System

Abstract

A system is provided.SOLUTION: This system includes a means for collecting necessary data from a data source, a means for analyzing the collected data, and a means for visually displaying an analysis result.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Modern businesses face an environment of high uncertainty regarding global trends and market changes. In these circumstances, traditional experience and data often become ineffective. Companies must be able to grasp the current situation in real time and respond quickly and appropriately. However, current technology lacks the means to effectively analyze and visually display the vast amounts of data collected. Furthermore, there are few ways to continuously improve visualizations based on user feedback. This makes it difficult for businesses to achieve key performance indicators (KPIs) in these uncertain times. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides the following means. First, a system is constructed that includes means for collecting necessary data from data sources. This means makes it possible to obtain necessary data from specified data sources in real time. Next, a system is provided that includes means for analyzing the collected data using a machine learning model. This analysis makes it possible to discover important patterns and trends from the collected data. Furthermore, a system is provided that includes means for converting the analysis results into visual representations such as graphs, heat maps, and trend lines, and displaying them to users in a visually easy-to-understand manner. Finally, a system is provided that includes means for collecting feedback from users and updating visualized information based on the feedback. This allows the visualized information to be continuously improved by reflecting real-time feedback provided by users, helping companies achieve their KPIs even in uncertain times.

[0006] "Data source" refers to the information source from which the required data is obtained, such as an external API or an internal database.

[0007] "Analysis" refers to the processing performed on collected data to discover patterns and trends.

[0008] A "machine learning model" refers to an algorithm or model used to make predictions or analyses based on collected data.

[0009] "Visualization" refers to converting analytical results into visual representations such as graphs, heat maps, and trend lines, and displaying them in an easy-to-understand manner for users.

[0010] "Feedback" refers to opinions and suggestions for improvement provided by users regarding the system's output results.

[0011] "Visual display" refers to the presentation of analytical results in a visual format (e.g., graphs, heat maps, trend lines).

[0012] "Means" refers to the methods or devices used to achieve a particular purpose. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

[0016] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0017] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0018] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0019] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0026] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0033] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0034] This invention is a system that provides high-quality visualization of the information needed for companies to respond quickly to uncertain market environments and achieve key performance indicators (KPIs).

[0035] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0036] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0037] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0038] Users can analyze the displayed visualization information and create specific action plans. They can also provide feedback as needed. For example, they can send feedback such as "We need more detailed sales data for the first quarter" to the server.

[0039] The server analyzes the collected feedback and identifies areas for improvement in the visualization. It then updates the visualization based on the feedback and presents it to the user again. Through this process, the system continuously improves and delivers the most effective information to users.

[0040] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, and feedback, and can provide information that allows companies to respond quickly and effectively to uncertain market environments. As a result, companies can not only more easily achieve their KPIs, but also make more accurate decisions.

[0041] The processing flow will be explained below.

[0042] Step 1:

[0043] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0044] Step 2:

[0045] The server sends requests to designated data sources to retrieve the required data. For example, the server may send requests to a market trends API to retrieve external market data, or query an internal database to gather sales data.

[0046] Step 3:

[0047] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0048] Step 4:

[0049] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0050] Step 5:

[0051] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0052] Step 6:

[0053] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0054] Step 7:

[0055] The user can provide feedback on the displayed visualization, for example, "I need more detailed sales data for the first quarter" to the server.

[0056] Step 8:

[0057] The server analyzes the collected feedback, identifies areas for improvement in the visualization, and updates and re-presents the visualization to the user based on the feedback.

[0058] Step 9:

[0059] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0060] Example 1

[0061] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0062] In order for companies to respond quickly to uncertain market conditions and achieve key performance indicators (KPIs), it is difficult to efficiently collect, analyze, visualize, and incorporate feedback from high-quality information. In particular, when data is collected from a wide range of sources, information collection and analysis can be a time-consuming process, resulting in the inability to make timely and effective decisions.

[0063] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0064] In this invention, the server includes means for a user to specify required information from a data source, means for collecting information based on the data source specified by the user, means for analyzing the collected information using a machine learning model or a statistical algorithm, means for converting the analysis results into a visual representation such as a graph, a heat map, or a trend line, means for displaying the visual representation on a terminal, means for collecting and analyzing feedback from users, and means for improving the visual representation based on the feedback, thereby enabling companies to respond quickly and effectively to uncertain market environments and make accurate decisions based on high-quality information.

[0065] "Data source" refers to the source or information source from which data is obtained.

[0066] "Information" includes data and content collected from data sources.

[0067] "User" refers to the end-user who operates the system and specifies, collects, analyzes, and provides feedback on required information.

[0068] "Server" refers to a central processing unit that collects, analyzes, visualizes, processes feedback, etc.

[0069] A "machine learning model" is an algorithm or model used in data analysis to derive patterns and predictions from data.

[0070] A "statistical algorithm" is a mathematical model or computational method used to analyze data and derive results.

[0071] "Analysis results" refers to the insights and conclusions obtained after analyzing data using machine learning models and statistical algorithms.

[0072] "Visual representation" refers to techniques and methods for presenting analytical results in easy-to-understand charts and graphs.

[0073] A "graph" is a form of visual display used to show data values ​​and trends.

[0074] A "heat map" is a visual representation that uses colors to show the relationships and distributions between specific variables.

[0075] A "trend line" is a line expressed as a straight or curved line that shows changes or trends in data.

[0076] "Terminal" refers to a device that allows a user to communicate with a server and display and manipulate data and visual presentations.

[0077] "Feedback" means any additional requests, comments or improvements provided by a User.

[0078] "High quality" means that the data and information are accurate, reliable, and useful as information for users to use in making decisions.

[0079] This invention is a system that provides high-quality visualization of the information companies need to respond quickly and effectively to uncertain market environments and achieve key performance indicators (KPIs).

[0080] First, the user specifies the information they want to collect from a data source (e.g., a market trend API or an internal sales database). Specifically, the user enters a request through the system interface, such as "collect data from the market trend API for the past six months."

[0081] The server collects information based on the data source specified by the user. In the case of an external API, the server sends a request, retrieves the response data in JSON format, and analyzes it. Specifically, the server sends a request such as "https: / / api.marketdata.com / v1 / trends?duration=6months" and analyzes the resulting data. In the case of an internal database, the server executes an SQL query to collect the required data. For example, a query such as "SELECT FROM sales_data WHERE date >= '2023-04-01'" is used.

[0082] The collected information is analyzed by the server. This analysis uses machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas). The server preprocesses the data and cleanses it by removing unnecessary data and missing values. For example, the server uses pandas to remove missing values ​​(e.g., "cleaned_data = raw_data.dropna()"), and then uses a scikit-learn linear regression model (e.g., "model.fit(X, y)") to predict sales trends.

[0083] Next, the server generates graphs, heat maps, and trend lines to visually represent the analysis results. For this, it uses libraries such as matplotlib and seaborn. Specifically, the server uses matplotlib to generate a sales trend graph with code like "plt.plot(dates, sales)", and seaborn to create a heat map showing market changes with "sns.heatmap(data)".

[0084] The visualized information is sent to the device and displayed to the user. The device then displays this visualized information in a dashboard on the browser, allowing the user to easily understand the data content and trends. For example, the user can click on the "Sales Trend" tab to view detailed graphs.

[0085] The user also analyzes the displayed information and provides feedback to the server as needed. For example, the user may send feedback such as, "I need more detailed sales data for Q1." The server analyzes this feedback, identifies areas for improvement in the visualization information, and provides it to the user again.

[0086] To illustrate this, here is an example of a prompt for a generative AI model:

[0087] "Please elaborate on how you collect data from market trend APIs and your internal sales database to analyze and visualize sales trends and market changes."

[0088] In this way, through a series of processes, from specifying raw data to collecting, analyzing, visualizing, and providing feedback, companies can respond quickly and effectively to market conditions and provide the information necessary to achieve KPIs.

[0089] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0090] Step 1:

[0091] The user inputs a data collection request into the system. Specifically, the user specifies the data source (e.g., a market trend API or an internal sales database) and sets parameters such as the collection period and type of information. The input request is sent to the server.

[0092] input:

[0093] Data source identifiers (e.g., API endpoints, database names)

[0094] Collection period (e.g., last 6 months)

[0095] Type of information (e.g., market trend data, sales data)

[0096] output:

[0097] Data Collection Request

[0098] Specific behavior:

[0099] The user opens the "Data Collection Request" form, fills in the required information, and clicks the "Submit" button.

[0100] Step 2:

[0101] Based on the data collection request received from the user, the server sends requests to the specified data sources to collect the required data, which may include sending API requests or executing SQL queries.

[0102] input:

[0103] Data Collection Request

[0104] output:

[0105] Data collected

[0106] Specific behavior:

[0107] The server sends a request like "https: / / api.marketdata.com / v1 / trends?duration=6months" and receives JSON data.

[0108] Execute the SQL query "SELECT FROM sales_data WHERE date >= '2023-04-01'" on the internal database to retrieve the data.

[0109] Step 3:

[0110] The server analyzes the collected data, which includes data preprocessing (e.g., removing missing values) and analysis using machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas).

[0111] input:

[0112] Data collected

[0113] output:

[0114] Analysis results

[0115] Specific behavior:

[0116] The server uses pandas to perform preprocessing such as "cleaned_data = raw_data.dropna()".

[0117] Use scikit-learn's linear regression model and run "model.fit(X, y)" to predict sales trends.

[0118] Step 4:

[0119] The server converts the analysis results into visual representations, using libraries such as matplotlib and seaborn to generate graphs and heatmaps.

[0120] input:

[0121] Analysis results

[0122] output:

[0123] Visualization data (graphs, heat maps, etc.)

[0124] Specific behavior:

[0125] The server uses matplotlib to create a sales trend graph using the code "plt.plot(dates, sales)".

[0126] Use seaborn to create a heatmap showing market changes with "sns.heatmap(data)".

[0127] Step 5:

[0128] The terminal receives the visualized data from the server and displays it to the user, allowing the user to easily understand the content and trends of the data.

[0129] input:

[0130] Visualized Data

[0131] output:

[0132] Visualization information displayed

[0133] Specific behavior:

[0134] The device displays graphs and heat maps on a dashboard.

[0135] Users can click on the "Sales Trends" tab to view detailed graphs.

[0136] Step 6:

[0137] The user analyzes the displayed visualization information and provides feedback as needed, for example by sending a request to the server saying, "I need detailed sales data for the first quarter."

[0138] input:

[0139] Visualization Information

[0140] Feedback Request

[0141] output:

[0142] Feedback requests to the server

[0143] Specific behavior:

[0144] The user fills in the feedback form with detailed data requests and clicks the "Submit" button.

[0145] Step 7:

[0146] The server analyzes the user's feedback and refines the visualization, which is then sent back to the terminal and displayed to the user.

[0147] input:

[0148] Feedback Request

[0149] output:

[0150] Improved visualization

[0151] Specific behavior:

[0152] The server will then query the data again based on the feedback to obtain any additional information needed.

[0153] Visualize new analysis results and send them to your device.

[0154] (Application example 1)

[0155] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0156] Companies need real-time data analysis and visualization to respond quickly and effectively to uncertain market conditions and achieve key performance indicators (KPIs). However, current systems do not adequately integrate and analyze market trends and sales data, making it difficult to utilize feedback for continuous improvement. As a result, there is a lack of effective information provision to support corporate decision-making.

[0157] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0158] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for users to provide feedback, means for updating visualization information based on the feedback, means for collecting sales data from a store's sales database, means for acquiring market trend data from an API, means for analyzing the sales data and market trend data using a machine learning model, and means for generating sales trend graphs, inventory heat maps, and graphs showing market changes, thereby enabling companies to quickly and effectively respond to market conditions and visually grasp data to achieve KPIs in real time.

[0159] A "data source" is a data provider, such as an external API or an internal database, from which information or data is obtained.

[0160] "Analysis" is the process of analyzing collected data using machine learning models and statistical methods to extract useful information and trends.

[0161] "Visualization" is the process of converting analytical results into visual representations such as graphs, heat maps, and trend lines.

[0162] "Feedback" is information collected from users to improve the system.

[0163] A "sales database" is a database that stores and manages sales data collected by stores and companies.

[0164] "Market trend data" is data that shows consumer behavior and trends in a particular market, typically obtained from external APIs.

[0165] A "machine learning model" is an algorithm that learns using large amounts of data and makes predictions and classifications for future data.

[0166] A "sales trend graph" is a graph that visually shows fluctuations in sales over a specific period of time.

[0167] An "inventory heat map" is a visual representation that uses different colors to show inventory status, and is typically used to intuitively understand whether there is an excess or shortage of inventory.

[0168] A "graph showing market changes" is a graph that visually represents market trends and changes.

[0169] The present invention aims to build a system that provides information necessary for companies to respond quickly to market conditions and achieve key performance indicators (KPIs). Specific embodiments are described below.

[0170] System Configuration

[0171] Hardware:

[0172] Server, smartphone or tablet

[0173] software:

[0174] Python, Pandas, Matplotlib, fbprophet, Requests

[0175] Program processing explanation

[0176] Data collection:

[0177] The server collects market trend data using external APIs and also retrieves sales data from the store's sales database. This process gathers the necessary data.

