, such as various departments within a company or external data sources.

[0076] "Data preprocessing" refers to the process of converting raw data into a format suitable for analysis and modeling by imputing missing values, removing outliers, and standardizing data formats.

[0077] A "generative artificial intelligence model" refers to a model that uses machine learning and deep learning techniques to learn patterns and trends from data and predict future data and answers.

[0078] A "query" refers to a question or request that a user sends to a system to obtain specific information.

[0079] "Response" refers to the answers or information that the system generates based on user queries.

[0080] "Visual representation methods" refer to ways of presenting data and forecast results in a format that is easy for users to understand, using graphs, charts, dashboards, and so on.

[0081] "Imputing missing values" refers to the process of filling in missing (blank) data with the mean or other appropriate values.

[0082] "Removing outliers" refers to the process of detecting, excluding, or correcting extreme values ​​or inaccurate data points within a dataset.

[0083] "Data format unification" refers to the process of transforming and standardizing data so that it has a consistent format and structure.

[0084] This invention is a system that integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of servers, terminals, and users.

[0085] Server-based processing

[0086] The server first retrieves data from each department's data collection source. Specifically, the server accesses each department's database and periodically extracts the necessary data. For example, it retrieves the latest monthly report from the accounting department's database.

[0087] The acquired data must undergo preprocessing, including imputation of missing values, removal of outliers, and standardization of data formats. The Python Pandas library is used for this preprocessing. For example, blank fields in employee evaluation data are filled with the average value.

[0088] Using pre-processed data, the server trains a generative artificial intelligence (AI) model. Machine learning libraries such as TENSORFLOW® and PyTorch are used to train a sales forecast model for the next quarter using historical sales data within the company.

[0089] Processing by the terminal

[0090] The terminal provides an interface for users to access the system and enter questions and queries. For example, if a user enters "Please tell me the sales forecast for the next quarter," that question is sent to the server in real time.

[0091] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, sales forecast results can be converted into a graph and presented to the user. JavaScript frameworks (such as React.js or Vue.js) are used for this display.

[0092] User operation

[0093] Users access the system through their terminals and input questions about the information they need. For example, they might ask, "How effective was this month's marketing campaign?"

[0094] Users can review the results displayed on their device and ask further questions if necessary. For example, after obtaining total sales data, they might ask additional questions such as, "Could you please provide sales data broken down by region?"

[0095] This system allows the server to perform a series of processes including data collection, preprocessing, and AI model training, while the terminal provides a user interface, allowing the user to enter queries and obtain results. An example of a prompt would be, "Retrieve the latest monthly report data, fill in missing values ​​with the mean, and train the AI ​​model to forecast sales for the next quarter."

[0096] This system efficiently utilizes data within a company, enabling improved operational efficiency and faster decision-making.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1: Data Collection

[0099] The server accesses each department's database and extracts the necessary data. Specifically, it retrieves the latest monthly report from the accounting department's database. During this process, it uses SQL queries to collect the data and saves it as a CSV file.

[0100] Input: Database of each department

[0101] Output: Acquired raw data (CSV file)

[0102] Specific actions:

[0103] The server issues an SQL query to the accounting department's database.

[0104] Extract the latest monthly report data.

[0105] Save the extracted data as a CSV file.

[0106] Step 2: Data Preprocessing

[0107] The server preprocesses the acquired data. First, it imputes missing values, then removes outliers, and finally standardizes the data format. This series of processes is performed using the Python Pandas library.

[0108] Input: Acquired raw data (CSV file)

[0109] Output: Preprocessed data

[0110] Specific actions:

[0111] Load data from a CSV file

[0112] Missing values ​​are imputed using the mean.

[0113] Removal of outliers (e.g., negative sales data)

[0114] Standardize data formats

[0115] Step 3: Training the AI ​​model

[0116] The server uses pre-processed data to train a generative artificial intelligence (AI) model. TensorFlow and PyTorch are used to build a sales forecasting model.

[0117] Input: Preprocessed data

[0118] Output: Trained AI model

[0119] Specific actions:

[0120] The data is split into features (X) and the target variable (y).

[0121] Building an AI Model

[0122] Model compilation and training

[0123] Step 4: Entering User Queries

[0124] Users access the system through their terminals and enter queries requesting specific information. For example, if they want to know the sales forecast for the next quarter, they would enter that information.

[0125] Input: User query

[0126] Output: Request sent from terminal to server

[0127] Specific actions:

[0128] The user enters a question into the browser interface.

[0129] The entered query is sent to the server by JavaScript.

[0130] Step 5: Generating the query response

[0131] The server generates responses based on user queries. It uses a pre-trained AI model to make predictions and generate the results.

[0132] Input: User query, pre-trained AI model

[0133] Output: Generated response data

[0134] Specific actions:

[0135] Processing user queries

[0136] Predictive execution using AI models

[0137] Generate results and return them to the terminal.

[0138] Step 6: Displaying the results

[0139] The terminal receives the results sent back from the server and displays them visually. Specifically, it converts sales forecast data into graphs and charts and presents them to the user.

[0140] Input: Response data from the server

[0141] Output: The result visually displayed to the user.

[0142] Specific actions:

[0143] Received response data in JSON format.

[0144] Convert data into graphs and charts (using D3.js, Highcharts, etc.)

[0145] Displayed in the user interface

[0146] Through these steps, the collaboration of servers, terminals, and users enables the efficient collection, preprocessing, and analysis of data within the enterprise, and the rapid delivery of the results.

[0147] (Application Example 1)

[0148] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0149] Effective production management in factories is crucial for integrating data from various departments and equipment, understanding production status in real time, and ensuring efficient operations. However, conventional systems often lack sufficient data integration and analysis capabilities, making it difficult for managers to make quick and accurate decisions. To address this challenge, a system is needed that collects and preprocesses data in real time and efficiently analyzes and displays it.

[0150] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0151] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing and displaying the data in real time, means for generating responses to user queries, and means for providing the generated responses to the user. This enables effective integration of production data within the factory, as well as real-time monitoring and optimization.

[0152] A "data source" refers to the location or device from which data is acquired, such as various sensors, databases, and information systems.

[0153] "Preprocessing" refers to the process of preparing acquired data for analysis, including imputing missing values, removing outliers, and standardizing data formats.

[0154] A "generative artificial intelligence model" is an AI model that uses collected and pre-processed data to automatically learn specific tasks and perform predictions and analyses.

[0155] "Means for analyzing and displaying data in real time" refers to tools and systems that have the function of analyzing production data within a factory in real time and immediately visualizing and displaying the results to the user.

[0156] A "query" is a question or instruction that a user asks the system to request specific information.

[0157] A "response" refers to the data or information that a generative artificial intelligence model or system provides in response to a user's query.

[0158] The embodiments for carrying out this invention are described below. The real-time production management system is a system for aggregating data within a factory and monitoring, analyzing, and displaying the production status in real time. Its main components are a server, terminals, and users, which work together in cooperation.

[0159] 1. Processing by the server

[0160] The server uses the following hardware and software:

[0161] Hardware: Sensor network within the factory, work robots, server units

[0162] Software: Sensor data ingestion platform for data collection, Python scripts for data processing, TensorFlow for AI model building.

[0163] The server first automatically acquires data from each data source. A concrete example of this is the process of acquiring real-time production data from sensors installed on each production line in a factory. The data is first aggregated on the server, and then preprocessing is performed. Preprocessing includes imputing missing data values, removing outliers, and standardizing data formats. For example, missing parts of the sensor data from production equipment are filled in with average values.

[0164] Using pre-processed data, a generative artificial intelligence model is trained. Based on historical data, the AI ​​model is trained to build a model for predicting and analyzing real-time production status. For example, TensorFlow can be used to train a model that predicts the operating rate of a production line.

[0165] 2. Processing by the terminal

[0166] The terminal provides a user interface and a means for users to check production status in real time. For example, it displays graphed production data on the administrator's PC or tablet using a dashboard tool (e.g., Grafana). When a user enters a query such as "What is the current utilization rate of line 2?", the terminal sends this query to the server.

[0167] The server generates a response to the query and sends that data back to the terminal. The terminal converts the received response data into a visually easy-to-understand format and displays it to the user. For example, it might display the predicted uptime data sent back from the server as a graph, making it easy for administrators to understand.

[0168] 3. User Operation

[0169] Users access the system through their terminal and ask questions about the information they need. For example, they might enter a prompt such as, "Predict and display the utilization rate of line 1 for the next week." Based on this prompt, the server uses a generative artificial intelligence model to perform the necessary calculations and generate the result.

[0170] Based on the results confirmed by the user, the system optimizes production plans, identifies problems, and asks further detailed questions. This system allows users to understand the factory's production status in real time, enabling rapid decision-making.

[0171] Examples of prompt statements:

[0172] "Please predict and display the utilization rate of Line 1 for the next week."

[0173] In this way, a real-time production management system can significantly improve factory production efficiency by having the server, terminals, and users work together as a unified whole.

[0174] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0175] Step 1: Data Collection

[0176] The server acquires data in real time from sensors and databases installed within the factory. At this stage, data such as production line utilization rates, inventory status, and the number of defective products are collected. The input is production data from sensors and databases, and the output is the initial production data stored on the server.

[0177] Step 2: Data preprocessing

[0178] The server preprocesses the collected data. This includes tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, if a production equipment sensor temporarily malfunctions and data is lost, the missing portion is filled in with the average value. The input is the initial production data, and the output is the preprocessed, clean data.

[0179] Step 3: Training the AI ​​model

[0180] The server trains a generative artificial intelligence model using preprocessed data. The model is trained to take in historical data and predict future production conditions. For example, TensorFlow is used to build a model for predicting production line utilization. The input is preprocessed data, and the output is the trained AI model.

[0181] Step 4: Receiving the query

[0182] The terminal receives queries from users. For example, an administrator might enter a query such as, "Predict and display the utilization rate of line 1 for the next week." The input is the query entered by the user into the terminal, and the output is that the query has been sent to the server.

[0183] Step 5: Generating responses to queries

[0184] The server uses an AI model to perform the necessary calculations based on the received query. It generates data according to the user's request, for example, predicting the production line's operating rate for the next week. The input is the user's query and the trained AI model, and the output is the response data to the query.

[0185] Step 6: Display the response

[0186] The terminal receives response data sent back from the server and displays it in a user-friendly format. For example, it can use Grafana to graph predictive data and display it on the administrator's PC or tablet. The input is the response data received from the server, and the output is the display of the visualized data.

[0187] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0188] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of a server, terminals, users, and an emotion engine.

[0189] 1. Processing by the server

[0190] The server has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server might collect the latest monthly reports from the accounting department's database.

[0191] The acquired data may contain inconsistencies if left as is, so preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server may fill in blanks in the evaluation data with the mean value.

[0192] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0193] Furthermore, the server has an emotion engine built in, which has the means to analyze the user's emotions. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[0194] 2. Processing by the terminal

[0195] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0196] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user. The terminal also receives feedback from an emotion engine and adjusts the displayed content according to the user's emotions.

[0197] 3. User Operation

[0198] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0199] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0200] In this way, this system works in conjunction with four elements: the server, terminal, user, and emotion engine, to effectively utilize internal company data and enable business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, AI model training, emotion analysis, user interface provision by the terminal, and query input and result confirmation by the user.

[0201] The following describes the processing flow.

[0202] Step 1:

[0203] The server accesses each department's database and automatically retrieves the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0204] Step 2:

[0205] The server preprocesses the acquired data. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in the evaluation data with the mean value.

[0206] Step 3:

[0207] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0208] Step 4:

[0209] The server uses pre-processed data to train a generative artificial intelligence model. For example, the server uses historical sales data to train a sales forecast model for the next quarter.

[0210] Step 5:

[0211] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0212] Step 6:

[0213] The device sends the user's question to the server. The question data is sent in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0214] Step 7:

[0215] The server searches for relevant data in response to user queries and generates appropriate responses. For example, the server searches a sales database, extracts data related to the next quarter's sales forecast, and uses an AI model to generate the sales forecast.

[0216] Step 8:

[0217] The server sends the generated response data back to the terminal. For example, the server sends sales forecast results back to the terminal.

[0218] Step 9:

[0219] The device receives a response from the server and displays it to the user. For example, the device displays sales forecast data to the user in graph and text format.

[0220] Step 10:

[0221] The user reviews the results, and the emotion engine analyzes the user's emotions from their voice or text. For example, the user might look at the results and enter a comment such as "I feel relieved."

[0222] Step 11:

[0223] Based on the emotional results analyzed by the emotion engine, the server adjusts its response. For example, if a user expresses negative emotions, the server provides additional information to reassure them.

[0224] Step 12:

[0225] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please tell me the data that forms the basis of the prediction." In this case, the process from step 5 onwards is repeated.

[0226] (Example 2)

[0227] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0228] Internal company data is often stored in different databases for each department, and because each database has a different data format and structure, it is difficult to integrate and use. Furthermore, while there is a need to provide responses that align with user emotions and needs, current systems make it extremely difficult to meet this requirement. This hinders operational efficiency and rapid decision-making.

[0229] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0230] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing the user's emotions, means for generating responses to user queries, and means for providing the generated responses to the user. This makes it possible to unify and integrate data from each department and provide optimal responses that meet the user's emotions and needs.

[0231] A "data source" refers to a system or database that extracts data from a source.

[0232] "Means of acquiring data" refers to methods of collecting necessary information from other systems and databases by utilizing network connections or APIs.

[0233] "Methods for preprocessing data" refer to processing methods used to impute missing values, remove outliers, and standardize data formats.

[0234] A "generative artificial intelligence model" refers to a type of artificial intelligence that has the ability to learn from large amounts of data and generate new data and insights.

[0235] "Methods for training" refer to methods of using data to train an AI model so that it can perform a specific task.

[0236] "Means of analyzing user emotions" refers to methods that read emotions from text or voice input by the user and generate appropriate responses based on those emotions.

[0237] "Means of generating responses to queries" refers to methods of providing appropriate answers or data based on questions or requests from users.

[0238] "Means of providing a response to the user" refers to the method or procedure for displaying the generated response on the user's device.

[0239] Modes for carrying out the invention

[0240] System Overview

[0241] This invention is a system that effectively integrates internal corporate data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of a server, terminals, users, and an emotion engine.

[0242] Server-based processing

[0243] The server has the means to retrieve data from each department's data collection source. This means includes having access rights to each department's database and a process to automatically retrieve the necessary data. The software used includes SQL database management systems and API access tools.

[0244] The acquired data may contain inconsistencies and therefore requires preprocessing. The server has preprocessing capabilities, including imputing missing values, removing outliers, and standardizing data formats. The software used for this includes the Python Pandas library and data cleansing tools.

[0245] Using pre-processed data, the server has the means to train generative artificial intelligence (AI) models. This involves using generative AI frameworks such as TensorFlow and PyTorch. For example, these tools are used to train a sales forecast model for the next quarter using historical sales data.

[0246] The server incorporates an emotion engine, which includes IBM Watson® and Google®'s Natural Language API. The emotion engine recognizes emotions from the user's voice and text and adjusts the response based on the analysis results.

[0247] Processing by the terminal

[0248] The terminal provides an interface for users to access the system and enter questions and queries. This includes web browser-based forms and dedicated applications. Questions entered by users are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0249] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and can convert it into a user-friendly format, such as a graph or table. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[0250] User operation

[0251] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0252] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0253] Examples of prompt statements

[0254] Server-based processing

[0255] "The server should collect the latest monthly reports from the accounting department's database."

[0256] Processing by the terminal

[0257] "When a user asks for the sales forecast for the next quarter, the device should send that question to the server."

[0258] User operation

[0259] "Users should use their devices to ask questions about the effectiveness of this month's marketing campaign."

[0260] In this way, this system works in cooperation with four parties: the server, terminal, user, and emotion engine, enabling effective use of internal company data and facilitating business efficiency and rapid decision-making.

[0261] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0262] Step 1:

[0263] The server retrieves data from the data collection sources of each department. Specifically, the server uses SQL queries and API requests to access the databases of each department, such as the accounting and sales departments, and retrieves the necessary data.

[0264] Input: Request for access to departmental databases

[0265] Output: Datasets obtained from each department

[0266] Step 2:

[0267] The server preprocesses the acquired data. This processing includes imputing missing values, removing outliers, and standardizing the data format. The software used is the Python Pandas library.

[0268] Input: Raw data obtained

[0269] Output: Preprocessed data

[0270] Specific operation: The server uses Pandas to impute missing values ​​with the mean, remove outliers, and standardize the data format.

[0271] Step 3:

[0272] The server uses pre-processed data to train a generative artificial intelligence (AI) model. This is done using tools such as TensorFlow or PyTorch.

[0273] Input: Preprocessed dataset

[0274] Output: Trained AI model

[0275] Specific operation: The server uses TensorFlow to train a sales forecast model for the next quarter based on past sales data.

[0276] Step 4:

[0277] The server analyzes the user's emotions using an emotion engine. This analysis utilizes IBM Watson and Google's Natural Language API.

[0278] Input: User input text or voice

[0279] Output: Emotion analysis results

[0280] Specific operation: The server uses IBM Watson to analyze the sentiment from the user's text input and customize the response content based on the result.

[0281] Step 5:

[0282] The terminal provides an interface for the user to enter questions. This is implemented through a web browser form or a dedicated application.

[0283] Input: Query from the user

[0284] Output: User interface screen

[0285] Specific operation: The terminal displays an input form in a web browser and enables the user to enter questions.

[0286] Step 6:

[0287] The user enters a query via the terminal. For example, enter a query such as "Please tell me the sales forecast for the next quarter."

[0288] Input: User's query <000​​​​​​​​​​​​​​​​​​​​​​​​​Specific operation: The terminal sends the user's query to the server in real time.

[0296] Step 8:

[0297] The server generates a response to the user's query.

[0298] Input: User's query and the trained AI model

[0299] Output: Generated response data

[0300] Specific operation: The server uses the trained AI model to generate sales prediction data for the user's question.

[0301] Step 9:

[0302] The server returns the generated response data to the terminal.

[0303] Input: Generated response data

[0304] Output: Response data sent to the terminal

[0305] Specific operation: The server sends the generated sales prediction data to the terminal.

[0306] Step 10:

[0307] The terminal displays the response data returned from the server to the user.

[0308] Input: Response data sent from the server

[0309] Output: Response result displayed to the user

[0310] Specific operation: The terminal converts the data received from the server into a graph or table format and presents it to the user.

[0311] The above outlines the specific steps involved in the system's processing.

[0312] (Application Example 2)

[0313] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0314] Modern autonomous vehicles require real-time analysis of large amounts of data acquired from various sensors and the provision of appropriate feedback to the driver. However, this data often contains missing or outlier values, making accurate prediction and feedback difficult. Furthermore, while generating responses that reflect the driver's emotions would improve driving safety and comfort, current systems have a problem in that emotion analysis and feedback generation are not adequately coordinated.

[0315] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, and means for analyzing the user's emotions using an emotion engine and generating appropriate feedback based on the analysis results. This makes it possible to predict driving conditions accurately in real time and provide feedback that corresponds to the driver's emotions.

[0316] A "data source" refers to a device or system that acquires information from various sensors, databases, and other sources.

[0317] "Preprocessing" refers to the process of modifying acquired data, such as imputing missing values, removing outliers, and standardizing data formats.

[0318] A "generative artificial intelligence model" is a machine learning model trained using pre-processed data, designed to extract specific patterns or insights from that data.

[0319] A "query" refers to a question or request made by a user to a system.

[0320] A "response" refers to the answer or information that a system provides in response to a user's query.

[0321] "Emotional analysis" is a method of recognizing and analyzing a user's emotional state from their voice and facial expressions.

[0322] "Feedback" refers to advice and instructions provided based on user behavior or the state of the system.

[0323] A "unified format" refers to a set of rules and standards for converting data collected from different data sources into a consistent format.

[0324] A "server" is a computer system used for data collection, preprocessing, analysis, and generating responses to users.

[0325] "Real-time" refers to a state where data collection, analysis, and response generation occur instantly, with minimal delay.

[0326] A "user" is a person who uses a system and is the entity that performs a series of operations.

[0327] This invention relates to a driver assistance application for autonomous vehicles, which analyzes vehicle data in real time and provides appropriate feedback and advice to the driver. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0328] 1. Processing by the server

[0329] The server has the means to collect and preprocess sensor data transmitted from vehicles. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. Based on the preprocessed data, the server trains a generative artificial intelligence model to generate a predictive model for driving conditions. This model is used to predict traffic congestion, speed, distance traveled, and other factors.

[0330] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions from their voice and facial expressions. Based on the results of this emotion analysis, it generates appropriate feedback for the driver.

[0331] The hardware used includes various sensors in the vehicle (cameras, LiDAR, GPS, etc.). Software such as TensorFlow (for AI model training) and EmotionDetector (for emotion analysis) are employed.

[0332] 2. Processing by the terminal

[0333] The terminal provides an interface for users to access the system and enter queries. Users can enter specific questions into the terminal, which then sends those questions to the server in real time. For example, if a user enters "Please tell me the traffic situation up to the next intersection," the terminal will send that question to the server.

[0334] When the server generates a response to a query, the data is sent back to the terminal and displayed in a user-friendly format. For example, traffic congestion prediction data sent back from the server can be converted into a graph and presented to the user. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[0335] 3. User Operation

[0336] Users can access the system through a terminal and enter questions about vehicle driving information. Using the interface provided by the terminal, users can enter specific queries and check the responses from the server. For example, they can enter questions such as, "Please tell me the predicted driving time for the next 30 minutes."

[0337] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining overall traffic information in the initial question, they can ask more detailed questions such as, "Please tell me about the traffic situation in a specific area." Furthermore, the system analyzes the user's voice and facial expressions to analyze their emotions and provides feedback based on the results.

[0338] Specific example

[0339] For example, if you enter a question such as "Please tell me the traffic conditions up to the next intersection," you can send a prompt message to the system like the following.

[0340] What is the next action indicated by the vehicle's sensor_data_url?

[0341] Please analyze the audio data (audio_input) and video data (video_input) of the driver currently in operation.

[0342] Thus, the present invention is a system that can improve driving safety and comfort by providing appropriate feedback and advice in real time through the cooperation of a server, terminal, user, and emotion engine.

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

[0344] Step 1:

[0345] The server collects data in real time from various sensors in the vehicle (cameras, LiDAR, GPS, etc.). This data includes mileage, speed, and surrounding traffic information. It receives raw data collected from the sensors as input and prepares it for pre-processing as output.

[0346] Step 2:

[0347] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, it might imputate missing data with the mean value of the surrounding data and remove outliers. It receives raw data collected from sensors as input and generates preprocessed, formatted data as output.

[0348] Step 3:

[0349] The server trains a generative artificial intelligence model based on pre-processed data. This process uses historical data to train a predictive model for traffic and driving conditions. It receives pre-processed, formatted data as input and generates a trained AI model as output.

[0350] Step 4:

[0351] The server collects user voice and facial expression data and analyzes emotions using an emotion engine. For example, it evaluates the driver's stress level and degree of distraction. It receives voice and video data as input and generates user emotion analysis results as output.

[0352] Step 5:

[0353] The server generates appropriate feedback for the driver based on sentiment analysis results and a trained AI model. This feedback is provided through voice guidance and a visual interface. It receives sentiment analysis results and predictions from the AI ​​model as input and generates feedback messages as output.

[0354] Step 6:

[0355] The terminal provides an interface for users to enter queries into the system. For example, a driver could enter, "Please tell me the traffic conditions up to the next intersection." It receives queries from the user as input and sends them to the server as output.

[0356] Step 7:

[0357] The server generates responses to queries sent from the terminal. For example, it uses pre-processed sensor data and an AI model to predict traffic congestion along driving routes and generates the results as feedback. It receives user queries as input and generates response messages as output.

[0358] Step 8:

[0359] The terminal receives response messages sent from the server and displays them in a user-friendly format. For example, it displays traffic congestion prediction results in graph or text format. It receives response messages from the server as input and provides visual feedback as output.

[0360] Step 9:

[0361] Users can review the feedback displayed through their device and ask more detailed questions as needed. For example, they can enter a detailed query such as, "Please tell me about the traffic conditions during a specific time period." The system uses the displayed feedback as input and a new query as output.

[0362] This allows the entire process to be performed in real time, enabling the driver to receive appropriate feedback and advice.

[0363] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0364] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0365] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0366] [Second Embodiment]

[0367] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0368] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0369] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0370] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0371] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0372] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0373] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0374] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0375] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0376] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0377] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0378] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0379] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of three components: a server, terminals, and users.

[0380] 1. Processing by the server

[0381] The server first has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server collects the latest monthly reports from the accounting department's database.

[0382] Because acquired data may contain inconsistencies, preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in employee evaluation data with the average value.

[0383] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0384] 2. Processing by the terminal

[0385] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0386] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user.

[0387] 3. User Operation

[0388] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0389] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data broken down by region?"

[0390] In this way, this system works in cooperation with the server, terminal, and user to effectively utilize internal company data, enabling business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, training of the AI ​​model, provision of a user interface by the terminal, and query input and result confirmation by the user.

[0391] The following describes the processing flow.

[0392] Step 1:

[0393] The server accesses each department's database and collects the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0394] Step 2:

[0395] The server preprocesses the acquired data. Specifically, it imputes missing values, removes outliers, and standardizes the data format. For example, the server fills in blanks in the evaluation data with the average value.

[0396] Step 3:

[0397] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0398] Step 4:

[0399] The server trains a generative artificial intelligence model. Using pre-processed data, it trains the AI ​​model to improve its predictive and analytical capabilities for specific tasks. For example, the server uses sales data to train a sales forecast model for the next quarter.

[0400] Step 5:

[0401] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0402] Step 6:

[0403] The device sends the user's question to the server. The question data is sent to the server in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0404] Step 7:

[0405] The server searches for the appropriate data in response to a user query. The server searches the database and extracts the relevant data. For example, the server searches the sales database and extracts data related to the sales forecast for the next quarter.

[0406] Step 8:

[0407] The server uses an AI model to generate responses to user queries. For example, the server uses extracted data and the AI ​​model to calculate and generate a sales forecast for the next quarter in text format.

[0408] Step 9:

[0409] The server sends the generated response to the terminal. For example, the server sends sales forecast results back to the terminal.

[0410] Step 10:

[0411] The device receives responses from the server and displays them in a user-friendly format. For example, the device displays sales forecast data to the user in graph and text format.

[0412] Step 11:

[0413] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please show me the data that supports the prediction." In this case, the process from step 5 onwards is repeated.

[0414] (Example 1)

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

[0416] Internal company data is often scattered across different departments, and its format and content are frequently inconsistent. This makes data sharing between departments difficult, hindering integrated analysis. Furthermore, incomplete or outlier data prevents accurate analysis and prediction. A system is needed to address these issues and effectively utilize internal company data.

[0417] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0418] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, and means for training a generative artificial intelligence model using the preprocessed data. This enables means for imputing missing values ​​in the collected data, removing outliers, standardizing the data format, and visually displaying the response to the query.

[0419] "Data source" refers to the organization or system that provides data, such as various departments within a company or external data sources.

[0420] "Data preprocessing" refers to the process of converting raw data into a format suitable for analysis and modeling by imputing missing values, removing outliers, and standardizing data formats.

[0421] A "generative artificial intelligence model" refers to a model that uses machine learning and deep learning techniques to learn patterns and trends from data and predict future data and answers.

[0422] A "query" refers to a question or request that a user sends to a system to obtain specific information.

[0423] "Response" refers to the answers or information that the system generates based on user queries.

[0424] "Visual representation methods" refer to ways of presenting data and forecast results in a format that is easy for users to understand, using graphs, charts, dashboards, and so on.

[0425] "Imputing missing values" refers to the process of filling in missing (blank) data with the mean or other appropriate values.

[0426] "Removing outliers" refers to the process of detecting, excluding, or correcting extreme values ​​or inaccurate data points within a dataset.

[0427] "Data format unification" refers to the process of transforming and standardizing data so that it has a consistent format and structure.

[0428] This invention is a system that integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of servers, terminals, and users.