[0178] Data Analysis:

[0179] The server analyzes the collected data using a machine learning model (specifically, a time-series forecasting model using the fbprophet library) to predict sales trends and market changes.

[0180] Visualization:

[0181] The server visualizes the analysis results, which are displayed in the form of sales trend graphs, inventory heat maps, and graphs showing market changes.

[0182] feedback:

[0183] Users can view the visualized information and provide feedback through their smartphones or tablets. For example, if they want to know more about the sales trends of a particular product, they can send a request to the server.

[0184] Information update:

[0185] The server updates the visualization based on user feedback, providing more accurate and useful information to the user.

[0186] Specific examples

[0187] For example, if the API URL is "https: / / api.example.com / market_data" and the database connection information is ("user", "password", "host", "database"), data collection will be performed based on this information.

[0188] Prompt Sentence Examples

[0189] As an example of a prompt sentence, the following text can be input into the generative model to obtain specific data and perform analysis.

[0190] Write Python code to retrieve market trend data from APIs such as the following and use Prophet to make predictions and visualizations:

[0191] API URL: https: / / api.example.com / market_data

[0192] Database connection information: user, password, host, database

[0193] Data to be acquired: Sales data and market trend data

[0194] Graph Visualization

[0195] Execution example:

[0196] market_data = fetch_market_data(api_url)

[0197] sales_data = fetch_sales_data(db_conn)

[0198] sales_forecast_data = sales_forecast(sales_data)

[0199] visualize_data(sales_forecast_data, market_data)

[0200] This allows users to make decisions based on real-time, accurate data.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1:

[0203] The server collects market trend data from an external API. Specifically, it sends an API request and parses the JSON data returned as a response to extract the necessary information. At this stage, the API URL (e.g., "https: / / api.example.com / market_data") is the input, and the acquired market trend data is the output.

[0204] Step 2:

[0205] The server connects to the sales database and retrieves sales data. This involves running a SQL query to pull the required records from the database. The input to this step is the database connection information (e.g., user, password, host, database) and the output is the sales data.

[0206] Step 3:

[0207] The server inputs the collected market trend data and sales data into a machine learning model (e.g., the fbprophet library) to perform time series forecasting analysis. Here, the parsed data is fed into the model, which outputs analyzed sales trends and market forecasts.

[0208] Step 4:

[0209] The server visualizes the analysis results. Specifically, it uses Python's Matplotlib library to generate sales trend graphs, inventory heat maps, and graphs showing market changes. At this stage, the analysis results from the machine learning model are the input, and the visualized graphs are the output.

[0210] Step 5:

[0211] The user checks the visualized information on a smartphone or tablet. The visualized information is displayed on the user's device, allowing the user to perform detailed analysis. The input of this stage is the visualized graph, and the output is the user's understanding or analysis results.

[0212] Step 6:

[0213] The user provides feedback as needed. For example, the user sends feedback such as "I would like to know more about the sales trends of a particular product" to the server. At this stage, the user's feedback is the input, and the updated request based on that feedback is the output.

[0214] Step 7:

[0215] The server analyzes the user feedback and updates the visualization information. Based on the analyzed feedback, it improves the visualization graph and data display. The input of this step is the user feedback, and the output is the updated visualization information based on the feedback.

[0216] Through this series of steps, the system achieves a cycle of collection, analysis, visualization, and feedback in real time, providing useful information that enables companies to quickly respond to market conditions.

[0217] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0218] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. This system also combines an emotion engine that recognizes the user's emotions, enabling more effective information presentation.

[0219] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0220] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0221] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0222] A distinctive feature of this invention is the incorporation of an emotion engine. The device monitors the user's facial expressions and speech, and the emotion engine recognizes the user's emotions. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0223] The emotion engine recognizes the user's emotions and uses them to dynamically adjust the visualization. For example, if the user expresses dissatisfaction or confusion, the server can provide more detailed visualizations or switch to a different display method based on the user's emotions.

[0224] Furthermore, user feedback is not just provided as text or a choice, but is also analyzed emotionally by an emotion engine. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0225] The server identifies areas for improvement in the visualization based on the collected feedback and the results of sentiment analysis. It then updates the visualization based on the feedback and presents it to the user again. This allows the system to continuously improve and provide the most effective information to users.

[0226] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, and can provide information that allows companies to respond quickly and effectively to uncertain market environments, making it easier for companies to achieve their KPIs and enabling more accurate decision-making.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0230] Step 2:

[0231] The server sends requests to designated data sources to retrieve the required data. For example, the server might send a request to a market trends API to retrieve external market data, while also querying an internal database to pull sales data.

[0232] Step 3:

[0233] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0234] Step 4:

[0235] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0236] Step 5:

[0237] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0238] Step 6:

[0239] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0240] Step 7:

[0241] The device monitors the user's facial expressions and speech, and recognizes the user's emotions using an emotion engine. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0242] Step 8:

[0243] The user's emotions, as recognized by the emotion engine, are sent to the server, which then adjusts the visualization based on that information. For example, if the user is confused, the server can make the visualization more detailed or switch to a different display method.

[0244] Step 9:

[0245] The user can provide feedback on the displayed visualization, for example, by sending feedback to the server such as "I need more detailed sales data for the first quarter."

[0246] Step 10:

[0247] The server analyzes the collected feedback and identifies areas for improvement in the visualization. An emotion engine also performs emotional analysis. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0248] Step 11:

[0249] The server updates the visualization based on the feedback and the results of the sentiment analysis, and sends the improved visualization to the device for re-presentation to the user.

[0250] Step 12:

[0251] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0252] Example 2

[0253] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0254] Conventional data analysis systems focus on data collection, analysis, and visualization, but do not address the dynamic presentation of information that takes user emotions into account. This makes it difficult to provide information that takes into account the user's level of understanding and satisfaction, making effective decision-making difficult, especially when the market environment fluctuates in real time. To solve this problem, a system that recognizes user emotions and dynamically adjusts information presentation based on them is needed.

[0255] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0256] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, means for dynamically adjusting the visual display based on the recognized emotion, means for collecting and analyzing user feedback, and means for improving the visual display based on the collected feedback and the emotion recognition results. This makes it possible to dynamically adjust and provide information while taking user emotions into consideration, thereby helping companies to respond quickly and effectively to uncertain market environments.

[0257] A "data source" refers to a data provider, such as an external API or an internal database, from which the necessary information is obtained.

[0258] "Server" refers to a computer system that performs core functions of the system, such as data collection, analysis, visualization, emotion recognition, and feedback analysis.

[0259] "User" refers to the entity that uses this system to collect data, view analysis results, and provide feedback.

[0260] An "emotion engine" refers to software or algorithms that recognize and analyze emotions from a user's facial expressions, voice, etc.

[0261] "Visualization" refers to the process of presenting analytical results in a visually understandable format, such as graphs, heat maps, or trend lines.

[0262] "Feedback" refers to the opinions and impressions that users provide regarding visualized information.

[0263] "Dynamic adjustment" refers to the process of changing the displayed information and its format in real time or incrementally based on the user's emotion recognition results and feedback.

[0264] A "machine learning model" is an algorithm used to analyze data, specifically to learn patterns and trends from data and make predictions or detect anomalies.

[0265] "Analysis" refers to the process of extracting trends and characteristics from collected data using statistical methods and algorithms.

[0266] "Collection" refers to the process of obtaining the necessary information from designated data sources and incorporating it into the system.

[0267] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. The system has functions for data collection, analysis, visualization, emotion recognition, and feedback analysis, thereby improving user understanding and satisfaction.

[0268] First, the user specifies the specific data they are interested in. For example, they input a request to the system such as, "I want to collect market trends and my company's sales data for the first quarter of 2023." At this time, the user also provides the API key and authentication information for the data source.

[0269] The server then sends requests to the specified data sources to collect the required data. Specifically, it obtains market trend data using external APIs (e.g., Eikon API) and pulls sales data from internal databases (e.g., Salesforce). The collected data is then stored in internal storage.

[0270] The server analyzes the data stored in the internal storage. For analysis, machine learning models such as (scikit-learn) and statistical algorithms are used to detect trends and outliers in the data. The results of these analyses are then converted into JSON format and used in the subsequent visualization process.

[0271] The analysis results are visualized by the server. Based on the analysis results, visual representations such as graphs, heat maps, and trend lines are generated using libraries such as (D3.js) and (Matplotlib). For example, a trend graph showing monthly sales increases or decreases, or a heat map showing market fluctuations by color intensity, are generated.

[0272] The device collects data using a camera and microphone to recognize emotional information such as the user's facial expressions and voice. The collected emotional data is analyzed in real time using OpenCV or IBM Watson. The results of the emotion analysis are sent to a server and used to dynamically adjust the visualization information.

[0273] For example, if the user expresses confusion or dissatisfaction, the server can adjust the visualization based on that emotion by providing more detail or a different display method, thereby providing information that matches the user's emotion. This process improves the user's understanding and satisfaction.

[0274] Furthermore, users can provide feedback on the visualized information. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to deeply understand the content of the feedback. The server then identifies areas for improvement in the visualized information based on the collected feedback and the results of the emotion analysis, and updates the visualized information as necessary. The improved visualized information is then displayed again on the device and provided to the user.

[0275] Below are some specific examples of prompt sentences to input into the generative AI model.

[0276] "Describe a system that provides high-quality visualizations of the information companies need to quickly respond to uncertain market conditions. Also, detail how the system recognizes user emotions and dynamically adjusts visualizations."

[0277] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, thereby providing high-quality information that enables companies to respond quickly and effectively to uncertain market environments.

[0278] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0279] Explaining the program's processing flow step by step

[0280] Step 1: Data collection

[0281] User

[0282] Input: Data collection request (e.g., market trend data and sales data), API key, and authentication information

[0283] Specific operation: The user inputs the required data type and authentication information into the interface.

[0284] server

[0285] Input: User's data collection request

[0286] Specific operation: The server sends a request to a data source (e.g., an external API or an internal database).

[0287] Data processing: The server receives the response to the request and extracts the necessary data.

[0288] Output: Collected market trend data and sales data (stored in internal storage)

[0289] Step 2: Data analysis

[0290] server

[0291] Input: Market trend data and sales data stored in internal storage

[0292] What it does: The server runs machine learning models and statistical algorithms to analyze the data, for example, using scikit-learn to detect outliers and perform future predictions.

[0293] Data processing: Statistical processing and machine learning algorithms are used to detect specific trends and anomalies in the data.

[0294] Output: Analysis results (e.g., trend data and anomaly detection reports in JSON format)

[0295] Step 3: Visualization

[0296] server

[0297] Input: Analysis results (trend data and anomaly detection reports in JSON format)

[0298] What happens: The server uses a visualization library (e.g., D3.js or Matplotlib) to generate a visual representation.

[0299] Data processing: Converting analysis results into graphs, heat maps, trend lines, etc.

[0300] Output: Visualized data (graphs and heatmaps in SVG or HTML format)

[0301] Terminal

[0302] Input: Visualized data

[0303] Specific behavior: The device renders a UI to display the visualization data.

[0304] Output: Graphs and heatmaps displayed on the user's screen

[0305] Step 4: Emotion Recognition

[0306] Terminal

[0307] Input: User facial and voice data collected through the camera and microphone

[0308] Specific operation: The device uses (OpenCV) and (IBM Watson) to perform real-time sentiment analysis.

[0309] Data processing: Facial recognition and voice analysis algorithms are used to identify user emotions.

[0310] Output: Analyzed user emotion data (e.g., user is confused, satisfied, etc.)

[0311] server

[0312] Input: User emotion data sent from the device

[0313] Specific operation: The server analyzes the emotion data and uses it to adjust the visualization information.

[0314] Step 5: Dynamically adjust visualizations

[0315] server

[0316] Input: Parsed user emotion data

[0317] Specific behavior: The server dynamically adjusts the visualization based on the sentiment analysis results, for example, by increasing the details of the visualization or switching to a different visualization method.

[0318] Data manipulation: Re-rendering visualization data

[0319] Output: Adjusted visualization data (sent back to the terminal)

[0320] Terminal

[0321] Input: Reconciled visualization data

[0322] What happens: The device re-renders and displays the new visualization data.

[0323] Output: Information redisplayed on the user's screen

[0324] Step 6: Gather feedback and improve

[0325] User

[0326] Input: Feedback on the visualization (e.g., "This graph is difficult to understand")

[0327] Specific Action: The user provides feedback to the system.

[0328] Terminal

[0329] Input: User-provided feedback

[0330] Specific operation: The device collects feedback in text format and analyzes it using the emotion engine.

[0331] Data processing: Analysis of feedback and its tone

[0332] Output: Parsed feedback data (sent to server)

[0333] server

[0334] Input: Parsed feedback data

[0335] Specific operation: The server identifies areas for improvement in the visualization information based on the feedback data and updates the visualization data.

[0336] Data processing: generating new visualizations

[0337] Output: Visualized data reflecting the feedback (sent to the device)

[0338] Terminal

[0339] Input: Visualization data reflecting feedback

[0340] What happens: The device re-renders and displays the new visualization data.