[0429] Server-based processing

[0430] The server first retrieves data from each department's data collection source. Specifically, the server accesses each department's database and periodically extracts the necessary data. For example, it retrieves the latest monthly report from the accounting department's database.

[0431] The acquired data must undergo preprocessing, including imputation of missing values, removal of outliers, and standardization of data formats. The Python Pandas library is used for this preprocessing. For example, blank fields in employee evaluation data are filled with the average value.

[0432] Using pre-processed data, the server trains a generative artificial intelligence (AI) model. Machine learning libraries such as TensorFlow and PyTorch are used to train a sales forecast model for the next quarter using historical sales data from the company.

[0433] Processing by the terminal

[0434] The terminal provides an interface for users to access the system and enter questions and queries. For example, if a user enters "Please tell me the sales forecast for the next quarter," that question is sent to the server in real time.

[0435] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, sales forecast results can be converted into a graph and presented to the user. JavaScript frameworks (such as React.js or Vue.js) are used for this display.

[0436] User operation

[0437] Users access the system through their terminals and input questions about the information they need. For example, they might ask, "How effective was this month's marketing campaign?"

[0438] Users can review the results displayed on their device and ask further questions if necessary. For example, after obtaining total sales data, they might ask additional questions such as, "Could you please provide sales data broken down by region?"

[0439] This system allows the server to perform a series of processes including data collection, preprocessing, and AI model training, while the terminal provides a user interface, allowing the user to enter queries and obtain results. An example of a prompt would be, "Retrieve the latest monthly report data, fill in missing values ​​with the mean, and train the AI ​​model to forecast sales for the next quarter."

[0440] This system efficiently utilizes data within a company, enabling improved operational efficiency and faster decision-making.

[0441] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0442] Step 1: Data Collection

[0443] The server accesses each department's database and extracts the necessary data. Specifically, it retrieves the latest monthly report from the accounting department's database. During this process, it uses SQL queries to collect the data and saves it as a CSV file.

[0444] Input: Database of each department

[0445] Output: Acquired raw data (CSV file)

[0446] Specific actions:

[0447] The server issues an SQL query to the accounting department's database.

[0448] Extract the latest monthly report data.

[0449] Save the extracted data as a CSV file.

[0450] Step 2: Data Preprocessing

[0451] The server preprocesses the acquired data. First, it imputes missing values, then removes outliers, and finally standardizes the data format. This series of processes is performed using the Python Pandas library.

[0452] Input: Acquired raw data (CSV file)

[0453] Output: Preprocessed data

[0454] Specific actions:

[0455] Load data from a CSV file

[0456] Missing values ​​are imputed using the mean.

[0457] Removal of outliers (e.g., negative sales data)

[0458] Standardize data formats

[0459] Step 3: Training the AI ​​model

[0460] The server uses pre-processed data to train a generative artificial intelligence (AI) model. TensorFlow and PyTorch are used to build a sales forecasting model.

[0461] Input: Preprocessed data

[0462] Output: Trained AI model

[0463] Specific actions:

[0464] The data is split into features (X) and the target variable (y).

[0465] Building an AI Model

[0466] Model compilation and training

[0467] Step 4: Entering User Queries

[0468] Users access the system through their terminals and enter queries requesting specific information. For example, if they want to know the sales forecast for the next quarter, they would enter that information.

[0469] Input: User query

[0470] Output: Request sent from terminal to server

[0471] Specific actions:

[0472] The user enters a question into the browser interface.

[0473] The entered query is sent to the server by JavaScript.

[0474] Step 5: Generating the query response

[0475] The server generates responses based on user queries. It uses a pre-trained AI model to make predictions and generate the results.

[0476] Input: User query, pre-trained AI model

[0477] Output: Generated response data

[0478] Specific actions:

[0479] Processing user queries

[0480] Predictive execution using AI models

[0481] Generate results and return them to the terminal.

[0482] Step 6: Displaying the results

[0483] The terminal receives the results sent back from the server and displays them visually. Specifically, it converts sales forecast data into graphs and charts and presents them to the user.

[0484] Input: Response data from the server

[0485] Output: The result visually displayed to the user.

[0486] Specific actions:

[0487] Received response data in JSON format.

[0488] Convert data into graphs and charts (using D3.js, Highcharts, etc.)

[0489] Displayed in the user interface

[0490] Through these steps, the collaboration of servers, terminals, and users enables the efficient collection, preprocessing, and analysis of data within the enterprise, and the rapid delivery of the results.

[0491] (Application Example 1)

[0492] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0493] Effective production management in factories is crucial for integrating data from various departments and equipment, understanding production status in real time, and ensuring efficient operations. However, conventional systems often lack sufficient data integration and analysis capabilities, making it difficult for managers to make quick and accurate decisions. To address this challenge, a system is needed that collects and preprocesses data in real time and efficiently analyzes and displays it.

[0494] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0495] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing and displaying the data in real time, means for generating responses to user queries, and means for providing the generated responses to the user. This enables effective integration of production data within the factory, as well as real-time monitoring and optimization.

[0496] A "data source" refers to the location or device from which data is acquired, such as various sensors, databases, and information systems.

[0497] "Preprocessing" refers to the process of preparing acquired data for analysis, including imputing missing values, removing outliers, and standardizing data formats.

[0498] A "generative artificial intelligence model" is an AI model that uses collected and pre-processed data to automatically learn specific tasks and perform predictions and analyses.

[0499] "Means for analyzing and displaying data in real time" refers to tools and systems that have the function of analyzing production data within a factory in real time and immediately visualizing and displaying the results to the user.

[0500] A "query" is a question or instruction that a user asks the system to request specific information.

[0501] A "response" refers to the data or information that a generative artificial intelligence model or system provides in response to a user's query.

[0502] The embodiments for carrying out this invention are described below. The real-time production management system is a system for aggregating data within a factory and monitoring, analyzing, and displaying the production status in real time. Its main components are a server, terminals, and users, which work together in cooperation.

[0503] 1. Processing by the server

[0504] The server uses the following hardware and software:

[0505] Hardware: Sensor network within the factory, work robots, server units

[0506] Software: Sensor data ingestion platform for data collection, Python scripts for data processing, TensorFlow for AI model building.

[0507] The server first automatically acquires data from each data source. A concrete example of this is the process of acquiring real-time production data from sensors installed on each production line in a factory. The data is first aggregated on the server, and then preprocessing is performed. Preprocessing includes imputing missing data values, removing outliers, and standardizing data formats. For example, missing parts of the sensor data from production equipment are filled in with average values.

[0508] Using pre-processed data, a generative artificial intelligence model is trained. Based on historical data, the AI ​​model is trained to build a model for predicting and analyzing real-time production status. For example, TensorFlow can be used to train a model that predicts the operating rate of a production line.

[0509] 2. Processing by the terminal

[0510] The terminal provides a user interface and a means for users to check production status in real time. For example, it displays graphed production data on the administrator's PC or tablet using a dashboard tool (e.g., Grafana). When a user enters a query such as "What is the current utilization rate of line 2?", the terminal sends this query to the server.

[0511] The server generates a response to the query and sends that data back to the terminal. The terminal converts the received response data into a visually easy-to-understand format and displays it to the user. For example, it might display the predicted uptime data sent back from the server as a graph, making it easy for administrators to understand.

[0512] 3. User Operation

[0513] Users access the system through their terminal and ask questions about the information they need. For example, they might enter a prompt such as, "Predict and display the utilization rate of line 1 for the next week." Based on this prompt, the server uses a generative artificial intelligence model to perform the necessary calculations and generate the result.

[0514] Based on the results confirmed by the user, the system optimizes production plans, identifies problems, and asks further detailed questions. This system allows users to understand the factory's production status in real time, enabling rapid decision-making.

[0515] Examples of prompt statements:

[0516] "Please predict and display the utilization rate of Line 1 for the next week."

[0517] In this way, a real-time production management system can significantly improve factory production efficiency by having the server, terminals, and users work together as a unified whole.

[0518] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0519] Step 1: Data Collection

[0520] The server acquires data in real time from sensors and databases installed within the factory. At this stage, data such as production line utilization rates, inventory status, and the number of defective products are collected. The input is production data from sensors and databases, and the output is the initial production data stored on the server.

[0521] Step 2: Data preprocessing

[0522] The server preprocesses the collected data. This includes tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, if a production equipment sensor temporarily malfunctions and data is lost, the missing portion is filled in with the average value. The input is the initial production data, and the output is the preprocessed, clean data.

[0523] Step 3: Training the AI ​​model

[0524] The server trains a generative artificial intelligence model using preprocessed data. The model is trained to take in historical data and predict future production conditions. For example, TensorFlow is used to build a model for predicting production line utilization. The input is preprocessed data, and the output is the trained AI model.

[0525] Step 4: Receiving the query

[0526] The terminal receives queries from users. For example, an administrator might enter a query such as, "Predict and display the utilization rate of line 1 for the next week." The input is the query entered by the user into the terminal, and the output is that the query has been sent to the server.

[0527] Step 5: Generating responses to queries

[0528] The server uses an AI model to perform the necessary calculations based on the received query. It generates data according to the user's request, for example, predicting the production line's operating rate for the next week. The input is the user's query and the trained AI model, and the output is the response data to the query.

[0529] Step 6: Display the response

[0530] The terminal receives response data sent back from the server and displays it in a user-friendly format. For example, it can use Grafana to graph predictive data and display it on the administrator's PC or tablet. The input is the response data received from the server, and the output is the display of the visualized data.

[0531] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0532] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of a server, terminals, users, and an emotion engine.

[0533] 1. Processing by the server

[0534] The server has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server might collect the latest monthly reports from the accounting department's database.

[0535] The acquired data may contain inconsistencies if left as is, so preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server may fill in blanks in the evaluation data with the mean value.

[0536] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0537] Furthermore, the server has an emotion engine built in, which has the means to analyze the user's emotions. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[0538] 2. Processing by the terminal

[0539] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0540] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user. The terminal also receives feedback from an emotion engine and adjusts the displayed content according to the user's emotions.

[0541] 3. User Operation

[0542] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0543] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0544] In this way, this system works in conjunction with four elements: the server, terminal, user, and emotion engine, to effectively utilize internal company data and enable business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, AI model training, emotion analysis, user interface provision by the terminal, and query input and result confirmation by the user.

[0545] The following describes the processing flow.

[0546] Step 1:

[0547] The server accesses each department's database and automatically retrieves the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0548] Step 2:

[0549] The server preprocesses the acquired data. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in the evaluation data with the mean value.

[0550] Step 3:

[0551] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0552] Step 4:

[0553] The server uses pre-processed data to train a generative artificial intelligence model. For example, the server uses historical sales data to train a sales forecast model for the next quarter.

[0554] Step 5:

[0555] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0556] Step 6:

[0557] The device sends the user's question to the server. The question data is sent in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0558] Step 7:

[0559] The server searches for relevant data in response to user queries and generates appropriate responses. For example, the server searches a sales database, extracts data related to the next quarter's sales forecast, and uses an AI model to generate the sales forecast.

[0560] Step 8:

[0561] The server sends the generated response data back to the terminal. For example, the server sends sales forecast results back to the terminal.

[0562] Step 9:

[0563] The device receives a response from the server and displays it to the user. For example, the device displays sales forecast data to the user in graph and text format.

[0564] Step 10:

[0565] The user reviews the results, and the emotion engine analyzes the user's emotions from their voice or text. For example, the user might look at the results and enter a comment such as "I feel relieved."

[0566] Step 11:

[0567] Based on the emotional results analyzed by the emotion engine, the server adjusts its response. For example, if a user expresses negative emotions, the server provides additional information to reassure them.

[0568] Step 12:

[0569] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please tell me the data that forms the basis of the prediction." In this case, the process from step 5 onwards is repeated.

[0570] (Example 2)

[0571] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0572] Internal company data is often stored in different databases for each department, and because each database has a different data format and structure, it is difficult to integrate and use. Furthermore, while there is a need to provide responses that align with user emotions and needs, current systems make it extremely difficult to meet this requirement. This hinders operational efficiency and rapid decision-making.

[0573] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0574] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing the user's emotions, means for generating responses to user queries, and means for providing the generated responses to the user. This makes it possible to unify and integrate data from each department and provide optimal responses that meet the user's emotions and needs.

[0575] A "data source" refers to a system or database that extracts data from a source.

[0576] "Means of acquiring data" refers to methods of collecting necessary information from other systems and databases by utilizing network connections or APIs.

[0577] "Methods for preprocessing data" refer to processing methods used to impute missing values, remove outliers, and standardize data formats.

[0578] A "generative artificial intelligence model" refers to a type of artificial intelligence that has the ability to learn from large amounts of data and generate new data and insights.

[0579] "Methods for training" refer to methods of using data to train an AI model so that it can perform a specific task.

[0580] "Means of analyzing user emotions" refers to methods that read emotions from text or voice input by the user and generate appropriate responses based on those emotions.

[0581] "Means of generating responses to queries" refers to methods of providing appropriate answers or data based on questions or requests from users.

[0582] "Means of providing a response to the user" refers to the method or procedure for displaying the generated response on the user's device.

[0583] Modes for carrying out the invention

[0584] System Overview

[0585] This invention is a system that effectively integrates internal corporate data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of a server, terminals, users, and an emotion engine.

[0586] Server-based processing

[0587] The server has the means to retrieve data from each department's data collection source. This means includes having access rights to each department's database and a process to automatically retrieve the necessary data. The software used includes SQL database management systems and API access tools.

[0588] The acquired data may contain inconsistencies and therefore requires preprocessing. The server has preprocessing capabilities, including imputing missing values, removing outliers, and standardizing data formats. The software used for this includes the Python Pandas library and data cleansing tools.

[0589] Using pre-processed data, the server has the means to train generative artificial intelligence (AI) models. This involves using generative AI frameworks such as TensorFlow and PyTorch. For example, these tools are used to train a sales forecast model for the next quarter using historical sales data.

[0590] The server incorporates an emotion engine, which includes IBM Watson and Google's Natural Language API. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[0591] Processing by the terminal

[0592] The terminal provides an interface for users to access the system and enter questions and queries. This includes web browser-based forms and dedicated applications. Questions entered by users are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0593] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and can convert it into a user-friendly format, such as a graph or table. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[0594] User operation

[0595] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0596] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0597] Examples of prompt statements

[0598] Server-based processing

[0599] "The server should collect the latest monthly reports from the accounting department's database."

[0600] Processing by the terminal

[0601] "When a user asks for the sales forecast for the next quarter, the device should send that question to the server."

[0602] User operation

[0603] "Users should use their devices to ask questions about the effectiveness of this month's marketing campaign."

[0604] In this way, this system works in cooperation with four parties: the server, terminal, user, and emotion engine, enabling effective use of internal company data and facilitating business efficiency and rapid decision-making.

[0605] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0606] Step 1:

[0607] The server retrieves data from the data collection sources of each department. Specifically, the server uses SQL queries and API requests to access the databases of each department, such as the accounting and sales departments, and retrieves the necessary data.

[0608] Input: Request for access to departmental databases

[0609] Output: Datasets obtained from each department

[0610] Step 2:

[0611] The server preprocesses the acquired data. This processing includes imputing missing values, removing outliers, and standardizing the data format. The software used is the Python Pandas library.

[0612] Input: Raw data obtained

[0613] Output: Preprocessed data

[0614] Specific operation: The server uses Pandas to impute missing values ​​with the mean, remove outliers, and standardize the data format.

[0615] Step 3:

[0616] The server uses pre-processed data to train a generative artificial intelligence (AI) model. This is done using tools such as TensorFlow or PyTorch.

[0617] Input: Preprocessed dataset

[0618] Output: Trained AI model

[0619] Specific operation: The server uses TensorFlow to train a sales forecast model for the next quarter based on past sales data.

[0620] Step 4:

[0621] The server analyzes the user's emotions using an emotion engine. This analysis utilizes IBM Watson and Google's Natural Language API.

[0622] Input: User input text or voice

[0623] Output: Emotion analysis results

[0624] Specific operation: The server uses IBM Watson to analyze the user's emotions from their text input and customizes the response based on the results.

[0625] Step 5:

[0626] The terminal provides the user with an interface for entering questions. This can be achieved through a web browser form or a dedicated application.

[0627] Input: User query

[0628] Output: User interface screen

[0629] Specific action: The device displays an input form in a web browser, allowing the user to enter a question.

[0630] Step 6:

[0631] The user enters a query via their terminal. For example, they might enter a query such as, "Please tell me the sales forecast for the next quarter."

[0632] Input: User query

[0633] Output: Input query

[0634] Specific action: The user types a question into the input form on the device and presses the submit button.

[0635] Step 7:

[0636] The terminal sends the query entered by the user to the server.

[0637] Input: Query entered by the user

[0638] Output: Query sent to the server

[0639] Specific operation: The terminal sends user queries to the server in real time.

[0640] Step 8:

[0641] The server generates a response to the user's query.

[0642] Input: User queries and trained AI models

[0643] Output: Generated response data

[0644] Specific operation: The server uses a pre-trained AI model to generate sales forecast data in response to the user's questions.

[0645] Step 9:

[0646] The server sends the generated response data back to the terminal.

[0647] Input: Generated response data

[0648] Output: Response data sent to the terminal

[0649] Specific operation: The server sends the sales forecast data it generates to the terminal.

[0650] Step 10:

[0651] The terminal displays the response data sent back from the server to the user.

[0652] Input: Response data sent from the server

[0653] Output: Response results displayed to the user

[0654] Specific operation: The terminal receives data from the server, converts it into graphs or tables, and presents it to the user.

[0655] The above outlines the specific steps involved in the system's processing.

[0656] (Application Example 2)

[0657] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0658] Modern autonomous vehicles require real-time analysis of large amounts of data acquired from various sensors and the provision of appropriate feedback to the driver. However, this data often contains missing or outlier values, making accurate prediction and feedback difficult. Furthermore, while generating responses that reflect the driver's emotions would improve driving safety and comfort, current systems have a problem in that emotion analysis and feedback generation are not adequately coordinated.

[0659] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, and means for analyzing the user's emotions using an emotion engine and generating appropriate feedback based on the analysis results. This makes it possible to predict driving conditions accurately in real time and provide feedback that corresponds to the driver's emotions.

[0660] A "data source" refers to a device or system that acquires information from various sensors, databases, and other sources.

[0661] "Preprocessing" refers to the process of modifying acquired data, such as imputing missing values, removing outliers, and standardizing data formats.

[0662] A "generative artificial intelligence model" is a machine learning model trained using pre-processed data, designed to extract specific patterns or insights from that data.

[0663] A "query" refers to a question or request made by a user to a system.

[0664] A "response" refers to the answer or information that a system provides in response to a user's query.

[0665] "Emotional analysis" is a method of recognizing and analyzing a user's emotional state from their voice and facial expressions.

[0666] "Feedback" refers to advice and instructions provided based on user behavior or the state of the system.

[0667] A "unified format" refers to a set of rules and standards for converting data collected from different data sources into a consistent format.

[0668] A "server" is a computer system used for data collection, preprocessing, analysis, and generating responses to users.

[0669] "Real-time" refers to a state where data collection, analysis, and response generation occur instantly, with minimal delay.

[0670] A "user" is a person who uses a system and is the entity that performs a series of operations.

[0671] This invention relates to a driver assistance application for autonomous vehicles, which analyzes vehicle data in real time and provides appropriate feedback and advice to the driver. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[0672] 1. Processing by the server

[0673] The server has the means to collect and preprocess sensor data transmitted from vehicles. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. Based on the preprocessed data, the server trains a generative artificial intelligence model to generate a predictive model for driving conditions. This model is used to predict traffic congestion, speed, distance traveled, and other factors.

[0674] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions from their voice and facial expressions. Based on the results of this emotion analysis, it generates appropriate feedback for the driver.

[0675] The hardware used includes various sensors in the vehicle (cameras, LiDAR, GPS, etc.). Software such as TensorFlow (for AI model training) and EmotionDetector (for emotion analysis) are employed.

[0676] 2. Processing by the terminal

[0677] The terminal provides an interface for users to access the system and enter queries. Users can enter specific questions into the terminal, which then sends those questions to the server in real time. For example, if a user enters "Please tell me the traffic situation up to the next intersection," the terminal will send that question to the server.

[0678] When the server generates a response to a query, the data is sent back to the terminal and displayed in a user-friendly format. For example, traffic congestion prediction data sent back from the server can be converted into a graph and presented to the user. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[0679] 3. User Operation

[0680] Users can access the system through a terminal and enter questions about vehicle driving information. Using the interface provided by the terminal, users can enter specific queries and check the responses from the server. For example, they can enter questions such as, "Please tell me the predicted driving time for the next 30 minutes."

[0681] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining overall traffic information in the initial question, they can ask more detailed questions such as, "Please tell me about the traffic situation in a specific area." Furthermore, the system analyzes the user's voice and facial expressions to analyze their emotions and provides feedback based on the results.

[0682] Specific example

[0683] For example, if you enter a question such as "Please tell me the traffic conditions up to the next intersection," you can send a prompt message to the system like the following.

[0684] What is the next action indicated by the vehicle's sensor_data_url?

[0685] Please analyze the audio data (audio_input) and video data (video_input) of the driver currently in operation.

[0686] Thus, the present invention is a system that can improve driving safety and comfort by providing appropriate feedback and advice in real time through the cooperation of a server, terminal, user, and emotion engine.

[0687] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0688] Step 1:

[0689] The server collects data in real time from various sensors in the vehicle (cameras, LiDAR, GPS, etc.). This data includes mileage, speed, and surrounding traffic information. It receives raw data collected from the sensors as input and prepares it for pre-processing as output.

[0690] Step 2:

[0691] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, it might imputate missing data with the mean value of the surrounding data and remove outliers. It receives raw data collected from sensors as input and generates preprocessed, formatted data as output.

[0692] Step 3:

[0693] The server trains a generative artificial intelligence model based on pre-processed data. This process uses historical data to train a predictive model for traffic and driving conditions. It receives pre-processed, formatted data as input and generates a trained AI model as output.

[0694] Step 4:

[0695] The server collects user voice and facial expression data and analyzes emotions using an emotion engine. For example, it evaluates the driver's stress level and degree of distraction. It receives voice and video data as input and generates user emotion analysis results as output.

[0696] Step 5:

[0697] The server generates appropriate feedback for the driver based on sentiment analysis results and a trained AI model. This feedback is provided through voice guidance and a visual interface. It receives sentiment analysis results and predictions from the AI ​​model as input and generates feedback messages as output.

[0698] Step 6:

[0699] The terminal provides an interface for users to enter queries into the system. For example, a driver could enter, "Please tell me the traffic conditions up to the next intersection." It receives queries from the user as input and sends them to the server as output.

[0700] Step 7:

[0701] The server generates responses to queries sent from the terminal. For example, it uses pre-processed sensor data and an AI model to predict traffic congestion along driving routes and generates the results as feedback. It receives user queries as input and generates response messages as output.

[0702] Step 8:

[0703] The terminal receives response messages sent from the server and displays them in a user-friendly format. For example, it displays traffic congestion prediction results in graph or text format. It receives response messages from the server as input and provides visual feedback as output.

[0704] Step 9:

[0705] Users can review the feedback displayed through their device and ask more detailed questions as needed. For example, they can enter a detailed query such as, "Please tell me about the traffic conditions during a specific time period." The system uses the displayed feedback as input and a new query as output.

[0706] This allows the entire process to be performed in real time, enabling the driver to receive appropriate feedback and advice.

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

[0708] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

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

[0710] [Third Embodiment]

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

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

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

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

[0715] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

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

[0717] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0718] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

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

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

[0721] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0723] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of three components: a server, terminals, and users.

[0724] 1. Processing by the server

[0725] The server first has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server collects the latest monthly reports from the accounting department's database.

[0726] Because acquired data may contain inconsistencies, preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in employee evaluation data with the average value.

[0727] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0728] 2. Processing by the terminal

[0729] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0730] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user.

[0731] 3. User Operation

[0732] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0733] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data broken down by region?"

[0734] In this way, this system works in cooperation with the server, terminal, and user to effectively utilize internal company data, enabling business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, training of the AI ​​model, provision of a user interface by the terminal, and query input and result confirmation by the user.

[0735] The following describes the processing flow.

[0736] Step 1:

[0737] The server accesses each department's database and collects the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0738] Step 2:

[0739] The server preprocesses the acquired data. Specifically, it imputes missing values, removes outliers, and standardizes the data format. For example, the server fills in blanks in the evaluation data with the average value.

[0740] Step 3:

[0741] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0742] Step 4:

[0743] The server trains a generative artificial intelligence model. Using pre-processed data, it trains the AI ​​model to improve its predictive and analytical capabilities for specific tasks. For example, the server uses sales data to train a sales forecast model for the next quarter.

[0744] Step 5:

[0745] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0746] Step 6:

[0747] The device sends the user's question to the server. The question data is sent to the server in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0748] Step 7:

[0749] The server searches for the appropriate data in response to a user query. The server searches the database and extracts the relevant data. For example, the server searches the sales database and extracts data related to the sales forecast for the next quarter.

[0750] Step 8:

[0751] The server uses an AI model to generate responses to user queries. For example, the server uses extracted data and the AI ​​model to calculate and generate a sales forecast for the next quarter in text format.

[0752] Step 9:

[0753] The server sends the generated response to the terminal. For example, the server sends sales forecast results back to the terminal.

[0754] Step 10:

[0755] The device receives responses from the server and displays them in a user-friendly format. For example, the device displays sales forecast data to the user in graph and text format.

[0756] Step 11:

[0757] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please show me the data that supports the prediction." In this case, the process from step 5 onwards is repeated.

[0758] (Example 1)

[0759] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0760] Internal company data is often scattered across different departments, and its format and content are frequently inconsistent. This makes data sharing between departments difficult, hindering integrated analysis. Furthermore, incomplete or outlier data prevents accurate analysis and prediction. A system is needed to address these issues and effectively utilize internal company data.

[0761] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0762] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, and means for training a generative artificial intelligence model using the preprocessed data. This enables means for imputing missing values ​​in the collected data, removing outliers, standardizing the data format, and visually displaying the response to the query.

[0763] "Data source" refers to the organization or system that provides data, such as various departments within a company or external data sources.

[0764] "Data preprocessing" refers to the process of converting raw data into a format suitable for analysis and modeling by imputing missing values, removing outliers, and standardizing data formats.

[0765] A "generative artificial intelligence model" refers to a model that uses machine learning and deep learning techniques to learn patterns and trends from data and predict future data and answers.

[0766] A "query" refers to a question or request that a user sends to a system to obtain specific information.

[0767] "Response" refers to the answers or information that the system generates based on user queries.

[0768] "Visual representation methods" refer to ways of presenting data and forecast results in a format that is easy for users to understand, using graphs, charts, dashboards, and so on.

[0769] "Imputing missing values" refers to the process of filling in missing (blank) data with the mean or other appropriate values.

[0770] "Removing outliers" refers to the process of detecting, excluding, or correcting extreme values ​​or inaccurate data points within a dataset.

[0771] "Data format unification" refers to the process of transforming and standardizing data so that it has a consistent format and structure.

[0772] This invention is a system that integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of servers, terminals, and users.

[0773] Server-based processing

[0774] The server first retrieves data from each department's data collection source. Specifically, the server accesses each department's database and periodically extracts the necessary data. For example, it retrieves the latest monthly report from the accounting department's database.

[0775] The acquired data must undergo preprocessing, including imputation of missing values, removal of outliers, and standardization of data formats. The Python Pandas library is used for this preprocessing. For example, blank fields in employee evaluation data are filled with the average value.

[0776] Using pre-processed data, the server trains a generative artificial intelligence (AI) model. Machine learning libraries such as TensorFlow and PyTorch are used to train a sales forecast model for the next quarter using historical sales data from the company.

[0777] Processing by the terminal

[0778] The terminal provides an interface for users to access the system and enter questions and queries. For example, if a user enters "Please tell me the sales forecast for the next quarter," that question is sent to the server in real time.

[0779] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, sales forecast results can be converted into a graph and presented to the user. JavaScript frameworks (such as React.js or Vue.js) are used for this display.

[0780] User operation

[0781] Users access the system through their terminals and input questions about the information they need. For example, they might ask, "How effective was this month's marketing campaign?"