[0341] Output: The improved information displayed on the user's screen

[0342] (Application example 2)

[0343] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0344] In autonomous vehicles, to optimize the user's driving experience and improve safety and comfort, it is necessary to accurately recognize the user's emotions and adjust the vehicle's operation and information display in real time based on that information. However, conventional systems have difficulty making such dynamic adjustments. A system that can solve this problem and provide a high-quality user experience is needed.

[0345] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0346] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, and means for dynamically adjusting the visualization information based on the recognized user's emotion, thereby enabling a high-quality driving experience for an autonomous vehicle and improving safety and comfort.

[0347] "Data source" refers to the information source or database from which the system gathers the information it needs.

[0348] "Means of analysis" refers to the function of analyzing collected data in various ways and extracting useful information.

[0349] "Means for visual display" refers to the function of converting the analysis results into visual representations such as graphs, heat maps, and trend lines in order to present them to the user in an easy-to-understand manner.

[0350] "Means for recognizing emotions" refers to machine learning models and sensors that automatically determine emotions from a user's facial expressions, voice, etc.

[0351] "Means for dynamic adjustment" refers to the ability to automatically change the system's visualizations and behavior in real time based on perceived changes in the user's emotions.

[0352] An "autonomous vehicle" is a vehicle that has the ability to travel automatically to a destination without direct operation by a driver.

[0353] "Safety" refers to the ability of a system or automated vehicle to minimize risk to the user.

[0354] "Comfort" refers to the sense of security and satisfaction that users feel when using the system or autonomous vehicle.

[0355] The embodiment of the present invention is a system for optimizing the driving experience of a user in an autonomous vehicle and improving safety and comfort, which mainly includes means for data collection, data analysis, visualization, emotion recognition, and dynamic adjustment.

[0356] Explanation of program processing

[0357] First, the server collects the necessary data from data sources, such as market trend data from external APIs and internal sales databases. Then, it analyzes the collected data using machine learning models and statistical algorithms to identify sales trends and market changes.

[0358] The analysis results are displayed visually, using graphs, heat maps, trend lines, and other visual representations to provide users with an easy-to-understand view of the data and its trends.

[0359] Next, the device recognizes the user's emotions. For this purpose, the smartphone's built-in camera and microphone are used. The camera is used to capture the user's facial expressions, and emotions are recognized using a deep learning model (using Keras and dlib). Voice data is also analyzed to help with emotion recognition.

[0360] Finally, the visualization and the autonomous vehicle's behavior can be dynamically adjusted based on the user's perceived emotions: for example, if the user expresses dissatisfaction or confusion, the visualization can be switched to a more detailed display, or the temperature or music in the car can be adjusted.

[0361] Hardware and software used

[0362] Deep learning model (Keras)

[0363] Face detection and landmark acquisition (dlib)

[0364] Image processing (OpenCV)

[0365] Sending API requests (Requests)

[0366] Specific examples

[0367] Market data visualization shows sales trend graphs and consumer behavior patterns, and controls the temperature and music in the car to enhance user comfort.

[0368] Prompt Sentence Examples

[0369] "If a user is confused, show them detailed market data and change the music in their car to something more relaxing."

[0370] "If the user is angry, prepare for an emergency shutdown."

[0371] Through these processes, the server can improve the user's driving experience, enhancing safety and comfort.

[0372] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0373] Step 1:

[0374] The server collects the required data from data sources. Data sources can include, for example, market trend data from external APIs or internal sales databases. The server sends requests to these data sources to collect the data. The input is an API request or a database query, and the output is the collected raw data.

[0375] Step 2:

[0376] The server analyzes the collected data. Specifically, it analyzes the collected sales data and market trend data using machine learning models and statistical algorithms. The input is the raw data collected in step 1, and the output is the analyzed results, such as sales trends and market changes.

[0377] Step 3:

[0378] The server visually displays the analysis results. It converts the analysis results into visual representations such as graphs, heat maps, and trend lines and provides them to the user in an easy-to-understand format. The input is the analysis results obtained in step 2, and the output is the visual display data.

[0379] Step 4:

[0380] The device recognizes the user's emotions. It uses the smartphone's built-in camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a deep learning model (using Keras and dlib). The input is camera images and audio data, and the output is the recognized user's emotions.

[0381] Step 5:

[0382] Based on the recognized user emotion, the server dynamically adjusts the visualization information and the behavior of the autonomous vehicle. For example, if the user expresses dissatisfaction or confusion, the server can switch to a more detailed information display or adjust the temperature or music inside the vehicle. The input is the user emotion recognized in step 4, and the output is the adjusted visualization information and vehicle behavior.

[0383] Through these steps, cooperation between servers, terminals, and users will be possible to improve the driving experience of autonomous vehicles, and to enhance safety and comfort.

[0384] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0385] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0386] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0387] [Second embodiment]

[0388] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0389] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0390] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0391] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0392] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0393] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0394] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0395] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0396] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0397] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0398] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0399] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0400] This invention is a system that provides high-quality visualization of the information needed for companies to respond quickly to uncertain market environments and achieve key performance indicators (KPIs).

[0401] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0402] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0403] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0404] Users can analyze the displayed visualization information and create specific action plans. They can also provide feedback as needed. For example, they can send feedback such as "We need more detailed sales data for the first quarter" to the server.

[0405] The server analyzes the collected feedback and identifies areas for improvement in the visualization. It then updates the visualization based on the feedback and presents it to the user again. Through this process, the system continuously improves and delivers the most effective information to users.

[0406] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, and feedback, and can provide information that allows companies to respond quickly and effectively to uncertain market environments. As a result, companies can not only more easily achieve their KPIs, but also make more accurate decisions.

[0407] The processing flow will be explained below.

[0408] Step 1:

[0409] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0410] Step 2:

[0411] The server sends requests to designated data sources to retrieve the required data. For example, the server may send requests to a market trends API to retrieve external market data, or query an internal database to gather sales data.

[0412] Step 3:

[0413] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0414] Step 4:

[0415] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0416] Step 5:

[0417] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0418] Step 6:

[0419] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0420] Step 7:

[0421] The user can provide feedback on the displayed visualization, for example, "I need more detailed sales data for the first quarter" to the server.

[0422] Step 8:

[0423] The server analyzes the collected feedback, identifies areas for improvement in the visualization, and updates and re-presents the visualization to the user based on the feedback.

[0424] Step 9:

[0425] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0426] Example 1

[0427] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0428] In order for companies to respond quickly to uncertain market conditions and achieve key performance indicators (KPIs), it is difficult to efficiently collect, analyze, visualize, and incorporate feedback from high-quality information. In particular, when data is collected from a wide range of sources, information collection and analysis can be a time-consuming process, resulting in the inability to make timely and effective decisions.

[0429] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0430] In this invention, the server includes means for a user to specify required information from a data source, means for collecting information based on the data source specified by the user, means for analyzing the collected information using a machine learning model or a statistical algorithm, means for converting the analysis results into a visual representation such as a graph, a heat map, or a trend line, means for displaying the visual representation on a terminal, means for collecting and analyzing feedback from users, and means for improving the visual representation based on the feedback, thereby enabling companies to respond quickly and effectively to uncertain market environments and make accurate decisions based on high-quality information.

[0431] "Data source" refers to the source or information source from which data is obtained.

[0432] "Information" includes data and content collected from data sources.

[0433] "User" refers to the end-user who operates the system and specifies, collects, analyzes, and provides feedback on required information.

[0434] "Server" refers to a central processing unit that collects, analyzes, visualizes, processes feedback, etc.

[0435] A "machine learning model" is an algorithm or model used in data analysis to derive patterns and predictions from data.

[0436] A "statistical algorithm" is a mathematical model or computational method used to analyze data and derive results.

[0437] "Analysis results" refers to the insights and conclusions obtained after analyzing data using machine learning models and statistical algorithms.

[0438] "Visual representation" refers to techniques and methods for presenting analytical results in easy-to-understand charts and graphs.

[0439] A "graph" is a form of visual display used to show data values ​​and trends.

[0440] A "heat map" is a visual representation that uses colors to show the relationships and distributions between specific variables.

[0441] A "trend line" is a line expressed as a straight or curved line that shows changes or trends in data.

[0442] "Terminal" refers to a device that allows a user to communicate with a server and display and manipulate data and visual presentations.

[0443] "Feedback" means any additional requests, comments or improvements provided by a User.

[0444] "High quality" means that the data and information are accurate, reliable, and useful as information for users to use in making decisions.

[0445] This invention is a system that provides high-quality visualization of the information companies need to respond quickly and effectively to uncertain market environments and achieve key performance indicators (KPIs).

[0446] First, the user specifies the information they want to collect from a data source (e.g., a market trend API or an internal sales database). Specifically, the user enters a request through the system interface, such as "collect data from the market trend API for the past six months."

[0447] The server collects information based on the data source specified by the user. In the case of an external API, the server sends a request, retrieves the response data in JSON format, and analyzes it. Specifically, the server sends a request such as "https: / / api.marketdata.com / v1 / trends?duration=6months" and analyzes the resulting data. In the case of an internal database, the server executes an SQL query to collect the required data. For example, a query such as "SELECT FROM sales_data WHERE date >= '2023-04-01'" is used.

[0448] The collected information is analyzed by the server. This analysis uses machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas). The server preprocesses the data and cleanses it by removing unnecessary data and missing values. For example, the server uses pandas to remove missing values ​​(e.g., "cleaned_data = raw_data.dropna()"), and then uses a scikit-learn linear regression model (e.g., "model.fit(X, y)") to predict sales trends.

[0449] Next, the server generates graphs, heat maps, and trend lines to visually represent the analysis results. For this, it uses libraries such as matplotlib and seaborn. Specifically, the server uses matplotlib to generate a sales trend graph with code like "plt.plot(dates, sales)", and seaborn to create a heat map showing market changes with "sns.heatmap(data)".

[0450] The visualized information is sent to the device and displayed to the user. The device then displays this visualized information in a dashboard on the browser, allowing the user to easily understand the data content and trends. For example, the user can click on the "Sales Trend" tab to view detailed graphs.

[0451] The user also analyzes the displayed information and provides feedback to the server as needed. For example, the user may send feedback such as, "I need more detailed sales data for Q1." The server analyzes this feedback, identifies areas for improvement in the visualization information, and provides it to the user again.

[0452] To illustrate this, here is an example of a prompt for a generative AI model:

[0453] "Please elaborate on how you collect data from market trend APIs and your internal sales database to analyze and visualize sales trends and market changes."

[0454] In this way, through a series of processes, from specifying raw data to collecting, analyzing, visualizing, and providing feedback, companies can respond quickly and effectively to market conditions and provide the information necessary to achieve KPIs.

[0455] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0456] Step 1:

[0457] The user inputs a data collection request into the system. Specifically, the user specifies the data source (e.g., a market trend API or an internal sales database) and sets parameters such as the collection period and type of information. The input request is sent to the server.

[0458] input:

[0459] Data source identifiers (e.g., API endpoints, database names)

[0460] Collection period (e.g., last 6 months)

[0461] Type of information (e.g., market trend data, sales data)

[0462] output:

[0463] Data Collection Request

[0464] Specific behavior:

[0465] The user opens the "Data Collection Request" form, fills in the required information, and clicks the "Submit" button.

[0466] Step 2:

[0467] Based on the data collection request received from the user, the server sends requests to the specified data sources to collect the required data, which may include sending API requests or executing SQL queries.

[0468] input:

[0469] Data Collection Request

[0470] output:

[0471] Data collected

[0472] Specific behavior:

[0473] The server sends a request like "https: / / api.marketdata.com / v1 / trends?duration=6months" and receives JSON data.

[0474] Execute the SQL query "SELECT FROM sales_data WHERE date >= '2023-04-01'" on the internal database to retrieve the data.

[0475] Step 3:

[0476] The server analyzes the collected data, which includes data preprocessing (e.g., removing missing values) and analysis using machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas).

[0477] input:

[0478] Data collected

[0479] output:

[0480] Analysis results

[0481] Specific behavior:

[0482] The server uses pandas to perform preprocessing such as "cleaned_data = raw_data.dropna()".

[0483] Use scikit-learn's linear regression model and run "model.fit(X, y)" to predict sales trends.

[0484] Step 4:

[0485] The server converts the analysis results into visual representations, using libraries such as matplotlib and seaborn to generate graphs and heatmaps.

[0486] input:

[0487] Analysis results

[0488] output:

[0489] Visualization data (graphs, heat maps, etc.)

[0490] Specific behavior:

[0491] The server uses matplotlib to create a sales trend graph using the code "plt.plot(dates, sales)".

[0492] Use seaborn to create a heatmap showing market changes with "sns.heatmap(data)".

[0493] Step 5:

[0494] The terminal receives the visualized data from the server and displays it to the user, allowing the user to easily understand the content and trends of the data.

[0495] input:

[0496] Visualized Data

[0497] output:

[0498] Visualization information displayed

[0499] Specific behavior:

[0500] The device displays graphs and heat maps on a dashboard.

[0501] Users can click on the "Sales Trends" tab to view detailed graphs.