[0782] Users can review the results displayed on their device and ask further questions if necessary. For example, after obtaining total sales data, they might ask additional questions such as, "Could you please provide sales data broken down by region?"

[0783] This system allows the server to perform a series of processes including data collection, preprocessing, and AI model training, while the terminal provides a user interface, allowing the user to enter queries and obtain results. An example of a prompt would be, "Retrieve the latest monthly report data, fill in missing values ​​with the mean, and train the AI ​​model to forecast sales for the next quarter."

[0784] This system efficiently utilizes data within a company, enabling improved operational efficiency and faster decision-making.

[0785] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0786] Step 1: Data Collection

[0787] The server accesses each department's database and extracts the necessary data. Specifically, it retrieves the latest monthly report from the accounting department's database. During this process, it uses SQL queries to collect the data and saves it as a CSV file.

[0788] Input: Database of each department

[0789] Output: Acquired raw data (CSV file)

[0790] Specific actions:

[0791] The server issues an SQL query to the accounting department's database.

[0792] Extract the latest monthly report data.

[0793] Save the extracted data as a CSV file.

[0794] Step 2: Data Preprocessing

[0795] The server preprocesses the acquired data. First, it imputes missing values, then removes outliers, and finally standardizes the data format. This series of processes is performed using the Python Pandas library.

[0796] Input: Acquired raw data (CSV file)

[0797] Output: Preprocessed data

[0798] Specific actions:

[0799] Load data from a CSV file

[0800] Missing values ​​are imputed using the mean.

[0801] Removal of outliers (e.g., negative sales data)

[0802] Standardize data formats

[0803] Step 3: Training the AI ​​model

[0804] The server uses pre-processed data to train a generative artificial intelligence (AI) model. TensorFlow and PyTorch are used to build a sales forecasting model.

[0805] Input: Preprocessed data

[0806] Output: Trained AI model

[0807] Specific actions:

[0808] The data is split into features (X) and the target variable (y).

[0809] Building an AI Model

[0810] Model compilation and training

[0811] Step 4: Entering User Queries

[0812] Users access the system through their terminals and enter queries requesting specific information. For example, if they want to know the sales forecast for the next quarter, they would enter that information.

[0813] Input: User query

[0814] Output: Request sent from terminal to server

[0815] Specific actions:

[0816] The user enters a question into the browser interface.

[0817] The entered query is sent to the server by JavaScript.

[0818] Step 5: Generating the query response

[0819] The server generates responses based on user queries. It uses a pre-trained AI model to make predictions and generate the results.

[0820] Input: User query, pre-trained AI model

[0821] Output: Generated response data

[0822] Specific actions:

[0823] Processing user queries

[0824] Predictive execution using AI models

[0825] Generate results and return them to the terminal.

[0826] Step 6: Displaying the results

[0827] The terminal receives the results sent back from the server and displays them visually. Specifically, it converts sales forecast data into graphs and charts and presents them to the user.

[0828] Input: Response data from the server

[0829] Output: The result visually displayed to the user.

[0830] Specific actions:

[0831] Received response data in JSON format.

[0832] Convert data into graphs and charts (using D3.js, Highcharts, etc.)

[0833] Displayed in the user interface

[0834] Through these steps, the collaboration of servers, terminals, and users enables the efficient collection, preprocessing, and analysis of data within the enterprise, and the rapid delivery of the results.

[0835] (Application Example 1)

[0836] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0837] Effective production management in factories is crucial for integrating data from various departments and equipment, understanding production status in real time, and ensuring efficient operations. However, conventional systems often lack sufficient data integration and analysis capabilities, making it difficult for managers to make quick and accurate decisions. To address this challenge, a system is needed that collects and preprocesses data in real time and efficiently analyzes and displays it.

[0838] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0839] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing and displaying the data in real time, means for generating responses to user queries, and means for providing the generated responses to the user. This enables effective integration of production data within the factory, as well as real-time monitoring and optimization.

[0840] A "data source" refers to the location or device from which data is acquired, such as various sensors, databases, and information systems.

[0841] "Preprocessing" refers to the process of preparing acquired data for analysis, including imputing missing values, removing outliers, and standardizing data formats.

[0842] A "generative artificial intelligence model" is an AI model that uses collected and pre-processed data to automatically learn specific tasks and perform predictions and analyses.

[0843] "Means for analyzing and displaying data in real time" refers to tools and systems that have the function of analyzing production data within a factory in real time and immediately visualizing and displaying the results to the user.

[0844] A "query" is a question or instruction that a user asks the system to request specific information.

[0845] A "response" refers to the data or information that a generative artificial intelligence model or system provides in response to a user's query.

[0846] The embodiments for carrying out this invention are described below. The real-time production management system is a system for aggregating data within a factory and monitoring, analyzing, and displaying the production status in real time. Its main components are a server, terminals, and users, which work together in cooperation.

[0847] 1. Processing by the server

[0848] The server uses the following hardware and software:

[0849] Hardware: Sensor network within the factory, work robots, server units

[0850] Software: Sensor data ingestion platform for data collection, Python scripts for data processing, TensorFlow for AI model building.

[0851] The server first automatically acquires data from each data source. A concrete example of this is the process of acquiring real-time production data from sensors installed on each production line in a factory. The data is first aggregated on the server, and then preprocessing is performed. Preprocessing includes imputing missing data values, removing outliers, and standardizing data formats. For example, missing parts of the sensor data from production equipment are filled in with average values.

[0852] Using pre-processed data, a generative artificial intelligence model is trained. Based on historical data, the AI ​​model is trained to build a model for predicting and analyzing real-time production status. For example, TensorFlow can be used to train a model that predicts the operating rate of a production line.

[0853] 2. Processing by the terminal

[0854] The terminal provides a user interface and a means for users to check production status in real time. For example, it displays graphed production data on the administrator's PC or tablet using a dashboard tool (e.g., Grafana). When a user enters a query such as "What is the current utilization rate of line 2?", the terminal sends this query to the server.

[0855] The server generates a response to the query and sends that data back to the terminal. The terminal converts the received response data into a visually easy-to-understand format and displays it to the user. For example, it might display the predicted uptime data sent back from the server as a graph, making it easy for administrators to understand.

[0856] 3. User Operation

[0857] Users access the system through their terminal and ask questions about the information they need. For example, they might enter a prompt such as, "Predict and display the utilization rate of line 1 for the next week." Based on this prompt, the server uses a generative artificial intelligence model to perform the necessary calculations and generate the result.

[0858] Based on the results confirmed by the user, the system optimizes production plans, identifies problems, and asks further detailed questions. This system allows users to understand the factory's production status in real time, enabling rapid decision-making.

[0859] Examples of prompt statements:

[0860] "Please predict and display the utilization rate of Line 1 for the next week."

[0861] In this way, a real-time production management system can significantly improve factory production efficiency by having the server, terminals, and users work together as a unified whole.

[0862] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0863] Step 1: Data Collection

[0864] The server acquires data in real time from sensors and databases installed within the factory. At this stage, data such as production line utilization rates, inventory status, and the number of defective products are collected. The input is production data from sensors and databases, and the output is the initial production data stored on the server.

[0865] Step 2: Data preprocessing

[0866] The server preprocesses the collected data. This includes tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, if a production equipment sensor temporarily malfunctions and data is lost, the missing portion is filled in with the average value. The input is the initial production data, and the output is the preprocessed, clean data.

[0867] Step 3: Training the AI ​​model

[0868] The server trains a generative artificial intelligence model using preprocessed data. The model is trained to take in historical data and predict future production conditions. For example, TensorFlow is used to build a model for predicting production line utilization. The input is preprocessed data, and the output is the trained AI model.

[0869] Step 4: Receiving the query

[0870] The terminal receives queries from users. For example, an administrator might enter a query such as, "Predict and display the utilization rate of line 1 for the next week." The input is the query entered by the user into the terminal, and the output is that the query has been sent to the server.

[0871] Step 5: Generating responses to queries

[0872] The server uses an AI model to perform the necessary calculations based on the received query. It generates data according to the user's request, for example, predicting the production line's operating rate for the next week. The input is the user's query and the trained AI model, and the output is the response data to the query.

[0873] Step 6: Display the response

[0874] The terminal receives response data sent back from the server and displays it in a user-friendly format. For example, it can use Grafana to graph predictive data and display it on the administrator's PC or tablet. The input is the response data received from the server, and the output is the display of the visualized data.

[0875] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0876] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of a server, terminals, users, and an emotion engine.

[0877] 1. Processing by the server

[0878] The server has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server might collect the latest monthly reports from the accounting department's database.

[0879] The acquired data may contain inconsistencies if left as is, so preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server may fill in blanks in the evaluation data with the mean value.

[0880] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[0881] Furthermore, the server has an emotion engine built in, which has the means to analyze the user's emotions. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[0882] 2. Processing by the terminal

[0883] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0884] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user. The terminal also receives feedback from an emotion engine and adjusts the displayed content according to the user's emotions.

[0885] 3. User Operation

[0886] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0887] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0888] In this way, this system works in conjunction with four elements: the server, terminal, user, and emotion engine, to effectively utilize internal company data and enable business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, AI model training, emotion analysis, user interface provision by the terminal, and query input and result confirmation by the user.

[0889] The following describes the processing flow.

[0890] Step 1:

[0891] The server accesses each department's database and automatically retrieves the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[0892] Step 2:

[0893] The server preprocesses the acquired data. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in the evaluation data with the mean value.

[0894] Step 3:

[0895] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[0896] Step 4:

[0897] The server uses pre-processed data to train a generative artificial intelligence model. For example, the server uses historical sales data to train a sales forecast model for the next quarter.

[0898] Step 5:

[0899] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[0900] Step 6:

[0901] The device sends the user's question to the server. The question data is sent in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[0902] Step 7:

[0903] The server searches for relevant data in response to user queries and generates appropriate responses. For example, the server searches a sales database, extracts data related to the next quarter's sales forecast, and uses an AI model to generate the sales forecast.

[0904] Step 8:

[0905] The server sends the generated response data back to the terminal. For example, the server sends sales forecast results back to the terminal.

[0906] Step 9:

[0907] The device receives a response from the server and displays it to the user. For example, the device displays sales forecast data to the user in graph and text format.

[0908] Step 10:

[0909] The user reviews the results, and the emotion engine analyzes the user's emotions from their voice or text. For example, the user might look at the results and enter a comment such as "I feel relieved."

[0910] Step 11:

[0911] Based on the emotional results analyzed by the emotion engine, the server adjusts its response. For example, if a user expresses negative emotions, the server provides additional information to reassure them.

[0912] Step 12:

[0913] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please tell me the data that forms the basis of the prediction." In this case, the process from step 5 onwards is repeated.

[0914] (Example 2)

[0915] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0916] Internal company data is often stored in different databases for each department, and because each database has a different data format and structure, it is difficult to integrate and use. Furthermore, while there is a need to provide responses that align with user emotions and needs, current systems make it extremely difficult to meet this requirement. This hinders operational efficiency and rapid decision-making.

[0917] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0918] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing the user's emotions, means for generating responses to user queries, and means for providing the generated responses to the user. This makes it possible to unify and integrate data from each department and provide optimal responses that meet the user's emotions and needs.

[0919] A "data source" refers to a system or database that extracts data from a source.

[0920] "Means of acquiring data" refers to methods of collecting necessary information from other systems and databases by utilizing network connections or APIs.

[0921] "Methods for preprocessing data" refer to processing methods used to impute missing values, remove outliers, and standardize data formats.

[0922] A "generative artificial intelligence model" refers to a type of artificial intelligence that has the ability to learn from large amounts of data and generate new data and insights.

[0923] "Methods for training" refer to methods of using data to train an AI model so that it can perform a specific task.

[0924] "Means of analyzing user emotions" refers to methods that read emotions from text or voice input by the user and generate appropriate responses based on those emotions.

[0925] "Means of generating responses to queries" refers to methods of providing appropriate answers or data based on questions or requests from users.

[0926] "Means of providing a response to the user" refers to the method or procedure for displaying the generated response on the user's device.

[0927] Modes for carrying out the invention

[0928] System Overview

[0929] This invention is a system that effectively integrates internal corporate data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of a server, terminals, users, and an emotion engine.

[0930] Server-based processing

[0931] The server has the means to retrieve data from each department's data collection source. This means includes having access rights to each department's database and a process to automatically retrieve the necessary data. The software used includes SQL database management systems and API access tools.

[0932] The acquired data may contain inconsistencies and therefore requires preprocessing. The server has preprocessing capabilities, including imputing missing values, removing outliers, and standardizing data formats. The software used for this includes the Python Pandas library and data cleansing tools.

[0933] Using pre-processed data, the server has the means to train generative artificial intelligence (AI) models. This involves using generative AI frameworks such as TensorFlow and PyTorch. For example, these tools are used to train a sales forecast model for the next quarter using historical sales data.

[0934] The server incorporates an emotion engine, which includes IBM Watson and Google's Natural Language API. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[0935] Processing by the terminal

[0936] The terminal provides an interface for users to access the system and enter questions and queries. This includes web browser-based forms and dedicated applications. Questions entered by users are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[0937] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and can convert it into a user-friendly format, such as a graph or table. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[0938] User operation

[0939] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[0940] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[0941] Examples of prompt statements

[0942] Server-based processing

[0943] "The server should collect the latest monthly reports from the accounting department's database."

[0944] Processing by the terminal

[0945] "When a user asks for the sales forecast for the next quarter, the device should send that question to the server."

[0946] User operation

[0947] "Users should use their devices to ask questions about the effectiveness of this month's marketing campaign."

[0948] In this way, this system works in cooperation with four parties: the server, terminal, user, and emotion engine, enabling effective use of internal company data and facilitating business efficiency and rapid decision-making.

[0949] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0950] Step 1:

[0951] The server retrieves data from the data collection sources of each department. Specifically, the server uses SQL queries and API requests to access the databases of each department, such as the accounting and sales departments, and retrieves the necessary data.

[0952] Input: Request for access to departmental databases

[0953] Output: Datasets obtained from each department

[0954] Step 2:

[0955] The server preprocesses the acquired data. This processing includes imputing missing values, removing outliers, and standardizing the data format. The software used is the Python Pandas library.