[0502] Step 6:

[0503] The user analyzes the displayed visualization information and provides feedback as needed, for example by sending a request to the server saying, "I need detailed sales data for the first quarter."

[0504] input:

[0505] Visualization Information

[0506] Feedback Request

[0507] output:

[0508] Feedback requests to the server

[0509] Specific behavior:

[0510] The user fills in the feedback form with detailed data requests and clicks the "Submit" button.

[0511] Step 7:

[0512] The server analyzes the user's feedback and refines the visualization, which is then sent back to the terminal and displayed to the user.

[0513] input:

[0514] Feedback Request

[0515] output:

[0516] Improved visualization

[0517] Specific behavior:

[0518] The server will then query the data again based on the feedback to obtain any additional information needed.

[0519] Visualize new analysis results and send them to your device.

[0520] (Application example 1)

[0521] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0522] Companies need real-time data analysis and visualization to respond quickly and effectively to uncertain market conditions and achieve key performance indicators (KPIs). However, current systems do not adequately integrate and analyze market trends and sales data, making it difficult to utilize feedback for continuous improvement. As a result, there is a lack of effective information provision to support corporate decision-making.

[0523] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0524] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for users to provide feedback, means for updating visualization information based on the feedback, means for collecting sales data from a store's sales database, means for acquiring market trend data from an API, means for analyzing the sales data and market trend data using a machine learning model, and means for generating sales trend graphs, inventory heat maps, and graphs showing market changes, thereby enabling companies to quickly and effectively respond to market conditions and visually grasp data to achieve KPIs in real time.

[0525] A "data source" is a data provider, such as an external API or an internal database, from which information or data is obtained.

[0526] "Analysis" is the process of analyzing collected data using machine learning models and statistical methods to extract useful information and trends.

[0527] "Visualization" is the process of converting analytical results into visual representations such as graphs, heat maps, and trend lines.

[0528] "Feedback" is information collected from users to improve the system.

[0529] A "sales database" is a database that stores and manages sales data collected by stores and companies.

[0530] "Market trend data" is data that shows consumer behavior and trends in a particular market, typically obtained from external APIs.

[0531] A "machine learning model" is an algorithm that learns using large amounts of data and makes predictions and classifications for future data.

[0532] A "sales trend graph" is a graph that visually shows fluctuations in sales over a specific period of time.

[0533] An "inventory heat map" is a visual representation that uses different colors to show inventory status, and is typically used to intuitively understand whether there is an excess or shortage of inventory.

[0534] A "graph showing market changes" is a graph that visually represents market trends and changes.

[0535] The present invention aims to build a system that provides information necessary for companies to respond quickly to market conditions and achieve key performance indicators (KPIs). Specific embodiments are described below.

[0536] System Configuration

[0537] Hardware:

[0538] Server, smartphone or tablet

[0539] software:

[0540] Python, Pandas, Matplotlib, fbprophet, Requests

[0541] Program processing explanation

[0542] Data collection:

[0543] The server collects market trend data using external APIs and also retrieves sales data from the store's sales database. This process gathers the necessary data.

[0544] Data Analysis:

[0545] The server analyzes the collected data using a machine learning model (specifically, a time-series forecasting model using the fbprophet library) to predict sales trends and market changes.

[0546] Visualization:

[0547] The server visualizes the analysis results, which are displayed in the form of sales trend graphs, inventory heat maps, and graphs showing market changes.

[0548] feedback:

[0549] Users can view the visualized information and provide feedback through their smartphones or tablets. For example, if they want to know more about the sales trends of a particular product, they can send a request to the server.

[0550] Information update:

[0551] The server updates the visualization based on user feedback, providing more accurate and useful information to the user.

[0552] Specific examples

[0553] For example, if the API URL is "https: / / api.example.com / market_data" and the database connection information is ("user", "password", "host", "database"), data collection will be performed based on this information.

[0554] Prompt Sentence Examples

[0555] As an example of a prompt sentence, the following text can be input into the generative model to obtain specific data and perform analysis.

[0556] Write Python code to retrieve market trend data from APIs such as the following and use Prophet to make predictions and visualizations:

[0557] API URL: https: / / api.example.com / market_data

[0558] Database connection information: user, password, host, database

[0559] Data to be acquired: Sales data and market trend data

[0560] Graph Visualization

[0561] Execution example:

[0562] market_data = fetch_market_data(api_url)

[0563] sales_data = fetch_sales_data(db_conn)

[0564] sales_forecast_data = sales_forecast(sales_data)

[0565] visualize_data(sales_forecast_data, market_data)

[0566] This allows users to make decisions based on real-time, accurate data.

[0567] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0568] Step 1:

[0569] The server collects market trend data from an external API. Specifically, it sends an API request and parses the JSON data returned as a response to extract the necessary information. At this stage, the API URL (e.g., "https: / / api.example.com / market_data") is the input, and the acquired market trend data is the output.

[0570] Step 2:

[0571] The server connects to the sales database and retrieves sales data. This involves running a SQL query to pull the required records from the database. The input to this step is the database connection information (e.g., user, password, host, database) and the output is the sales data.

[0572] Step 3:

[0573] The server inputs the collected market trend data and sales data into a machine learning model (e.g., the fbprophet library) to perform time series forecasting analysis. Here, the parsed data is fed into the model, which outputs analyzed sales trends and market forecasts.

[0574] Step 4:

[0575] The server visualizes the analysis results. Specifically, it uses Python's Matplotlib library to generate sales trend graphs, inventory heat maps, and graphs showing market changes. At this stage, the analysis results from the machine learning model are the input, and the visualized graphs are the output.

[0576] Step 5:

[0577] The user checks the visualized information on a smartphone or tablet. The visualized information is displayed on the user's device, allowing the user to perform detailed analysis. The input of this stage is the visualized graph, and the output is the user's understanding or analysis results.

[0578] Step 6:

[0579] The user provides feedback as needed. For example, the user sends feedback such as "I would like to know more about the sales trends of a particular product" to the server. At this stage, the user's feedback is the input, and the updated request based on that feedback is the output.

[0580] Step 7:

[0581] The server analyzes the user feedback and updates the visualization information. Based on the analyzed feedback, it improves the visualization graph and data display. The input of this step is the user feedback, and the output is the updated visualization information based on the feedback.

[0582] Through this series of steps, the system achieves a cycle of collection, analysis, visualization, and feedback in real time, providing useful information that enables companies to quickly respond to market conditions.

[0583] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0584] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. This system also combines an emotion engine that recognizes the user's emotions, enabling more effective information presentation.

[0585] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0586] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0587] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0588] A distinctive feature of this invention is the incorporation of an emotion engine. The device monitors the user's facial expressions and speech, and the emotion engine recognizes the user's emotions. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0589] The emotion engine recognizes the user's emotions and uses them to dynamically adjust the visualization. For example, if the user expresses dissatisfaction or confusion, the server can provide more detailed visualizations or switch to a different display method based on the user's emotions.

[0590] Furthermore, user feedback is not just provided as text or a choice, but is also analyzed emotionally by an emotion engine. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0591] The server identifies areas for improvement in the visualization based on the collected feedback and the results of sentiment analysis. It then updates the visualization based on the feedback and presents it to the user again. This allows the system to continuously improve and provide the most effective information to users.

[0592] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, and can provide information that allows companies to respond quickly and effectively to uncertain market environments, making it easier for companies to achieve their KPIs and enabling more accurate decision-making.

[0593] The processing flow will be explained below.

[0594] Step 1:

[0595] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0596] Step 2:

[0597] The server sends requests to designated data sources to retrieve the required data. For example, the server might send a request to a market trends API to retrieve external market data, while also querying an internal database to pull sales data.

[0598] Step 3:

[0599] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0600] Step 4:

[0601] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0602] Step 5:

[0603] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0604] Step 6:

[0605] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0606] Step 7:

[0607] The device monitors the user's facial expressions and speech, and recognizes the user's emotions using an emotion engine. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0608] Step 8:

[0609] The user's emotions, as recognized by the emotion engine, are sent to the server, which then adjusts the visualization based on that information. For example, if the user is confused, the server can make the visualization more detailed or switch to a different display method.

[0610] Step 9:

[0611] The user can provide feedback on the displayed visualization, for example, by sending feedback to the server such as "I need more detailed sales data for the first quarter."

[0612] Step 10:

[0613] The server analyzes the collected feedback and identifies areas for improvement in the visualization. An emotion engine also performs emotional analysis. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0614] Step 11:

[0615] The server updates the visualization based on the feedback and the results of the sentiment analysis, and sends the improved visualization to the device for re-presentation to the user.

[0616] Step 12:

[0617] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0618] Example 2

[0619] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0620] Conventional data analysis systems focus on data collection, analysis, and visualization, but do not address the dynamic presentation of information that takes user emotions into account. This makes it difficult to provide information that takes into account the user's level of understanding and satisfaction, making effective decision-making difficult, especially when the market environment fluctuates in real time. To solve this problem, a system that recognizes user emotions and dynamically adjusts information presentation based on them is needed.

[0621] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0622] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, means for dynamically adjusting the visual display based on the recognized emotion, means for collecting and analyzing user feedback, and means for improving the visual display based on the collected feedback and the emotion recognition results. This makes it possible to dynamically adjust and provide information while taking user emotions into consideration, thereby helping companies to respond quickly and effectively to uncertain market environments.

[0623] A "data source" refers to a data provider, such as an external API or an internal database, from which the necessary information is obtained.

[0624] "Server" refers to a computer system that performs core functions of the system, such as data collection, analysis, visualization, emotion recognition, and feedback analysis.

[0625] "User" refers to the entity that uses this system to collect data, view analysis results, and provide feedback.

[0626] An "emotion engine" refers to software or algorithms that recognize and analyze emotions from a user's facial expressions, voice, etc.

[0627] "Visualization" refers to the process of presenting analytical results in a visually understandable format, such as graphs, heat maps, or trend lines.

[0628] "Feedback" refers to the opinions and impressions that users provide regarding visualized information.

[0629] "Dynamic adjustment" refers to the process of changing the displayed information and its format in real time or incrementally based on the user's emotion recognition results and feedback.

[0630] A "machine learning model" is an algorithm used to analyze data, specifically to learn patterns and trends from data and make predictions or detect anomalies.

[0631] "Analysis" refers to the process of extracting trends and characteristics from collected data using statistical methods and algorithms.

[0632] "Collection" refers to the process of obtaining the necessary information from designated data sources and incorporating it into the system.

[0633] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. The system has functions for data collection, analysis, visualization, emotion recognition, and feedback analysis, thereby improving user understanding and satisfaction.

[0634] First, the user specifies the specific data they are interested in. For example, they input a request to the system such as, "I want to collect market trends and my company's sales data for the first quarter of 2023." At this time, the user also provides the API key and authentication information for the data source.

[0635] The server then sends requests to the specified data sources to collect the required data. Specifically, it obtains market trend data using external APIs (e.g., Eikon API) and pulls sales data from internal databases (e.g., Salesforce). The collected data is then stored in internal storage.

[0636] The server analyzes the data stored in the internal storage. For analysis, machine learning models such as (scikit-learn) and statistical algorithms are used to detect trends and outliers in the data. The results of these analyses are then converted into JSON format and used in the subsequent visualization process.

[0637] The analysis results are visualized by the server. Based on the analysis results, visual representations such as graphs, heat maps, and trend lines are generated using libraries such as (D3.js) and (Matplotlib). For example, a trend graph showing monthly sales increases or decreases, or a heat map showing market fluctuations by color intensity, are generated.

[0638] The device collects data using a camera and microphone to recognize emotional information such as the user's facial expressions and voice. The collected emotional data is analyzed in real time using OpenCV or IBM Watson. The results of the emotion analysis are sent to a server and used to dynamically adjust the visualization information.

[0639] For example, if the user expresses confusion or dissatisfaction, the server can adjust the visualization based on that emotion by providing more detail or a different display method, thereby providing information that matches the user's emotion. This process improves the user's understanding and satisfaction.

[0640] Furthermore, users can provide feedback on the visualized information. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to deeply understand the content of the feedback. The server then identifies areas for improvement in the visualized information based on the collected feedback and the results of the emotion analysis, and updates the visualized information as necessary. The improved visualized information is then displayed again on the device and provided to the user.

[0641] Below are some specific examples of prompt sentences to input into the generative AI model.

[0642] "Describe a system that provides high-quality visualizations of the information companies need to quickly respond to uncertain market conditions. Also, detail how the system recognizes user emotions and dynamically adjusts visualizations."

[0643] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, thereby providing high-quality information that enables companies to respond quickly and effectively to uncertain market environments.

[0644] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0645] Explaining the program's processing flow step by step

[0646] Step 1: Data collection

[0647] User

[0648] Input: Data collection request (e.g., market trend data and sales data), API key, and authentication information

[0649] Specific operation: The user inputs the required data type and authentication information into the interface.

[0650] server

[0651] Input: User's data collection request

[0652] Specific operation: The server sends a request to a data source (e.g., an external API or an internal database).

[0653] Data processing: The server receives the response to the request and extracts the necessary data.