[0956] Input: Raw data obtained

[0957] Output: Preprocessed data

[0958] Specific operation: The server uses Pandas to impute missing values ​​with the mean, remove outliers, and standardize the data format.

[0959] Step 3:

[0960] The server uses pre-processed data to train a generative artificial intelligence (AI) model. This is done using tools such as TensorFlow or PyTorch.

[0961] Input: Preprocessed dataset

[0962] Output: Trained AI model

[0963] Specific operation: The server uses TensorFlow to train a sales forecast model for the next quarter based on past sales data.

[0964] Step 4:

[0965] The server analyzes the user's emotions using an emotion engine. This analysis utilizes IBM Watson and Google's Natural Language API.

[0966] Input: User input text or voice

[0967] Output: Emotion analysis results

[0968] Specific operation: The server uses IBM Watson to analyze the user's emotions from their text input and customizes the response based on the results.

[0969] Step 5:

[0970] The terminal provides the user with an interface for entering questions. This can be achieved through a web browser form or a dedicated application.

[0971] Input: User query

[0972] Output: User interface screen

[0973] Specific action: The device displays an input form in a web browser, allowing the user to enter a question.

[0974] Step 6:

[0975] The user enters a query via their terminal. For example, they might enter a query such as, "Please tell me the sales forecast for the next quarter."

[0976] Input: User query

[0977] Output: Input query

[0978] Specific action: The user types a question into the input form on the device and presses the submit button.

[0979] Step 7:

[0980] The terminal sends the query entered by the user to the server.

[0981] Input: Query entered by the user

[0982] Output: Query sent to the server

[0983] Specific operation: The terminal sends user queries to the server in real time.

[0984] Step 8:

[0985] The server generates a response to the user's query.

[0986] Input: User queries and trained AI models

[0987] Output: Generated response data

[0988] Specific operation: The server uses a pre-trained AI model to generate sales forecast data in response to the user's questions.

[0989] Step 9:

[0990] The server sends the generated response data back to the terminal.

[0991] Input: Generated response data

[0992] Output: Response data sent to the terminal

[0993] Specific operation: The server sends the sales forecast data it generates to the terminal.

[0994] Step 10:

[0995] The terminal displays the response data sent back from the server to the user.

[0996] Input: Response data sent from the server

[0997] Output: Response results displayed to the user

[0998] Specific operation: The terminal receives data from the server, converts it into graphs or tables, and presents it to the user.

[0999] The above outlines the specific steps involved in the system's processing.

[1000] (Application Example 2)

[1001] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1002] Modern autonomous vehicles require real-time analysis of large amounts of data acquired from various sensors and the provision of appropriate feedback to the driver. However, this data often contains missing or outlier values, making accurate prediction and feedback difficult. Furthermore, while generating responses that reflect the driver's emotions would improve driving safety and comfort, current systems have a problem in that emotion analysis and feedback generation are not adequately coordinated.

[1003] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, and means for analyzing the user's emotions using an emotion engine and generating appropriate feedback based on the analysis results. This makes it possible to predict driving conditions accurately in real time and provide feedback that corresponds to the driver's emotions.

[1004] A "data source" refers to a device or system that acquires information from various sensors, databases, and other sources.

[1005] "Preprocessing" refers to the process of modifying acquired data, such as imputing missing values, removing outliers, and standardizing data formats.

[1006] A "generative artificial intelligence model" is a machine learning model trained using pre-processed data, designed to extract specific patterns or insights from that data.

[1007] A "query" refers to a question or request made by a user to a system.

[1008] A "response" refers to the answer or information that a system provides in response to a user's query.

[1009] "Emotional analysis" is a method of recognizing and analyzing a user's emotional state from their voice and facial expressions.

[1010] "Feedback" refers to advice and instructions provided based on user behavior or the state of the system.

[1011] A "unified format" refers to a set of rules and standards for converting data collected from different data sources into a consistent format.

[1012] A "server" is a computer system used for data collection, preprocessing, analysis, and generating responses to users.

[1013] "Real-time" refers to a state where data collection, analysis, and response generation occur instantly, with minimal delay.

[1014] A "user" is a person who uses a system and is the entity that performs a series of operations.

[1015] This invention relates to a driver assistance application for autonomous vehicles, which analyzes vehicle data in real time and provides appropriate feedback and advice to the driver. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[1016] 1. Processing by the server

[1017] The server has the means to collect and preprocess sensor data transmitted from vehicles. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. Based on the preprocessed data, the server trains a generative artificial intelligence model to generate a predictive model for driving conditions. This model is used to predict traffic congestion, speed, distance traveled, and other factors.

[1018] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions from their voice and facial expressions. Based on the results of this emotion analysis, it generates appropriate feedback for the driver.

[1019] The hardware used includes various sensors in the vehicle (cameras, LiDAR, GPS, etc.). Software such as TensorFlow (for AI model training) and EmotionDetector (for emotion analysis) are employed.

[1020] 2. Processing by the terminal

[1021] The terminal provides an interface for users to access the system and enter queries. Users can enter specific questions into the terminal, which then sends those questions to the server in real time. For example, if a user enters "Please tell me the traffic situation up to the next intersection," the terminal will send that question to the server.

[1022] When the server generates a response to a query, the data is sent back to the terminal and displayed in a user-friendly format. For example, traffic congestion prediction data sent back from the server can be converted into a graph and presented to the user. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[1023] 3. User Operation

[1024] Users can access the system through a terminal and enter questions about vehicle driving information. Using the interface provided by the terminal, users can enter specific queries and check the responses from the server. For example, they can enter questions such as, "Please tell me the predicted driving time for the next 30 minutes."

[1025] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining overall traffic information in the initial question, they can ask more detailed questions such as, "Please tell me about the traffic situation in a specific area." Furthermore, the system analyzes the user's voice and facial expressions to analyze their emotions and provides feedback based on the results.

[1026] Specific example

[1027] For example, if you enter a question such as "Please tell me the traffic conditions up to the next intersection," you can send a prompt message to the system like the following.

[1028] What is the next action indicated by the vehicle's sensor_data_url?

[1029] Please analyze the audio data (audio_input) and video data (video_input) of the driver currently in operation.

[1030] Thus, the present invention is a system that can improve driving safety and comfort by providing appropriate feedback and advice in real time through the cooperation of a server, terminal, user, and emotion engine.

[1031] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1032] Step 1:

[1033] The server collects data in real time from various sensors in the vehicle (cameras, LiDAR, GPS, etc.). This data includes mileage, speed, and surrounding traffic information. It receives raw data collected from the sensors as input and prepares it for pre-processing as output.

[1034] Step 2:

[1035] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, it might imputate missing data with the mean value of the surrounding data and remove outliers. It receives raw data collected from sensors as input and generates preprocessed, formatted data as output.

[1036] Step 3:

[1037] The server trains a generative artificial intelligence model based on pre-processed data. This process uses historical data to train a predictive model for traffic and driving conditions. It receives pre-processed, formatted data as input and generates a trained AI model as output.

[1038] Step 4:

[1039] The server collects user voice and facial expression data and analyzes emotions using an emotion engine. For example, it evaluates the driver's stress level and degree of distraction. It receives voice and video data as input and generates user emotion analysis results as output.

[1040] Step 5:

[1041] The server generates appropriate feedback for the driver based on sentiment analysis results and a trained AI model. This feedback is provided through voice guidance and a visual interface. It receives sentiment analysis results and predictions from the AI ​​model as input and generates feedback messages as output.

[1042] Step 6:

[1043] The terminal provides an interface for users to enter queries into the system. For example, a driver could enter, "Please tell me the traffic conditions up to the next intersection." It receives queries from the user as input and sends them to the server as output.

[1044] Step 7:

[1045] The server generates responses to queries sent from the terminal. For example, it uses pre-processed sensor data and an AI model to predict traffic congestion along driving routes and generates the results as feedback. It receives user queries as input and generates response messages as output.

[1046] Step 8:

[1047] The terminal receives response messages sent from the server and displays them in a user-friendly format. For example, it displays traffic congestion prediction results in graph or text format. It receives response messages from the server as input and provides visual feedback as output.

[1048] Step 9:

[1049] Users can review the feedback displayed through their device and ask more detailed questions as needed. For example, they can enter a detailed query such as, "Please tell me about the traffic conditions during a specific time period." The system uses the displayed feedback as input and a new query as output.

[1050] This allows the entire process to be performed in real time, enabling the driver to receive appropriate feedback and advice.

[1051] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1052] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1053] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1054] [Fourth Embodiment]

[1055] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1056] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1057] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1058] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1059] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1060] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1061] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1062] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1063] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1064] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1065] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1066] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1067] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1068] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of three components: a server, terminals, and users.

[1069] 1. Processing by the server

[1070] The server first has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server collects the latest monthly reports from the accounting department's database.

[1071] Because acquired data may contain inconsistencies, preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in employee evaluation data with the average value.

[1072] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[1073] 2. Processing by the terminal

[1074] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[1075] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user.

[1076] 3. User Operation

[1077] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[1078] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data broken down by region?"

[1079] In this way, this system works in cooperation with the server, terminal, and user to effectively utilize internal company data, enabling business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, training of the AI ​​model, provision of a user interface by the terminal, and query input and result confirmation by the user.

[1080] The following describes the processing flow.

[1081] Step 1:

[1082] The server accesses each department's database and collects the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[1083] Step 2:

[1084] The server preprocesses the acquired data. Specifically, it imputes missing values, removes outliers, and standardizes the data format. For example, the server fills in blanks in the evaluation data with the average value.

[1085] Step 3:

[1086] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[1087] Step 4:

[1088] The server trains a generative artificial intelligence model. Using pre-processed data, it trains the AI ​​model to improve its predictive and analytical capabilities for specific tasks. For example, the server uses sales data to train a sales forecast model for the next quarter.

[1089] Step 5:

[1090] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[1091] Step 6:

[1092] The device sends the user's question to the server. The question data is sent to the server in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[1093] Step 7:

[1094] The server searches for the appropriate data in response to a user query. The server searches the database and extracts the relevant data. For example, the server searches the sales database and extracts data related to the sales forecast for the next quarter.

[1095] Step 8:

[1096] The server uses an AI model to generate responses to user queries. For example, the server uses extracted data and the AI ​​model to calculate and generate a sales forecast for the next quarter in text format.

[1097] Step 9:

[1098] The server sends the generated response to the terminal. For example, the server sends sales forecast results back to the terminal.

[1099] Step 10:

[1100] The device receives responses from the server and displays them in a user-friendly format. For example, the device displays sales forecast data to the user in graph and text format.

[1101] Step 11:

[1102] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please show me the data that supports the prediction." In this case, the process from step 5 onwards is repeated.

[1103] (Example 1)

[1104] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1105] Internal company data is often scattered across different departments, and its format and content are frequently inconsistent. This makes data sharing between departments difficult, hindering integrated analysis. Furthermore, incomplete or outlier data prevents accurate analysis and prediction. A system is needed to address these issues and effectively utilize internal company data.

[1106] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1107] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, and means for training a generative artificial intelligence model using the preprocessed data. This enables means for imputing missing values ​​in the collected data, removing outliers, standardizing the data format, and visually displaying the response to the query.

[1108] "Data source" refers to the organization or system that provides data, such as various departments within a company or external data sources.

[1109] "Data preprocessing" refers to the process of converting raw data into a format suitable for analysis and modeling by imputing missing values, removing outliers, and standardizing data formats.

[1110] A "generative artificial intelligence model" refers to a model that uses machine learning and deep learning techniques to learn patterns and trends from data and predict future data and answers.

[1111] A "query" refers to a question or request that a user sends to a system to obtain specific information.

[1112] "Response" refers to the answers or information that the system generates based on user queries.

[1113] "Visual representation methods" refer to ways of presenting data and forecast results in a format that is easy for users to understand, using graphs, charts, dashboards, and so on.

[1114] "Imputing missing values" refers to the process of filling in missing (blank) data with the mean or other appropriate values.

[1115] "Removing outliers" refers to the process of detecting, excluding, or correcting extreme values ​​or inaccurate data points within a dataset.

[1116] "Data format unification" refers to the process of transforming and standardizing data so that it has a consistent format and structure.

[1117] This invention is a system that integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of servers, terminals, and users.

[1118] Server-based processing

[1119] The server first retrieves data from each department's data collection source. Specifically, the server accesses each department's database and periodically extracts the necessary data. For example, it retrieves the latest monthly report from the accounting department's database.

[1120] The acquired data must undergo preprocessing, including imputation of missing values, removal of outliers, and standardization of data formats. The Python Pandas library is used for this preprocessing. For example, blank fields in employee evaluation data are filled with the average value.

[1121] Using pre-processed data, the server trains a generative artificial intelligence (AI) model. Machine learning libraries such as TensorFlow and PyTorch are used to train a sales forecast model for the next quarter using historical sales data from the company.

[1122] Processing by the terminal

[1123] The terminal provides an interface for users to access the system and enter questions and queries. For example, if a user enters "Please tell me the sales forecast for the next quarter," that question is sent to the server in real time.

[1124] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, sales forecast results can be converted into a graph and presented to the user. JavaScript frameworks (such as React.js or Vue.js) are used for this display.

[1125] User operation

[1126] Users access the system through their terminals and input questions about the information they need. For example, they might ask, "How effective was this month's marketing campaign?"

[1127] Users can review the results displayed on their device and ask further questions if necessary. For example, after obtaining total sales data, they might ask additional questions such as, "Could you please provide sales data broken down by region?"

[1128] This system allows the server to perform a series of processes including data collection, preprocessing, and AI model training, while the terminal provides a user interface, allowing the user to enter queries and obtain results. An example of a prompt would be, "Retrieve the latest monthly report data, fill in missing values ​​with the mean, and train the AI ​​model to forecast sales for the next quarter."

[1129] This system efficiently utilizes data within a company, enabling improved operational efficiency and faster decision-making.

[1130] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1131] Step 1: Data Collection

[1132] The server accesses each department's database and extracts the necessary data. Specifically, it retrieves the latest monthly report from the accounting department's database. During this process, it uses SQL queries to collect the data and saves it as a CSV file.