[0654] Output: Collected market trend data and sales data (stored in internal storage)

[0655] Step 2: Data analysis

[0656] server

[0657] Input: Market trend data and sales data stored in internal storage

[0658] What it does: The server runs machine learning models and statistical algorithms to analyze the data, for example, using scikit-learn to detect outliers and perform future predictions.

[0659] Data processing: Statistical processing and machine learning algorithms are used to detect specific trends and anomalies in the data.

[0660] Output: Analysis results (e.g., trend data and anomaly detection reports in JSON format)

[0661] Step 3: Visualization

[0662] server

[0663] Input: Analysis results (trend data and anomaly detection reports in JSON format)

[0664] What happens: The server uses a visualization library (e.g., D3.js or Matplotlib) to generate a visual representation.

[0665] Data processing: Converting analysis results into graphs, heat maps, trend lines, etc.

[0666] Output: Visualized data (graphs and heatmaps in SVG or HTML format)

[0667] Terminal

[0668] Input: Visualized data

[0669] Specific behavior: The device renders a UI to display the visualization data.

[0670] Output: Graphs and heatmaps displayed on the user's screen

[0671] Step 4: Emotion Recognition

[0672] Terminal

[0673] Input: User facial and voice data collected through the camera and microphone

[0674] Specific operation: The device uses (OpenCV) and (IBM Watson) to perform real-time sentiment analysis.

[0675] Data processing: Facial recognition and voice analysis algorithms are used to identify user emotions.

[0676] Output: Analyzed user emotion data (e.g., user is confused, satisfied, etc.)

[0677] server

[0678] Input: User emotion data sent from the device

[0679] Specific operation: The server analyzes the emotion data and uses it to adjust the visualization information.

[0680] Step 5: Dynamically adjust visualizations

[0681] server

[0682] Input: Parsed user emotion data

[0683] Specific behavior: The server dynamically adjusts the visualization based on the sentiment analysis results, for example, by increasing the details of the visualization or switching to a different visualization method.

[0684] Data manipulation: Re-rendering visualization data

[0685] Output: Adjusted visualization data (sent back to the terminal)

[0686] Terminal

[0687] Input: Reconciled visualization data

[0688] What happens: The device re-renders and displays the new visualization data.

[0689] Output: Information redisplayed on the user's screen

[0690] Step 6: Gather feedback and improve

[0691] User

[0692] Input: Feedback on the visualization (e.g., "This graph is difficult to understand")

[0693] Specific Action: The user provides feedback to the system.

[0694] Terminal

[0695] Input: User-provided feedback

[0696] Specific operation: The device collects feedback in text format and analyzes it using the emotion engine.

[0697] Data processing: Analysis of feedback and its tone

[0698] Output: Parsed feedback data (sent to server)

[0699] server

[0700] Input: Parsed feedback data

[0701] Specific operation: The server identifies areas for improvement in the visualization information based on the feedback data and updates the visualization data.

[0702] Data processing: generating new visualizations

[0703] Output: Visualized data reflecting the feedback (sent to the device)

[0704] Terminal

[0705] Input: Visualization data reflecting feedback

[0706] What happens: The device re-renders and displays the new visualization data.

[0707] Output: The improved information displayed on the user's screen

[0708] (Application example 2)

[0709] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0710] In autonomous vehicles, to optimize the user's driving experience and improve safety and comfort, it is necessary to accurately recognize the user's emotions and adjust the vehicle's operation and information display in real time based on that information. However, conventional systems have difficulty making such dynamic adjustments. A system that can solve this problem and provide a high-quality user experience is needed.

[0711] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0712] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, and means for dynamically adjusting the visualization information based on the recognized user's emotion, thereby enabling a high-quality driving experience for an autonomous vehicle and improving safety and comfort.

[0713] "Data source" refers to the information source or database from which the system gathers the information it needs.

[0714] "Means of analysis" refers to the function of analyzing collected data in various ways and extracting useful information.

[0715] "Means for visual display" refers to the function of converting the analysis results into visual representations such as graphs, heat maps, and trend lines in order to present them to the user in an easy-to-understand manner.

[0716] "Means for recognizing emotions" refers to machine learning models and sensors that automatically determine emotions from a user's facial expressions, voice, etc.

[0717] "Means for dynamic adjustment" refers to the ability to automatically change the system's visualizations and behavior in real time based on perceived changes in the user's emotions.

[0718] An "autonomous vehicle" is a vehicle that has the ability to travel automatically to a destination without direct operation by a driver.

[0719] "Safety" refers to the ability of a system or automated vehicle to minimize risk to the user.

[0720] "Comfort" refers to the sense of security and satisfaction that users feel when using the system or autonomous vehicle.

[0721] The embodiment of the present invention is a system for optimizing the driving experience of a user in an autonomous vehicle and improving safety and comfort, which mainly includes means for data collection, data analysis, visualization, emotion recognition, and dynamic adjustment.

[0722] Explanation of program processing

[0723] First, the server collects the necessary data from data sources, such as market trend data from external APIs and internal sales databases. Then, it analyzes the collected data using machine learning models and statistical algorithms to identify sales trends and market changes.

[0724] The analysis results are displayed visually, using graphs, heat maps, trend lines, and other visual representations to provide users with an easy-to-understand view of the data and its trends.

[0725] Next, the device recognizes the user's emotions. For this purpose, the smartphone's built-in camera and microphone are used. The camera is used to capture the user's facial expressions, and emotions are recognized using a deep learning model (using Keras and dlib). Voice data is also analyzed to help with emotion recognition.

[0726] Finally, the visualization and the autonomous vehicle's behavior can be dynamically adjusted based on the user's perceived emotions: for example, if the user expresses dissatisfaction or confusion, the visualization can be switched to a more detailed display, or the temperature or music in the car can be adjusted.

[0727] Hardware and software used

[0728] Deep learning model (Keras)

[0729] Face detection and landmark acquisition (dlib)

[0730] Image processing (OpenCV)

[0731] Sending API requests (Requests)

[0732] Specific examples

[0733] Market data visualization shows sales trend graphs and consumer behavior patterns, and controls the temperature and music in the car to enhance user comfort.

[0734] Prompt Sentence Examples

[0735] "If a user is confused, show them detailed market data and change the music in their car to something more relaxing."

[0736] "If the user is angry, prepare for an emergency shutdown."

[0737] Through these processes, the server can improve the user's driving experience, enhancing safety and comfort.

[0738] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0739] Step 1:

[0740] The server collects the required data from data sources. Data sources can include, for example, market trend data from external APIs or internal sales databases. The server sends requests to these data sources to collect the data. The input is an API request or a database query, and the output is the collected raw data.

[0741] Step 2:

[0742] The server analyzes the collected data. Specifically, it analyzes the collected sales data and market trend data using machine learning models and statistical algorithms. The input is the raw data collected in step 1, and the output is the analyzed results, such as sales trends and market changes.

[0743] Step 3:

[0744] The server visually displays the analysis results. It converts the analysis results into visual representations such as graphs, heat maps, and trend lines and provides them to the user in an easy-to-understand format. The input is the analysis results obtained in step 2, and the output is the visual display data.

[0745] Step 4:

[0746] The device recognizes the user's emotions. It uses the smartphone's built-in camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a deep learning model (using Keras and dlib). The input is camera images and audio data, and the output is the recognized user's emotions.

[0747] Step 5:

[0748] Based on the recognized user emotion, the server dynamically adjusts the visualization information and the behavior of the autonomous vehicle. For example, if the user expresses dissatisfaction or confusion, the server can switch to a more detailed information display or adjust the temperature or music inside the vehicle. The input is the user emotion recognized in step 4, and the output is the adjusted visualization information and vehicle behavior.

[0749] Through these steps, cooperation between servers, terminals, and users will be possible to improve the driving experience of autonomous vehicles, and to enhance safety and comfort.

[0750] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0751] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0752] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0753] [Third embodiment]

[0754] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0755] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0756] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0757] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0758] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0759] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0760] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0761] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0762] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0763] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0764] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0765] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0766] This invention is a system that provides high-quality visualization of the information needed for companies to respond quickly to uncertain market environments and achieve key performance indicators (KPIs).

[0767] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0768] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0769] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0770] Users can analyze the displayed visualization information and create specific action plans. They can also provide feedback as needed. For example, they can send feedback such as "We need more detailed sales data for the first quarter" to the server.

[0771] The server analyzes the collected feedback and identifies areas for improvement in the visualization. It then updates the visualization based on the feedback and presents it to the user again. Through this process, the system continuously improves and delivers the most effective information to users.

[0772] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, and feedback, and can provide information that allows companies to respond quickly and effectively to uncertain market environments. As a result, companies can not only more easily achieve their KPIs, but also make more accurate decisions.

[0773] The processing flow will be explained below.

[0774] Step 1:

[0775] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0776] Step 2:

[0777] The server sends requests to designated data sources to retrieve the required data. For example, the server may send requests to a market trends API to retrieve external market data, or query an internal database to gather sales data.

[0778] Step 3:

[0779] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0780] Step 4:

[0781] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0782] Step 5:

[0783] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0784] Step 6:

[0785] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0786] Step 7:

[0787] The user can provide feedback on the displayed visualization, for example, "I need more detailed sales data for the first quarter" to the server.

[0788] Step 8:

[0789] The server analyzes the collected feedback, identifies areas for improvement in the visualization, and updates and re-presents the visualization to the user based on the feedback.

[0790] Step 9:

[0791] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0792] Example 1

[0793] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0794] In order for companies to respond quickly to uncertain market conditions and achieve key performance indicators (KPIs), it is difficult to efficiently collect, analyze, visualize, and incorporate feedback from high-quality information. In particular, when data is collected from a wide range of sources, information collection and analysis can be a time-consuming process, resulting in the inability to make timely and effective decisions.

[0795] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0796] In this invention, the server includes means for a user to specify required information from a data source, means for collecting information based on the data source specified by the user, means for analyzing the collected information using a machine learning model or a statistical algorithm, means for converting the analysis results into a visual representation such as a graph, a heat map, or a trend line, means for displaying the visual representation on a terminal, means for collecting and analyzing feedback from users, and means for improving the visual representation based on the feedback, thereby enabling companies to respond quickly and effectively to uncertain market environments and make accurate decisions based on high-quality information.

[0797] "Data source" refers to the source or information source from which data is obtained.

[0798] "Information" includes data and content collected from data sources.

[0799] "User" refers to the end-user who operates the system and specifies, collects, analyzes, and provides feedback on required information.

[0800] "Server" refers to a central processing unit that collects, analyzes, visualizes, processes feedback, etc.

[0801] A "machine learning model" is an algorithm or model used in data analysis to derive patterns and predictions from data.

[0802] A "statistical algorithm" is a mathematical model or computational method used to analyze data and derive results.

[0803] "Analysis results" refers to the insights and conclusions obtained after analyzing data using machine learning models and statistical algorithms.

[0804] "Visual representation" refers to techniques and methods for presenting analytical results in easy-to-understand charts and graphs.

[0805] A "graph" is a form of visual display used to show data values ​​and trends.

[0806] A "heat map" is a visual representation that uses colors to show the relationships and distributions between specific variables.

[0807] A "trend line" is a line expressed as a straight or curved line that shows changes or trends in data.

[0808] "Terminal" refers to a device that allows a user to communicate with a server and display and manipulate data and visual presentations.

[0809] "Feedback" means any additional requests, comments or improvements provided by a User.

[0810] "High quality" means that the data and information are accurate, reliable, and useful as information for users to use in making decisions.

[0811] This invention is a system that provides high-quality visualization of the information companies need to respond quickly and effectively to uncertain market environments and achieve key performance indicators (KPIs).

[0812] First, the user specifies the information they want to collect from a data source (e.g., a market trend API or an internal sales database). Specifically, the user enters a request through the system interface, such as "collect data from the market trend API for the past six months."

[0813] The server collects information based on the data source specified by the user. In the case of an external API, the server sends a request, retrieves the response data in JSON format, and analyzes it. Specifically, the server sends a request such as "https: / / api.marketdata.com / v1 / trends?duration=6months" and analyzes the resulting data. In the case of an internal database, the server executes an SQL query to collect the required data. For example, a query such as "SELECT FROM sales_data WHERE date >= '2023-04-01'" is used.

[0814] The collected information is analyzed by the server. This analysis uses machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas). The server preprocesses the data and cleanses it by removing unnecessary data and missing values. For example, the server uses pandas to remove missing values ​​(e.g., "cleaned_data = raw_data.dropna()"), and then uses a scikit-learn linear regression model (e.g., "model.fit(X, y)") to predict sales trends.

[0815] Next, the server generates graphs, heat maps, and trend lines to visually represent the analysis results. For this, it uses libraries such as matplotlib and seaborn. Specifically, the server uses matplotlib to generate a sales trend graph with code like "plt.plot(dates, sales)", and seaborn to create a heat map showing market changes with "sns.heatmap(data)".

[0816] The visualized information is sent to the device and displayed to the user. The device then displays this visualized information in a dashboard on the browser, allowing the user to easily understand the data content and trends. For example, the user can click on the "Sales Trend" tab to view detailed graphs.