[1133] Input: Database of each department

[1134] Output: Acquired raw data (CSV file)

[1135] Specific actions:

[1136] The server issues an SQL query to the accounting department's database.

[1137] Extract the latest monthly report data.

[1138] Save the extracted data as a CSV file.

[1139] Step 2: Data Preprocessing

[1140] The server preprocesses the acquired data. First, it imputes missing values, then removes outliers, and finally standardizes the data format. This series of processes is performed using the Python Pandas library.

[1141] Input: Acquired raw data (CSV file)

[1142] Output: Preprocessed data

[1143] Specific actions:

[1144] Load data from a CSV file

[1145] Missing values ​​are imputed using the mean.

[1146] Removal of outliers (e.g., negative sales data)

[1147] Standardize data formats

[1148] Step 3: Training the AI ​​model

[1149] The server uses pre-processed data to train a generative artificial intelligence (AI) model. TensorFlow and PyTorch are used to build a sales forecasting model.

[1150] Input: Preprocessed data

[1151] Output: Trained AI model

[1152] Specific actions:

[1153] The data is split into features (X) and the target variable (y).

[1154] Building an AI Model

[1155] Model compilation and training

[1156] Step 4: Entering User Queries

[1157] Users access the system through their terminals and enter queries requesting specific information. For example, if they want to know the sales forecast for the next quarter, they would enter that information.

[1158] Input: User query

[1159] Output: Request sent from terminal to server

[1160] Specific actions:

[1161] The user enters a question into the browser interface.

[1162] The entered query is sent to the server by JavaScript.

[1163] Step 5: Generating the query response

[1164] The server generates responses based on user queries. It uses a pre-trained AI model to make predictions and generate the results.

[1165] Input: User query, pre-trained AI model

[1166] Output: Generated response data

[1167] Specific actions:

[1168] Processing user queries

[1169] Predictive execution using AI models

[1170] Generate results and return them to the terminal.

[1171] Step 6: Displaying the results

[1172] The terminal receives the results sent back from the server and displays them visually. Specifically, it converts sales forecast data into graphs and charts and presents them to the user.

[1173] Input: Response data from the server

[1174] Output: The result visually displayed to the user.

[1175] Specific actions:

[1176] Received response data in JSON format.

[1177] Convert data into graphs and charts (using D3.js, Highcharts, etc.)

[1178] Displayed in the user interface

[1179] Through these steps, the collaboration of servers, terminals, and users enables the efficient collection, preprocessing, and analysis of data within the enterprise, and the rapid delivery of the results.

[1180] (Application Example 1)

[1181] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1182] Effective production management in factories is crucial for integrating data from various departments and equipment, understanding production status in real time, and ensuring efficient operations. However, conventional systems often lack sufficient data integration and analysis capabilities, making it difficult for managers to make quick and accurate decisions. To address this challenge, a system is needed that collects and preprocesses data in real time and efficiently analyzes and displays it.

[1183] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1184] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing and displaying the data in real time, means for generating responses to user queries, and means for providing the generated responses to the user. This enables effective integration of production data within the factory, as well as real-time monitoring and optimization.

[1185] A "data source" refers to the location or device from which data is acquired, such as various sensors, databases, and information systems.

[1186] "Preprocessing" refers to the process of preparing acquired data for analysis, including imputing missing values, removing outliers, and standardizing data formats.

[1187] A "generative artificial intelligence model" is an AI model that uses collected and pre-processed data to automatically learn specific tasks and perform predictions and analyses.

[1188] "Means for analyzing and displaying data in real time" refers to tools and systems that have the function of analyzing production data within a factory in real time and immediately visualizing and displaying the results to the user.

[1189] A "query" is a question or instruction that a user asks the system to request specific information.

[1190] A "response" refers to the data or information that a generative artificial intelligence model or system provides in response to a user's query.

[1191] The embodiments for carrying out this invention are described below. The real-time production management system is a system for aggregating data within a factory and monitoring, analyzing, and displaying the production status in real time. Its main components are a server, terminals, and users, which work together in cooperation.

[1192] 1. Processing by the server

[1193] The server uses the following hardware and software:

[1194] Hardware: Sensor network within the factory, work robots, server units

[1195] Software: Sensor data ingestion platform for data collection, Python scripts for data processing, TensorFlow for AI model building.

[1196] The server first automatically acquires data from each data source. A concrete example of this is the process of acquiring real-time production data from sensors installed on each production line in a factory. The data is first aggregated on the server, and then preprocessing is performed. Preprocessing includes imputing missing data values, removing outliers, and standardizing data formats. For example, missing parts of the sensor data from production equipment are filled in with average values.

[1197] Using pre-processed data, a generative artificial intelligence model is trained. Based on historical data, the AI ​​model is trained to build a model for predicting and analyzing real-time production status. For example, TensorFlow can be used to train a model that predicts the operating rate of a production line.

[1198] 2. Processing by the terminal

[1199] The terminal provides a user interface and a means for users to check production status in real time. For example, it displays graphed production data on the administrator's PC or tablet using a dashboard tool (e.g., Grafana). When a user enters a query such as "What is the current utilization rate of line 2?", the terminal sends this query to the server.

[1200] The server generates a response to the query and sends that data back to the terminal. The terminal converts the received response data into a visually easy-to-understand format and displays it to the user. For example, it might display the predicted uptime data sent back from the server as a graph, making it easy for administrators to understand.

[1201] 3. User Operation

[1202] Users access the system through their terminal and ask questions about the information they need. For example, they might enter a prompt such as, "Predict and display the utilization rate of line 1 for the next week." Based on this prompt, the server uses a generative artificial intelligence model to perform the necessary calculations and generate the result.

[1203] Based on the results confirmed by the user, the system optimizes production plans, identifies problems, and asks further detailed questions. This system allows users to understand the factory's production status in real time, enabling rapid decision-making.

[1204] Examples of prompt statements:

[1205] "Please predict and display the utilization rate of Line 1 for the next week."

[1206] In this way, a real-time production management system can significantly improve factory production efficiency by having the server, terminals, and users work together as a unified whole.

[1207] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1208] Step 1: Data Collection

[1209] The server acquires data in real time from sensors and databases installed within the factory. At this stage, data such as production line utilization rates, inventory status, and the number of defective products are collected. The input is production data from sensors and databases, and the output is the initial production data stored on the server.

[1210] Step 2: Data preprocessing

[1211] The server preprocesses the collected data. This includes tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, if a production equipment sensor temporarily malfunctions and data is lost, the missing portion is filled in with the average value. The input is the initial production data, and the output is the preprocessed, clean data.

[1212] Step 3: Training the AI ​​model

[1213] The server trains a generative artificial intelligence model using preprocessed data. The model is trained to take in historical data and predict future production conditions. For example, TensorFlow is used to build a model for predicting production line utilization. The input is preprocessed data, and the output is the trained AI model.

[1214] Step 4: Receiving the query

[1215] The terminal receives queries from users. For example, an administrator might enter a query such as, "Predict and display the utilization rate of line 1 for the next week." The input is the query entered by the user into the terminal, and the output is that the query has been sent to the server.

[1216] Step 5: Generating responses to queries

[1217] The server uses an AI model to perform the necessary calculations based on the received query. It generates data according to the user's request, for example, predicting the production line's operating rate for the next week. The input is the user's query and the trained AI model, and the output is the response data to the query.

[1218] Step 6: Display the response

[1219] The terminal receives response data sent back from the server and displays it in a user-friendly format. For example, it can use Grafana to graph predictive data and display it on the administrator's PC or tablet. The input is the response data received from the server, and the output is the display of the visualized data.

[1220] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1221] The embodiments for carrying out the present invention are described below. This system effectively integrates internal company data, strengthens interdepartmental collaboration, and improves operational efficiency. This system mainly consists of a server, terminals, users, and an emotion engine.

[1222] 1. Processing by the server

[1223] The server has the means to retrieve data from each department's data collection source. This includes having access rights to each department's database and a process to automatically retrieve the necessary data. For example, the server might collect the latest monthly reports from the accounting department's database.

[1224] The acquired data may contain inconsistencies if left as is, so preprocessing is necessary. The server has the means to perform preprocessing, such as imputing missing values, removing outliers, and standardizing data formats. For example, the server may fill in blanks in the evaluation data with the mean value.

[1225] Using pre-processed data, the server has the means to train generative artificial intelligence models. This allows it to train AI models to extract specific insights from enterprise data. For example, the server can use historical sales data to train a sales forecast model for the next quarter.

[1226] Furthermore, the server has an emotion engine built in, which has the means to analyze the user's emotions. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[1227] 2. Processing by the terminal

[1228] The terminal provides an interface for users to access the system and enter questions and queries. Questions entered by the user are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[1229] When the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and displays it in a user-friendly format. For example, it might convert sales forecast data sent back from the server into a graph and present it to the user. The terminal also receives feedback from an emotion engine and adjusts the displayed content according to the user's emotions.

[1230] 3. User Operation

[1231] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[1232] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[1233] In this way, this system works in conjunction with four elements: the server, terminal, user, and emotion engine, to effectively utilize internal company data and enable business efficiency and rapid decision-making. Specifically, the system integrates data collection and preprocessing by the server, AI model training, emotion analysis, user interface provision by the terminal, and query input and result confirmation by the user.

[1234] The following describes the processing flow.

[1235] Step 1:

[1236] The server accesses each department's database and automatically retrieves the necessary data. For example, the server retrieves the latest monthly report from the accounting department's database.

[1237] Step 2:

[1238] The server preprocesses the acquired data. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. For example, the server fills in blanks in the evaluation data with the mean value.

[1239] Step 3:

[1240] The server centralizes pre-processed data and converts it into a unified format. This ensures that data from multiple data sources is stored in a consistent format. For example, the server combines the contents of CSV and Excel files into a single database.

[1241] Step 4:

[1242] The server uses pre-processed data to train a generative artificial intelligence model. For example, the server uses historical sales data to train a sales forecast model for the next quarter.

[1243] Step 5:

[1244] Users access the system through the terminal interface and enter questions or queries. For example, a user might type, "Please tell me the sales forecast for the next quarter."

[1245] Step 6:

[1246] The device sends the user's question to the server. The question data is sent in the form of an API request. For example, the device sends the query "Please tell me the sales forecast for the next quarter" to the server.

[1247] Step 7:

[1248] The server searches for relevant data in response to user queries and generates appropriate responses. For example, the server searches a sales database, extracts data related to the next quarter's sales forecast, and uses an AI model to generate the sales forecast.

[1249] Step 8:

[1250] The server sends the generated response data back to the terminal. For example, the server sends sales forecast results back to the terminal.

[1251] Step 9:

[1252] The device receives a response from the server and displays it to the user. For example, the device displays sales forecast data to the user in graph and text format.

[1253] Step 10:

[1254] The user reviews the results, and the emotion engine analyzes the user's emotions from their voice or text. For example, the user might look at the results and enter a comment such as "I feel relieved."

[1255] Step 11:

[1256] Based on the emotional results analyzed by the emotion engine, the server adjusts its response. For example, if a user expresses negative emotions, the server provides additional information to reassure them.

[1257] Step 12:

[1258] The user checks the display on their device and asks further questions as needed. For example, the user might ask, "Please tell me the data that forms the basis of the prediction." In this case, the process from step 5 onwards is repeated.

[1259] (Example 2)

[1260] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1261] Internal company data is often stored in different databases for each department, and because each database has a different data format and structure, it is difficult to integrate and use. Furthermore, while there is a need to provide responses that align with user emotions and needs, current systems make it extremely difficult to meet this requirement. This hinders operational efficiency and rapid decision-making.

[1262] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1263] In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, means for analyzing the user's emotions, means for generating responses to user queries, and means for providing the generated responses to the user. This makes it possible to unify and integrate data from each department and provide optimal responses that meet the user's emotions and needs.

[1264] A "data source" refers to a system or database that extracts data from a source.

[1265] "Means of acquiring data" refers to methods of collecting necessary information from other systems and databases by utilizing network connections or APIs.

[1266] "Methods for preprocessing data" refer to processing methods used to impute missing values, remove outliers, and standardize data formats.

[1267] A "generative artificial intelligence model" refers to a type of artificial intelligence that has the ability to learn from large amounts of data and generate new data and insights.

[1268] "Methods for training" refer to methods of using data to train an AI model so that it can perform a specific task.

[1269] "Means of analyzing user emotions" refers to methods that read emotions from text or voice input by the user and generate appropriate responses based on those emotions.

[1270] "Means of generating responses to queries" refers to methods of providing appropriate answers or data based on questions or requests from users.

[1271] "Means of providing a response to the user" refers to the method or procedure for displaying the generated response on the user's device.

[1272] Modes for carrying out the invention

[1273] System Overview

[1274] This invention is a system that effectively integrates internal corporate data, strengthens interdepartmental collaboration, and improves operational efficiency. This system primarily consists of a server, terminals, users, and an emotion engine.

[1275] Server-based processing

[1276] The server has the means to retrieve data from each department's data collection source. This means includes having access rights to each department's database and a process to automatically retrieve the necessary data. The software used includes SQL database management systems and API access tools.

[1277] The acquired data may contain inconsistencies and therefore requires preprocessing. The server has preprocessing capabilities, including imputing missing values, removing outliers, and standardizing data formats. The software used for this includes the Python Pandas library and data cleansing tools.

[1278] Using pre-processed data, the server has the means to train generative artificial intelligence (AI) models. This involves using generative AI frameworks such as TensorFlow and PyTorch. For example, these tools are used to train a sales forecast model for the next quarter using historical sales data.

[1279] The server incorporates an emotion engine, which includes IBM Watson and Google's Natural Language API. The emotion engine recognizes emotions from the user's voice and text, and adjusts the response based on the analysis results.

[1280] Processing by the terminal

[1281] The terminal provides an interface for users to access the system and enter questions and queries. This includes web browser-based forms and dedicated applications. Questions entered by users are sent to the server in real time. For example, if a user enters "Please tell me the sales forecast for the next quarter," the terminal sends that question to the server.

[1282] Once the server generates a response to a query, the data is sent back to the terminal. The terminal receives this data and can convert it into a user-friendly format, such as a graph or table. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[1283] User operation

[1284] Users access the system through a terminal and ask questions about the information they need. Using the interface provided by the terminal, users enter specific queries. For example, they might ask, "What was the effectiveness of this month's marketing campaign?"