[0817] The user also analyzes the displayed information and provides feedback to the server as needed. For example, the user may send feedback such as, "I need more detailed sales data for Q1." The server analyzes this feedback, identifies areas for improvement in the visualization information, and provides it to the user again.

[0818] To illustrate this, here is an example of a prompt for a generative AI model:

[0819] "Please elaborate on how you collect data from market trend APIs and your internal sales database to analyze and visualize sales trends and market changes."

[0820] In this way, through a series of processes, from specifying raw data to collecting, analyzing, visualizing, and providing feedback, companies can respond quickly and effectively to market conditions and provide the information necessary to achieve KPIs.

[0821] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0822] Step 1:

[0823] The user inputs a data collection request into the system. Specifically, the user specifies the data source (e.g., a market trend API or an internal sales database) and sets parameters such as the collection period and type of information. The input request is sent to the server.

[0824] input:

[0825] Data source identifiers (e.g., API endpoints, database names)

[0826] Collection period (e.g., last 6 months)

[0827] Type of information (e.g., market trend data, sales data)

[0828] output:

[0829] Data Collection Request

[0830] Specific behavior:

[0831] The user opens the "Data Collection Request" form, fills in the required information, and clicks the "Submit" button.

[0832] Step 2:

[0833] Based on the data collection request received from the user, the server sends requests to the specified data sources to collect the required data, which may include sending API requests or executing SQL queries.

[0834] input:

[0835] Data Collection Request

[0836] output:

[0837] Data collected

[0838] Specific behavior:

[0839] The server sends a request like "https: / / api.marketdata.com / v1 / trends?duration=6months" and receives JSON data.

[0840] Execute the SQL query "SELECT FROM sales_data WHERE date >= '2023-04-01'" on the internal database to retrieve the data.

[0841] Step 3:

[0842] The server analyzes the collected data, which includes data preprocessing (e.g., removing missing values) and analysis using machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas).

[0843] input:

[0844] Data collected

[0845] output:

[0846] Analysis results

[0847] Specific behavior:

[0848] The server uses pandas to perform preprocessing such as "cleaned_data = raw_data.dropna()".

[0849] Use scikit-learn's linear regression model and run "model.fit(X, y)" to predict sales trends.

[0850] Step 4:

[0851] The server converts the analysis results into visual representations, using libraries such as matplotlib and seaborn to generate graphs and heatmaps.

[0852] input:

[0853] Analysis results

[0854] output:

[0855] Visualization data (graphs, heat maps, etc.)

[0856] Specific behavior:

[0857] The server uses matplotlib to create a sales trend graph using the code "plt.plot(dates, sales)".

[0858] Use seaborn to create a heatmap showing market changes with "sns.heatmap(data)".

[0859] Step 5:

[0860] The terminal receives the visualized data from the server and displays it to the user, allowing the user to easily understand the content and trends of the data.

[0861] input:

[0862] Visualized Data

[0863] output:

[0864] Visualization information displayed

[0865] Specific behavior:

[0866] The device displays graphs and heat maps on a dashboard.

[0867] Users can click on the "Sales Trends" tab to view detailed graphs.

[0868] Step 6:

[0869] The user analyzes the displayed visualization information and provides feedback as needed, for example by sending a request to the server saying, "I need detailed sales data for the first quarter."

[0870] input:

[0871] Visualization Information

[0872] Feedback Request

[0873] output:

[0874] Feedback requests to the server

[0875] Specific behavior:

[0876] The user fills in the feedback form with detailed data requests and clicks the "Submit" button.

[0877] Step 7:

[0878] The server analyzes the user's feedback and refines the visualization, which is then sent back to the terminal and displayed to the user.

[0879] input:

[0880] Feedback Request

[0881] output:

[0882] Improved visualization

[0883] Specific behavior:

[0884] The server will then query the data again based on the feedback to obtain any additional information needed.

[0885] Visualize new analysis results and send them to your device.

[0886] (Application example 1)

[0887] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] Companies need real-time data analysis and visualization to respond quickly and effectively to uncertain market conditions and achieve key performance indicators (KPIs). However, current systems do not adequately integrate and analyze market trends and sales data, making it difficult to utilize feedback for continuous improvement. As a result, there is a lack of effective information provision to support corporate decision-making.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0890] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for users to provide feedback, means for updating visualization information based on the feedback, means for collecting sales data from a store's sales database, means for acquiring market trend data from an API, means for analyzing the sales data and market trend data using a machine learning model, and means for generating sales trend graphs, inventory heat maps, and graphs showing market changes, thereby enabling companies to quickly and effectively respond to market conditions and visually grasp data to achieve KPIs in real time.

[0891] A "data source" is a data provider, such as an external API or an internal database, from which information or data is obtained.

[0892] "Analysis" is the process of analyzing collected data using machine learning models and statistical methods to extract useful information and trends.

[0893] "Visualization" is the process of converting analytical results into visual representations such as graphs, heat maps, and trend lines.

[0894] "Feedback" is information collected from users to improve the system.

[0895] A "sales database" is a database that stores and manages sales data collected by stores and companies.

[0896] "Market trend data" is data that shows consumer behavior and trends in a particular market, typically obtained from external APIs.

[0897] A "machine learning model" is an algorithm that learns using large amounts of data and makes predictions and classifications for future data.

[0898] A "sales trend graph" is a graph that visually shows fluctuations in sales over a specific period of time.

[0899] An "inventory heat map" is a visual representation that uses different colors to show inventory status, and is typically used to intuitively understand whether there is an excess or shortage of inventory.

[0900] A "graph showing market changes" is a graph that visually represents market trends and changes.

[0901] The present invention aims to build a system that provides information necessary for companies to respond quickly to market conditions and achieve key performance indicators (KPIs). Specific embodiments are described below.

[0902] System Configuration

[0903] Hardware:

[0904] Server, smartphone or tablet

[0905] software:

[0906] Python, Pandas, Matplotlib, fbprophet, Requests

[0907] Program processing explanation

[0908] Data collection:

[0909] The server collects market trend data using external APIs and also retrieves sales data from the store's sales database. This process gathers the necessary data.

[0910] Data Analysis:

[0911] The server analyzes the collected data using a machine learning model (specifically, a time-series forecasting model using the fbprophet library) to predict sales trends and market changes.

[0912] Visualization:

[0913] The server visualizes the analysis results, which are displayed in the form of sales trend graphs, inventory heat maps, and graphs showing market changes.

[0914] feedback:

[0915] Users can view the visualized information and provide feedback through their smartphones or tablets. For example, if they want to know more about the sales trends of a particular product, they can send a request to the server.

[0916] Information update:

[0917] The server updates the visualization based on user feedback, providing more accurate and useful information to the user.

[0918] Specific examples

[0919] For example, if the API URL is "https: / / api.example.com / market_data" and the database connection information is ("user", "password", "host", "database"), data collection will be performed based on this information.

[0920] Prompt Sentence Examples

[0921] As an example of a prompt sentence, the following text can be input into the generative model to obtain specific data and perform analysis.

[0922] Write Python code to retrieve market trend data from APIs such as the following and use Prophet to make predictions and visualizations:

[0923] API URL: https: / / api.example.com / market_data

[0924] Database connection information: user, password, host, database

[0925] Data to be acquired: Sales data and market trend data

[0926] Graph Visualization

[0927] Execution example:

[0928] market_data = fetch_market_data(api_url)

[0929] sales_data = fetch_sales_data(db_conn)

[0930] sales_forecast_data = sales_forecast(sales_data)

[0931] visualize_data(sales_forecast_data, market_data)

[0932] This allows users to make decisions based on real-time, accurate data.

[0933] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0934] Step 1:

[0935] The server collects market trend data from an external API. Specifically, it sends an API request and parses the JSON data returned as a response to extract the necessary information. At this stage, the API URL (e.g., "https: / / api.example.com / market_data") is the input, and the acquired market trend data is the output.

[0936] Step 2:

[0937] The server connects to the sales database and retrieves sales data. This involves running a SQL query to pull the required records from the database. The input to this step is the database connection information (e.g., user, password, host, database) and the output is the sales data.

[0938] Step 3:

[0939] The server inputs the collected market trend data and sales data into a machine learning model (e.g., the fbprophet library) to perform time series forecasting analysis. Here, the parsed data is fed into the model, which outputs analyzed sales trends and market forecasts.

[0940] Step 4:

[0941] The server visualizes the analysis results. Specifically, it uses Python's Matplotlib library to generate sales trend graphs, inventory heat maps, and graphs showing market changes. At this stage, the analysis results from the machine learning model are the input, and the visualized graphs are the output.

[0942] Step 5:

[0943] The user checks the visualized information on a smartphone or tablet. The visualized information is displayed on the user's device, allowing the user to perform detailed analysis. The input of this stage is the visualized graph, and the output is the user's understanding or analysis results.

[0944] Step 6:

[0945] The user provides feedback as needed. For example, the user sends feedback such as "I would like to know more about the sales trends of a particular product" to the server. At this stage, the user's feedback is the input, and the updated request based on that feedback is the output.

[0946] Step 7:

[0947] The server analyzes the user feedback and updates the visualization information. Based on the analyzed feedback, it improves the visualization graph and data display. The input of this step is the user feedback, and the output is the updated visualization information based on the feedback.

[0948] Through this series of steps, the system achieves a cycle of collection, analysis, visualization, and feedback in real time, providing useful information that enables companies to quickly respond to market conditions.

[0949] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0950] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. This system also combines an emotion engine that recognizes the user's emotions, enabling more effective information presentation.

[0951] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[0952] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[0953] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[0954] A distinctive feature of this invention is the incorporation of an emotion engine. The device monitors the user's facial expressions and speech, and the emotion engine recognizes the user's emotions. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0955] The emotion engine recognizes the user's emotions and uses them to dynamically adjust the visualization. For example, if the user expresses dissatisfaction or confusion, the server can provide more detailed visualizations or switch to a different display method based on the user's emotions.

[0956] Furthermore, user feedback is not just provided as text or a choice, but is also analyzed emotionally by an emotion engine. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0957] The server identifies areas for improvement in the visualization based on the collected feedback and the results of sentiment analysis. It then updates the visualization based on the feedback and presents it to the user again. This allows the system to continuously improve and provide the most effective information to users.

[0958] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, and can provide information that allows companies to respond quickly and effectively to uncertain market environments, making it easier for companies to achieve their KPIs and enabling more accurate decision-making.

[0959] The processing flow will be explained below.

[0960] Step 1:

[0961] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[0962] Step 2:

[0963] The server sends requests to designated data sources to retrieve the required data. For example, the server might send a request to a market trends API to retrieve external market data, while also querying an internal database to pull sales data.

[0964] Step 3:

[0965] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[0966] Step 4:

[0967] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[0968] Step 5:

[0969] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[0970] Step 6:

[0971] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[0972] Step 7:

[0973] The device monitors the user's facial expressions and speech, and recognizes the user's emotions using an emotion engine. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[0974] Step 8:

[0975] The user's emotions, as recognized by the emotion engine, are sent to the server, which then adjusts the visualization based on that information. For example, if the user is confused, the server can make the visualization more detailed or switch to a different display method.

[0976] Step 9:

[0977] The user can provide feedback on the displayed visualization, for example, by sending feedback to the server such as "I need more detailed sales data for the first quarter."

[0978] Step 10:

[0979] The server analyzes the collected feedback and identifies areas for improvement in the visualization. An emotion engine also performs emotional analysis. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[0980] Step 11:

[0981] The server updates the visualization based on the feedback and the results of the sentiment analysis, and sends the improved visualization to the device for re-presentation to the user.

[0982] Step 12:

[0983] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[0984] Example 2

[0985] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0986] Conventional data analysis systems focus on data collection, analysis, and visualization, but do not address the dynamic presentation of information that takes user emotions into account. This makes it difficult to provide information that takes into account the user's level of understanding and satisfaction, making effective decision-making difficult, especially when the market environment fluctuates in real time. To solve this problem, a system that recognizes user emotions and dynamically adjusts information presentation based on them is needed.

[0987] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0988] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, means for dynamically adjusting the visual display based on the recognized emotion, means for collecting and analyzing user feedback, and means for improving the visual display based on the collected feedback and the emotion recognition results. This makes it possible to dynamically adjust and provide information while taking user emotions into consideration, thereby helping companies to respond quickly and effectively to uncertain market environments.

[0989] A "data source" refers to a data provider, such as an external API or an internal database, from which the necessary information is obtained.

[0990] "Server" refers to a computer system that performs core functions of the system, such as data collection, analysis, visualization, emotion recognition, and feedback analysis.

[0991] "User" refers to the entity that uses this system to collect data, view analysis results, and provide feedback.

[0992] An "emotion engine" refers to software or algorithms that recognize and analyze emotions from a user's facial expressions, voice, etc.

[0993] "Visualization" refers to the process of presenting analytical results in a visually understandable format, such as graphs, heat maps, or trend lines.

[0994] "Feedback" refers to the opinions and impressions that users provide regarding visualized information.

[0995] "Dynamic adjustment" refers to the process of changing the displayed information and its format in real time or incrementally based on the user's emotion recognition results and feedback.

[0996] A "machine learning model" is an algorithm used to analyze data, specifically to learn patterns and trends from data and make predictions or detect anomalies.