[1285] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining total sales data in the initial question, they can ask additional questions such as, "Could you please provide sales data by region?" The emotion engine analyzes the user's emotions and optimizes the response, providing answers that are more appropriate to their feelings.

[1286] Examples of prompt statements

[1287] Server-based processing

[1288] "The server should collect the latest monthly reports from the accounting department's database."

[1289] Processing by the terminal

[1290] "When a user asks for the sales forecast for the next quarter, the device should send that question to the server."

[1291] User operation

[1292] "Users should use their devices to ask questions about the effectiveness of this month's marketing campaign."

[1293] In this way, this system works in cooperation with four parties: the server, terminal, user, and emotion engine, enabling effective use of internal company data and facilitating business efficiency and rapid decision-making.

[1294] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1295] Step 1:

[1296] The server retrieves data from the data collection sources of each department. Specifically, the server uses SQL queries and API requests to access the databases of each department, such as the accounting and sales departments, and retrieves the necessary data.

[1297] Input: Request for access to departmental databases

[1298] Output: Datasets obtained from each department

[1299] Step 2:

[1300] The server preprocesses the acquired data. This processing includes imputing missing values, removing outliers, and standardizing the data format. The software used is the Python Pandas library.

[1301] Input: Raw data obtained

[1302] Output: Preprocessed data

[1303] Specific operation: The server uses Pandas to impute missing values ​​with the mean, remove outliers, and standardize the data format.

[1304] Step 3:

[1305] The server uses pre-processed data to train a generative artificial intelligence (AI) model. This is done using tools such as TensorFlow or PyTorch.

[1306] Input: Preprocessed dataset

[1307] Output: Trained AI model

[1308] Specific operation: The server uses TensorFlow to train a sales forecast model for the next quarter based on past sales data.

[1309] Step 4:

[1310] The server analyzes the user's emotions using an emotion engine. This analysis utilizes IBM Watson and Google's Natural Language API.

[1311] Input: User input text or voice

[1312] Output: Emotion analysis results

[1313] Specific operation: The server uses IBM Watson to analyze the user's emotions from their text input and customizes the response based on the results.

[1314] Step 5:

[1315] The terminal provides the user with an interface for entering questions. This can be achieved through a web browser form or a dedicated application.

[1316] Input: User query

[1317] Output: User interface screen

[1318] Specific action: The device displays an input form in a web browser, allowing the user to enter a question.

[1319] Step 6:

[1320] The user enters a query via their terminal. For example, they might enter a query such as, "Please tell me the sales forecast for the next quarter."

[1321] Input: User query

[1322] Output: Input query

[1323] Specific action: The user types a question into the input form on the device and presses the submit button.

[1324] Step 7:

[1325] The terminal sends the query entered by the user to the server.

[1326] Input: Query entered by the user

[1327] Output: Query sent to the server

[1328] Specific operation: The terminal sends user queries to the server in real time.

[1329] Step 8:

[1330] The server generates a response to the user's query.

[1331] Input: User queries and trained AI models

[1332] Output: Generated response data

[1333] Specific operation: The server uses a pre-trained AI model to generate sales forecast data in response to the user's questions.

[1334] Step 9:

[1335] The server sends the generated response data back to the terminal.

[1336] Input: Generated response data

[1337] Output: Response data sent to the terminal

[1338] Specific operation: The server sends the sales forecast data it generates to the terminal.

[1339] Step 10:

[1340] The terminal displays the response data sent back from the server to the user.

[1341] Input: Response data sent from the server

[1342] Output: Response results displayed to the user

[1343] Specific operation: The terminal receives data from the server, converts it into graphs or tables, and presents it to the user.

[1344] The above outlines the specific steps involved in the system's processing.

[1345] (Application Example 2)

[1346] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1347] Modern autonomous vehicles require real-time analysis of large amounts of data acquired from various sensors and the provision of appropriate feedback to the driver. However, this data often contains missing or outlier values, making accurate prediction and feedback difficult. Furthermore, while generating responses that reflect the driver's emotions would improve driving safety and comfort, current systems have a problem in that emotion analysis and feedback generation are not adequately coordinated.

[1348] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring data from a data collection source, means for preprocessing the acquired data, means for training a generative artificial intelligence model using the preprocessed data, and means for analyzing the user's emotions using an emotion engine and generating appropriate feedback based on the analysis results. This makes it possible to predict driving conditions accurately in real time and provide feedback that corresponds to the driver's emotions.

[1349] A "data source" refers to a device or system that acquires information from various sensors, databases, and other sources.

[1350] "Preprocessing" refers to the process of modifying acquired data, such as imputing missing values, removing outliers, and standardizing data formats.

[1351] A "generative artificial intelligence model" is a machine learning model trained using pre-processed data, designed to extract specific patterns or insights from that data.

[1352] A "query" refers to a question or request made by a user to a system.

[1353] A "response" refers to the answer or information that a system provides in response to a user's query.

[1354] "Emotional analysis" is a method of recognizing and analyzing a user's emotional state from their voice and facial expressions.

[1355] "Feedback" refers to advice and instructions provided based on user behavior or the state of the system.

[1356] A "unified format" refers to a set of rules and standards for converting data collected from different data sources into a consistent format.

[1357] A "server" is a computer system used for data collection, preprocessing, analysis, and generating responses to users.

[1358] "Real-time" refers to a state where data collection, analysis, and response generation occur instantly, with minimal delay.

[1359] A "user" is a person who uses a system and is the entity that performs a series of operations.

[1360] This invention relates to a driver assistance application for autonomous vehicles, which analyzes vehicle data in real time and provides appropriate feedback and advice to the driver. This system operates through the cooperation of a server, terminal, user, and emotion engine.

[1361] 1. Processing by the server

[1362] The server has the means to collect and preprocess sensor data transmitted from vehicles. This preprocessing includes imputing missing values, removing outliers, and standardizing data formats. Based on the preprocessed data, the server trains a generative artificial intelligence model to generate a predictive model for driving conditions. This model is used to predict traffic congestion, speed, distance traveled, and other factors.

[1363] Furthermore, the server incorporates an emotion engine that analyzes the user's emotions from their voice and facial expressions. Based on the results of this emotion analysis, it generates appropriate feedback for the driver.

[1364] The hardware used includes various sensors in the vehicle (cameras, LiDAR, GPS, etc.). Software such as TensorFlow (for AI model training) and EmotionDetector (for emotion analysis) are employed.

[1365] 2. Processing by the terminal

[1366] The terminal provides an interface for users to access the system and enter queries. Users can enter specific questions into the terminal, which then sends those questions to the server in real time. For example, if a user enters "Please tell me the traffic situation up to the next intersection," the terminal will send that question to the server.

[1367] When the server generates a response to a query, the data is sent back to the terminal and displayed in a user-friendly format. For example, traffic congestion prediction data sent back from the server can be converted into a graph and presented to the user. The terminal also receives feedback from the emotion engine and adjusts the displayed content according to the user's emotions.

[1368] 3. User Operation

[1369] Users can access the system through a terminal and enter questions about vehicle driving information. Using the interface provided by the terminal, users can enter specific queries and check the responses from the server. For example, they can enter questions such as, "Please tell me the predicted driving time for the next 30 minutes."

[1370] Users can review the results displayed on their device and ask further detailed questions as needed. For example, after obtaining overall traffic information in the initial question, they can ask more detailed questions such as, "Please tell me about the traffic situation in a specific area." Furthermore, the system analyzes the user's voice and facial expressions to analyze their emotions and provides feedback based on the results.

[1371] Specific example

[1372] For example, if you enter a question such as "Please tell me the traffic conditions up to the next intersection," you can send a prompt message to the system like the following.

[1373] What is the next action indicated by the vehicle's sensor_data_url?

[1374] Please analyze the audio data (audio_input) and video data (video_input) of the driver currently in operation.

[1375] Thus, the present invention is a system that can improve driving safety and comfort by providing appropriate feedback and advice in real time through the cooperation of a server, terminal, user, and emotion engine.

[1376] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1377] Step 1:

[1378] The server collects data in real time from various sensors in the vehicle (cameras, LiDAR, GPS, etc.). This data includes mileage, speed, and surrounding traffic information. It receives raw data collected from the sensors as input and prepares it for pre-processing as output.

[1379] Step 2:

[1380] The server preprocesses the collected data. Specifically, it performs tasks such as imputing missing values, removing outliers, and standardizing data formats. For example, it might imputate missing data with the mean value of the surrounding data and remove outliers. It receives raw data collected from sensors as input and generates preprocessed, formatted data as output.

[1381] Step 3:

[1382] The server trains a generative artificial intelligence model based on pre-processed data. This process uses historical data to train a predictive model for traffic and driving conditions. It receives pre-processed, formatted data as input and generates a trained AI model as output.

[1383] Step 4:

[1384] The server collects user voice and facial expression data and analyzes emotions using an emotion engine. For example, it evaluates the driver's stress level and degree of distraction. It receives voice and video data as input and generates user emotion analysis results as output.

[1385] Step 5:

[1386] The server generates appropriate feedback for the driver based on sentiment analysis results and a trained AI model. This feedback is provided through voice guidance and a visual interface. It receives sentiment analysis results and predictions from the AI ​​model as input and generates feedback messages as output.

[1387] Step 6:

[1388] The terminal provides an interface for users to enter queries into the system. For example, a driver could enter, "Please tell me the traffic conditions up to the next intersection." It receives queries from the user as input and sends them to the server as output.

[1389] Step 7:

[1390] The server generates responses to queries sent from the terminal. For example, it uses pre-processed sensor data and an AI model to predict traffic congestion along driving routes and generates the results as feedback. It receives user queries as input and generates response messages as output.

[1391] Step 8:

[1392] The terminal receives response messages sent from the server and displays them in a user-friendly format. For example, it displays traffic congestion prediction results in graph or text format. It receives response messages from the server as input and provides visual feedback as output.

[1393] Step 9:

[1394] Users can review the feedback displayed through their device and ask more detailed questions as needed. For example, they can enter a detailed query such as, "Please tell me about the traffic conditions during a specific time period." The system uses the displayed feedback as input and a new query as output.

[1395] This allows the entire process to be performed in real time, enabling the driver to receive appropriate feedback and advice.

[1396] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1397] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1398] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1399] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1400] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1401] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1402] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1403] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1404] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1405] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1406] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1407] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1408] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1409] 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.

[1410] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1411] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1412] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1413] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1414] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1415] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1416] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1417] The following is further disclosed regarding the embodiments described above.

[1418] (Claim 1)

[1419] Means of obtaining data from data sources,

[1420] A means for preprocessing the acquired data,

[1421] A means for training a generative artificial intelligence model using preprocessed data,

[1422] A means of generating a response to a query from a user,

[1423] Means for providing the generated response to the user,

[1424] A system that includes this.

[1425] (Claim 2)

[1426] The system according to claim 1, wherein the data collection source spans multiple departments.

[1427] (Claim 3)

[1428] The system according to claim 1, comprising means for centralizing pre-processed data and converting it into a unified format.

[1429] "Example 1"

[1430] (Claim 1)

[1431] Means of obtaining data from data sources,

[1432] A means for preprocessing the acquired data,

[1433] A means for training a generative artificial intelligence model using preprocessed data,

[1434] A means of generating a response to a query from a user,

[1435] Means for providing the generated response to the user,

[1436] A means of visually displaying the response to a query,

[1437] A means of imputing missing values ​​in the collected data,

[1438] Means for removing outliers,

[1439] Means for standardizing data formats,

[1440] A system that includes this.

[1441] (Claim 2)

[1442] The system according to claim 1, wherein the data collection source spans multiple departments.

[1443] (Claim 3)

[1444] The system according to claim 1, comprising means for centralizing pre-processed data and converting it into a unified format.

[1445] "Application Example 1"

[1446] (Claim 1)

[1447] Means of obtaining data from data sources,

[1448] A means for preprocessing the acquired data,

[1449] A means for training a generative artificial intelligence model using preprocessed data,

[1450] A means of analyzing and displaying data in real time,

[1451] A means of generating a response to a query from a user,

[1452] Means for providing the generated response to the user,

[1453] A system that includes this.

[1454] (Claim 2)

[1455] The system according to claim 1, wherein the data collection source spans multiple departments.

[1456] (Claim 3)

[1457] The system according to claim 1, comprising means for centralizing pre-processed data and converting it into a unified format.

[1458] "Example 2 of combining an emotion engine"

[1459] (Claim 1)

[1460] Means of obtaining data from data sources,

[1461] A means for preprocessing the acquired data,

[1462] A means for training a generative artificial intelligence model using preprocessed data,

[1463] A means of analyzing user emotions,

[1464] A means of generating a response to a query from a user,

[1465] Means for providing the generated response to the user,

[1466] A system that includes this.

[1467] (Claim 2)

[1468] The system according to claim 1, wherein the data collection source spans multiple departments.

[1469] (Claim 3)

[1470] The system according to claim 1, comprising means for centralizing pre-processed data and converting it into a unified format.

[1471] "Application example 2 when combining with an emotional engine"

[1472] (Claim 1)

[1473] Means for acquiring data from data sources,

[1474] A means for preprocessing the acquired data,

[1475] A means for training a generative artificial intelligence model using preprocessed data,

[1476] A means of generating a response to a query from a user,

[1477] Means for providing the generated response to the user,

[1478] A means for analyzing acquired data and user sentiment, and for generating appropriate feedback based on the analysis results,

[1479] A system that includes this.

[1480] (Claim 2)

[1481] The system according to claim 1, wherein the data collection source spans multiple regions.

[1482] (Claim 3)

[1483] The system according to claim 1, comprising means for centralizing pre-processed data and converting it into a unified format. [Explanation of Symbols]

[1484] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of obtaining data from data sources, A means for preprocessing the acquired data, A means for training a generative artificial intelligence model using preprocessed data, A means of generating a response to a query from a user, Means for providing the generated response to the user, A system that includes this.

2. The system according to claim 1, wherein the data collection source spans multiple departments.

3. The system according to claim 1, which includes means for centralizing pre-processed data and converting it into a unified format.

Images