[0997] "Analysis" refers to the process of extracting trends and characteristics from collected data using statistical methods and algorithms.

[0998] "Collection" refers to the process of obtaining the necessary information from designated data sources and incorporating it into the system.

[0999] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. The system has functions for data collection, analysis, visualization, emotion recognition, and feedback analysis, thereby improving user understanding and satisfaction.

[1000] First, the user specifies the specific data they are interested in. For example, they input a request to the system such as, "I want to collect market trends and my company's sales data for the first quarter of 2023." At this time, the user also provides the API key and authentication information for the data source.

[1001] The server then sends requests to the specified data sources to collect the required data. Specifically, it obtains market trend data using external APIs (e.g., Eikon API) and pulls sales data from internal databases (e.g., Salesforce). The collected data is then stored in internal storage.

[1002] The server analyzes the data stored in the internal storage. For analysis, machine learning models such as (scikit-learn) and statistical algorithms are used to detect trends and outliers in the data. The results of these analyses are then converted into JSON format and used in the subsequent visualization process.

[1003] The analysis results are visualized by the server. Based on the analysis results, visual representations such as graphs, heat maps, and trend lines are generated using libraries such as (D3.js) and (Matplotlib). For example, a trend graph showing monthly sales increases or decreases, or a heat map showing market fluctuations by color intensity, are generated.

[1004] The device collects data using a camera and microphone to recognize emotional information such as the user's facial expressions and voice. The collected emotional data is analyzed in real time using OpenCV or IBM Watson. The results of the emotion analysis are sent to a server and used to dynamically adjust the visualization information.

[1005] For example, if the user expresses confusion or dissatisfaction, the server can adjust the visualization based on that emotion by providing more detail or a different display method, thereby providing information that matches the user's emotion. This process improves the user's understanding and satisfaction.

[1006] Furthermore, users can provide feedback on the visualized information. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to deeply understand the content of the feedback. The server then identifies areas for improvement in the visualized information based on the collected feedback and the results of the emotion analysis, and updates the visualized information as necessary. The improved visualized information is then displayed again on the device and provided to the user.

[1007] Below are some specific examples of prompt sentences to input into the generative AI model.

[1008] "Describe a system that provides high-quality visualizations of the information companies need to quickly respond to uncertain market conditions. Also, detail how the system recognizes user emotions and dynamically adjusts visualizations."

[1009] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, thereby providing high-quality information that enables companies to respond quickly and effectively to uncertain market environments.

[1010] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1011] Explaining the program's processing flow step by step

[1012] Step 1: Data collection

[1013] User

[1014] Input: Data collection request (e.g., market trend data and sales data), API key, and authentication information

[1015] Specific operation: The user inputs the required data type and authentication information into the interface.

[1016] server

[1017] Input: User's data collection request

[1018] Specific operation: The server sends a request to a data source (e.g., an external API or an internal database).

[1019] Data processing: The server receives the response to the request and extracts the necessary data.

[1020] Output: Collected market trend data and sales data (stored in internal storage)

[1021] Step 2: Data analysis

[1022] server

[1023] Input: Market trend data and sales data stored in internal storage

[1024] What it does: The server runs machine learning models and statistical algorithms to analyze the data, for example, using scikit-learn to detect outliers and perform future predictions.

[1025] Data processing: Statistical processing and machine learning algorithms are used to detect specific trends and anomalies in the data.

[1026] Output: Analysis results (e.g., trend data and anomaly detection reports in JSON format)

[1027] Step 3: Visualization

[1028] server

[1029] Input: Analysis results (trend data and anomaly detection reports in JSON format)

[1030] What happens: The server uses a visualization library (e.g., D3.js or Matplotlib) to generate a visual representation.

[1031] Data processing: Converting analysis results into graphs, heat maps, trend lines, etc.

[1032] Output: Visualized data (graphs and heatmaps in SVG or HTML format)

[1033] Terminal

[1034] Input: Visualized data

[1035] Specific behavior: The device renders a UI to display the visualization data.

[1036] Output: Graphs and heatmaps displayed on the user's screen

[1037] Step 4: Emotion Recognition

[1038] Terminal

[1039] Input: User facial and voice data collected through the camera and microphone

[1040] Specific operation: The device uses (OpenCV) and (IBM Watson) to perform real-time sentiment analysis.

[1041] Data processing: Facial recognition and voice analysis algorithms are used to identify user emotions.

[1042] Output: Analyzed user emotion data (e.g., user is confused, satisfied, etc.)

[1043] server

[1044] Input: User emotion data sent from the device

[1045] Specific operation: The server analyzes the emotion data and uses it to adjust the visualization information.

[1046] Step 5: Dynamically adjust visualizations

[1047] server

[1048] Input: Parsed user emotion data

[1049] Specific behavior: The server dynamically adjusts the visualization based on the sentiment analysis results, for example, by increasing the details of the visualization or switching to a different visualization method.

[1050] Data manipulation: Re-rendering visualization data

[1051] Output: Adjusted visualization data (sent back to the terminal)

[1052] Terminal

[1053] Input: Reconciled visualization data

[1054] What happens: The device re-renders and displays the new visualization data.

[1055] Output: Information redisplayed on the user's screen

[1056] Step 6: Gather feedback and improve

[1057] User

[1058] Input: Feedback on the visualization (e.g., "This graph is difficult to understand")

[1059] Specific Action: The user provides feedback to the system.

[1060] Terminal

[1061] Input: User-provided feedback

[1062] Specific operation: The device collects feedback in text format and analyzes it using the emotion engine.

[1063] Data processing: Analysis of feedback and its tone

[1064] Output: Parsed feedback data (sent to server)

[1065] server

[1066] Input: Parsed feedback data

[1067] Specific operation: The server identifies areas for improvement in the visualization information based on the feedback data and updates the visualization data.

[1068] Data processing: generating new visualizations

[1069] Output: Visualized data reflecting the feedback (sent to the device)

[1070] Terminal

[1071] Input: Visualization data reflecting feedback

[1072] What happens: The device re-renders and displays the new visualization data.

[1073] Output: The improved information displayed on the user's screen

[1074] (Application example 2)

[1075] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1076] In autonomous vehicles, to optimize the user's driving experience and improve safety and comfort, it is necessary to accurately recognize the user's emotions and adjust the vehicle's operation and information display in real time based on that information. However, conventional systems have difficulty making such dynamic adjustments. A system that can solve this problem and provide a high-quality user experience is needed.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1078] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, and means for dynamically adjusting the visualization information based on the recognized user's emotion, thereby enabling a high-quality driving experience for an autonomous vehicle and improving safety and comfort.

[1079] "Data source" refers to the information source or database from which the system gathers the information it needs.

[1080] "Means of analysis" refers to the function of analyzing collected data in various ways and extracting useful information.

[1081] "Means for visual display" refers to the function of converting the analysis results into visual representations such as graphs, heat maps, and trend lines in order to present them to the user in an easy-to-understand manner.

[1082] "Means for recognizing emotions" refers to machine learning models and sensors that automatically determine emotions from a user's facial expressions, voice, etc.

[1083] "Means for dynamic adjustment" refers to the ability to automatically change the system's visualizations and behavior in real time based on perceived changes in the user's emotions.

[1084] An "autonomous vehicle" is a vehicle that has the ability to travel automatically to a destination without direct operation by a driver.

[1085] "Safety" refers to the ability of a system or automated vehicle to minimize risk to the user.

[1086] "Comfort" refers to the sense of security and satisfaction that users feel when using the system or autonomous vehicle.

[1087] An embodiment of the present invention is a system for optimizing a user's driving experience and improving safety and comfort in an autonomous vehicle, which mainly includes means for data collection, data analysis, visualization, emotion recognition, and dynamic adjustment.

[1088] Explanation of program processing

[1089] First, the server collects the necessary data from data sources, such as market trend data from external APIs and internal sales databases. Then, it analyzes the collected data using machine learning models and statistical algorithms to identify sales trends and market changes.

[1090] The analysis results are displayed visually, using graphs, heat maps, trend lines, and other visual representations to provide users with an easy-to-understand view of the data and its trends.

[1091] Next, the device recognizes the user's emotions. For this purpose, the smartphone's built-in camera and microphone are used. The camera is used to capture the user's facial expressions, and emotions are recognized using a deep learning model (using Keras and dlib). Voice data is also analyzed to help with emotion recognition.

[1092] Finally, the visualization and the autonomous vehicle's behavior can be dynamically adjusted based on the user's perceived emotions: for example, if the user expresses dissatisfaction or confusion, the visualization can be switched to a more detailed display, or the temperature or music in the car can be adjusted.

[1093] Hardware and software used

[1094] Deep learning model (Keras)

[1095] Face detection and landmark acquisition (dlib)

[1096] Image processing (OpenCV)

[1097] Sending API requests (Requests)

[1098] Specific examples

[1099] Market data visualization shows sales trend graphs and consumer behavior patterns, and controls the temperature and music in the car to enhance user comfort.

[1100] Prompt Sentence Examples

[1101] "If a user is confused, show them detailed market data and change the music in their car to something more relaxing."

[1102] "If the user is angry, prepare for an emergency shutdown."

[1103] Through these processes, the server can improve the user's driving experience, enhancing safety and comfort.

[1104] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1105] Step 1:

[1106] The server collects the required data from data sources. Data sources can include, for example, market trend data from external APIs or internal sales databases. The server sends requests to these data sources to collect the data. The input is an API request or a database query, and the output is the collected raw data.

[1107] Step 2:

[1108] The server analyzes the collected data. Specifically, it analyzes the collected sales data and market trend data using machine learning models and statistical algorithms. The input is the raw data collected in step 1, and the output is the analyzed results, such as sales trends and market changes.

[1109] Step 3:

[1110] The server visually displays the analysis results. It converts the analysis results into visual representations such as graphs, heat maps, and trend lines and provides them to the user in an easy-to-understand format. The input is the analysis results obtained in step 2, and the output is the visual display data.

[1111] Step 4:

[1112] The device recognizes the user's emotions. It uses the smartphone's built-in camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a deep learning model (using Keras and dlib). The input is camera images and audio data, and the output is the recognized user's emotions.

[1113] Step 5:

[1114] Based on the recognized user emotion, the server dynamically adjusts the visualization information and the behavior of the autonomous vehicle. For example, if the user expresses dissatisfaction or confusion, the server can switch to a more detailed information display or adjust the temperature or music inside the vehicle. The input is the user emotion recognized in step 4, and the output is the adjusted visualization information and vehicle behavior.

[1115] Through these steps, cooperation between servers, terminals, and users will be possible to improve the driving experience of autonomous vehicles, and to enhance safety and comfort.

[1116] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1117] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1118] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1119] [Fourth embodiment]

[1120] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1121] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1122] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1123] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1124] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1125] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1126] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1127] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1128] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1129] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1131] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1132] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1133] This invention is a system that provides high-quality visualization of the information needed for companies to respond quickly to uncertain market environments and achieve key performance indicators (KPIs).

[1134] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[1135] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[1136] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[1137] Users can analyze the displayed visualization information and create specific action plans. They can also provide feedback as needed. For example, they can send feedback such as "We need more detailed sales data for the first quarter" to the server.

[1138] The server analyzes the collected feedback and identifies areas for improvement in the visualization. It then updates the visualization based on the feedback and presents it to the user again. Through this process, the system continuously improves and delivers the most effective information to users.

[1139] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, and feedback, and can provide information that allows companies to respond quickly and effectively to uncertain market environments. As a result, companies can not only more easily achieve their KPIs, but also make more accurate decisions.

[1140] The processing flow will be explained below.

[1141] Step 1:

[1142] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[1143] Step 2:

[1144] The server sends requests to designated data sources to retrieve the required data. For example, the server may send requests to a market trends API to retrieve external market data, or query an internal database to gather sales data.

[1145] Step 3:

[1146] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[1147] Step 4:

[1148] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[1149] Step 5:

[1150] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[1151] Step 6:

[1152] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[1153] Step 7:

[1154] The user can provide feedback on the displayed visualization, for example, "I need more detailed sales data for the first quarter" to the server.

[1155] Step 8:

[1156] The server analyzes the collected feedback, identifies areas for improvement in the visualization, and updates and re-presents the visualization to the user based on the feedback.

[1157] Step 9:

[1158] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[1159] Example 1

[1160] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1161] In order for companies to respond quickly to uncertain market conditions and achieve key performance indicators (KPIs), it is difficult to efficiently collect, analyze, visualize, and incorporate feedback from high-quality information. In particular, when data is collected from a wide range of sources, information collection and analysis can be a time-consuming process, resulting in the inability to make timely and effective decisions.

[1162] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1163] In this invention, the server includes means for a user to specify required information from a data source, means for collecting information based on the data source specified by the user, means for analyzing the collected information using a machine learning model or a statistical algorithm, means for converting the analysis results into a visual representation such as a graph, a heat map, or a trend line, means for displaying the visual representation on a terminal, means for collecting and analyzing feedback from users, and means for improving the visual representation based on the feedback, thereby enabling companies to respond quickly and effectively to uncertain market environments and make accurate decisions based on high-quality information.

[1164] "Data source" refers to the source or information source from which data is obtained.

[1165] "Information" includes data and content collected from data sources.

[1166] "User" refers to the end-user who operates the system and specifies, collects, analyzes, and provides feedback on required information.

[1167] "Server" refers to a central processing unit that collects, analyzes, visualizes, processes feedback, etc.

[1168] A "machine learning model" is an algorithm or model used in data analysis to derive patterns and predictions from data.

[1169] A "statistical algorithm" is a mathematical model or computational method used to analyze data and derive results.

[1170] "Analysis results" refers to the insights and conclusions obtained after analyzing data using machine learning models and statistical algorithms.

[1171] "Visual representation" refers to techniques and methods for presenting analytical results in easy-to-understand charts and graphs.

[1172] A "graph" is a form of visual display used to show data values ​​and trends.

[1173] A "heat map" is a visual representation that uses colors to show the relationships and distributions between specific variables.

[1174] A "trend line" is a line expressed as a straight or curved line that shows changes or trends in data.

[1175] "Terminal" refers to a device that allows a user to communicate with a server and display and manipulate data and visual presentations.

[1176] "Feedback" means any additional requests, comments or improvements provided by a User.

[1177] "High quality" means that the data and information are accurate, reliable, and useful as information for users to use in making decisions.

[1178] This invention is a system that provides high-quality visualization of the information companies need to respond quickly and effectively to uncertain market environments and achieve key performance indicators (KPIs).

[1179] First, the user specifies the information they want to collect from a data source (e.g., a market trend API or an internal sales database). Specifically, the user enters a request through the system interface, such as "collect data from the market trend API for the past six months."

[1180] The server collects information based on the data source specified by the user. In the case of an external API, the server sends a request, retrieves the response data in JSON format, and analyzes it. Specifically, the server sends a request such as "https: / / api.marketdata.com / v1 / trends?duration=6months" and analyzes the resulting data. In the case of an internal database, the server executes an SQL query to collect the required data. For example, a query such as "SELECT FROM sales_data WHERE date >= '2023-04-01'" is used.

[1181] The collected information is analyzed by the server. This analysis uses machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas). The server preprocesses the data and cleanses it by removing unnecessary data and missing values. For example, the server uses pandas to remove missing values ​​(e.g., "cleaned_data = raw_data.dropna()"), and then uses a scikit-learn linear regression model (e.g., "model.fit(X, y)") to predict sales trends.

[1182] Next, the server generates graphs, heat maps, and trend lines to visually represent the analysis results. For this, it uses libraries such as matplotlib and seaborn. Specifically, the server uses matplotlib to generate a sales trend graph with code like "plt.plot(dates, sales)", and seaborn to create a heat map showing market changes with "sns.heatmap(data)".

[1183] The visualized information is sent to the device and displayed to the user. The device then displays this visualized information in a dashboard on the browser, allowing the user to easily understand the data content and trends. For example, the user can click on the "Sales Trend" tab to view detailed graphs.

[1184] The user also analyzes the displayed information and provides feedback to the server as needed. For example, the user may send feedback such as, "I need more detailed sales data for Q1." The server analyzes this feedback, identifies areas for improvement in the visualization information, and provides it to the user again.

[1185] To illustrate this, here is an example of a prompt for a generative AI model:

[1186] "Please elaborate on how you collect data from market trend APIs and your internal sales database to analyze and visualize sales trends and market changes."

[1187] In this way, through a series of processes, from specifying raw data to collecting, analyzing, visualizing, and providing feedback, companies can respond quickly and effectively to market conditions and provide the information necessary to achieve KPIs.

[1188] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1189] Step 1:

[1190] The user inputs a data collection request into the system. Specifically, the user specifies the data source (e.g., a market trend API or an internal sales database) and sets parameters such as the collection period and type of information. The input request is sent to the server.

[1191] input:

[1192] Data source identifiers (e.g., API endpoints, database names)

[1193] Collection period (e.g., last 6 months)

[1194] Type of information (e.g., market trend data, sales data)

[1195] output:

[1196] Data Collection Request

[1197] Specific behavior:

[1198] The user opens the "Data Collection Request" form, fills in the required information, and clicks the "Submit" button.

[1199] Step 2:

[1200] Based on the data collection request received from the user, the server sends requests to the specified data sources to collect the required data, which may include sending API requests or executing SQL queries.

[1201] input:

[1202] Data Collection Request

[1203] output:

[1204] Data collected

[1205] Specific behavior:

[1206] The server sends a request like "https: / / api.marketdata.com / v1 / trends?duration=6months" and receives JSON data.

[1207] Execute the SQL query "SELECT FROM sales_data WHERE date >= '2023-04-01'" on the internal database to retrieve the data.

[1208] Step 3:

[1209] The server analyzes the collected data, which includes data preprocessing (e.g., removing missing values) and analysis using machine learning models (e.g., scikit-learn) and statistical algorithms (e.g., pandas).

[1210] input:

[1211] Data collected

[1212] output:

[1213] Analysis results

[1214] Specific behavior:

[1215] The server uses pandas to perform preprocessing such as "cleaned_data = raw_data.dropna()".

[1216] Use scikit-learn's linear regression model and run "model.fit(X, y)" to predict sales trends.

[1217] Step 4:

[1218] The server converts the analysis results into visual representations, using libraries such as matplotlib and seaborn to generate graphs and heatmaps.

[1219] input:

[1220] Analysis results

[1221] output:

[1222] Visualization data (graphs, heat maps, etc.)

[1223] Specific behavior:

[1224] The server uses matplotlib to create a sales trend graph using the code "plt.plot(dates, sales)".

[1225] Use seaborn to create a heatmap showing market changes with "sns.heatmap(data)".

[1226] Step 5:

[1227] The terminal receives the visualized data from the server and displays it to the user, allowing the user to easily understand the content and trends of the data.

[1228] input:

[1229] Visualized Data

[1230] output:

[1231] Visualization information displayed

[1232] Specific behavior:

[1233] The device displays graphs and heat maps on a dashboard.

[1234] Users can click on the "Sales Trends" tab to view detailed graphs.

[1235] Step 6:

[1236] The user analyzes the displayed visualization information and provides feedback as needed, for example by sending a request to the server saying, "I need detailed sales data for the first quarter."

[1237] input:

[1238] Visualization Information

[1239] Feedback Request

[1240] output:

[1241] Feedback requests to the server

[1242] Specific behavior:

[1243] The user fills in the feedback form with detailed data requests and clicks the "Submit" button.

[1244] Step 7:

[1245] The server analyzes the user's feedback and refines the visualization, which is then sent back to the terminal and displayed to the user.

[1246] input:

[1247] Feedback Request

[1248] output:

[1249] Improved visualization

[1250] Specific behavior:

[1251] The server will then query the data again based on the feedback to obtain any additional information needed.

[1252] Visualize new analysis results and send them to your device.

[1253] (Application example 1)

[1254] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1255] Companies need real-time data analysis and visualization to respond quickly and effectively to uncertain market conditions and achieve key performance indicators (KPIs). However, current systems do not adequately integrate and analyze market trends and sales data, making it difficult to utilize feedback for continuous improvement. As a result, there is a lack of effective information provision to support corporate decision-making.

[1256] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1257] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for users to provide feedback, means for updating visualization information based on the feedback, means for collecting sales data from a store's sales database, means for acquiring market trend data from an API, means for analyzing the sales data and market trend data using a machine learning model, and means for generating sales trend graphs, inventory heat maps, and graphs showing market changes, thereby enabling companies to quickly and effectively respond to market conditions and visually grasp data to achieve KPIs in real time.

[1258] A "data source" is a data provider, such as an external API or an internal database, from which information or data is obtained.

[1259] "Analysis" is the process of analyzing collected data using machine learning models and statistical methods to extract useful information and trends.

[1260] "Visualization" is the process of converting analytical results into visual representations such as graphs, heat maps, and trend lines.

[1261] "Feedback" is information collected from users to improve the system.

[1262] A "sales database" is a database that stores and manages sales data collected by stores and companies.

[1263] "Market trend data" is data that shows consumer behavior and trends in a particular market, typically obtained from external APIs.

[1264] A "machine learning model" is an algorithm that learns using large amounts of data and makes predictions and classifications for future data.

[1265] A "sales trend graph" is a graph that visually shows fluctuations in sales over a specific period of time.

[1266] An "inventory heat map" is a visual representation that uses different colors to show inventory status, and is typically used to intuitively understand whether there is an excess or shortage of inventory.

[1267] A "graph showing market changes" is a graph that visually represents market trends and changes.

[1268] The present invention aims to build a system that provides information necessary for companies to respond quickly to market conditions and achieve key performance indicators (KPIs). Specific embodiments are described below.

[1269] System Configuration

[1270] Hardware:

[1271] Server, smartphone or tablet

[1272] software:

[1273] Python, Pandas, Matplotlib, fbprophet, Requests

[1274] Program processing explanation

[1275] Data collection:

[1276] The server collects market trend data using external APIs and also retrieves sales data from the store's sales database. This process gathers the necessary data.

[1277] Data Analysis:

[1278] The server analyzes the collected data using a machine learning model (specifically, a time-series forecasting model using the fbprophet library) to predict sales trends and market changes.

[1279] Visualization:

[1280] The server visualizes the analysis results, which are displayed in the form of sales trend graphs, inventory heat maps, and graphs showing market changes.

[1281] feedback:

[1282] Users can view the visualized information and provide feedback through their smartphones or tablets. For example, if they want to know more about the sales trends of a particular product, they can send a request to the server.

[1283] Information update:

[1284] The server updates the visualization based on user feedback, providing more accurate and useful information to the user.

[1285] Specific examples

[1286] For example, if the API URL is "https: / / api.example.com / market_data" and the database connection information is ("user", "password", "host", "database"), data collection will be performed based on this information.

[1287] Prompt Sentence Examples

[1288] As an example of a prompt sentence, the following text can be input into the generative model to obtain specific data and perform analysis.

[1289] Write Python code to retrieve market trend data from APIs such as the following and use Prophet to make predictions and visualizations:

[1290] API URL: https: / / api.example.com / market_data

[1291] Database connection information: user, password, host, database

[1292] Data to be acquired: Sales data and market trend data

[1293] Graph Visualization

[1294] Execution example:

[1295] market_data = fetch_market_data(api_url)

[1296] sales_data = fetch_sales_data(db_conn)

[1297] sales_forecast_data = sales_forecast(sales_data)

[1298] visualize_data(sales_forecast_data, market_data)

[1299] This allows users to make decisions based on real-time, accurate data.

[1300] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1301] Step 1:

[1302] The server collects market trend data from an external API. Specifically, it sends an API request and parses the JSON data returned as a response to extract the necessary information. At this stage, the API URL (e.g., "https: / / api.example.com / market_data") is the input, and the acquired market trend data is the output.

[1303] Step 2:

[1304] The server connects to the sales database and retrieves sales data. This involves running a SQL query to pull the required records from the database. The input to this step is the database connection information (e.g., user, password, host, database) and the output is the sales data.

[1305] Step 3:

[1306] The server inputs the collected market trend data and sales data into a machine learning model (e.g., the fbprophet library) to perform time series forecasting analysis. Here, the parsed data is fed into the model, which outputs analyzed sales trends and market forecasts.

[1307] Step 4:

[1308] The server visualizes the analysis results. Specifically, it uses Python's Matplotlib library to generate sales trend graphs, inventory heat maps, and graphs showing market changes. At this stage, the analysis results from the machine learning model are the input, and the visualized graphs are the output.

[1309] Step 5:

[1310] The user checks the visualized information on a smartphone or tablet. The visualized information is displayed on the user's device, allowing the user to perform detailed analysis. The input of this stage is the visualized graph, and the output is the user's understanding or analysis results.

[1311] Step 6:

[1312] The user provides feedback as needed. For example, the user sends feedback such as "I would like to know more about the sales trends of a particular product" to the server. At this stage, the user's feedback is the input, and the updated request based on that feedback is the output.

[1313] Step 7:

[1314] The server analyzes the user feedback and updates the visualization information. Based on the analyzed feedback, it improves the visualization graph and data display. The input of this step is the user feedback, and the output is the updated visualization information based on the feedback.

[1315] Through this series of steps, the system achieves a cycle of collection, analysis, visualization, and feedback in real time, providing useful information that enables companies to quickly respond to market conditions.

[1316] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1317] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. This system also combines an emotion engine that recognizes the user's emotions, enabling more effective information presentation.

[1318] First, the user specifies the data they want to collect from a data source (e.g., a market trend API or an internal sales database). The server then sends a request to the specified data source and collects the data. Specifically, it can retrieve market trend data from an external API and pull sales data from an internal database.

[1319] The collected data is analyzed by the server using machine learning models and statistical algorithms. For example, the server analyzes the collected sales data and market trend data to identify sales trends and market changes.

[1320] Next, the analysis results are visualized. The server converts the analysis results into visual representations such as graphs, heat maps, and trend lines. This makes it easier for users to visually understand the content and trends of the data. As a practical example, the server generates a sales trend graph or a heat map showing market changes and displays them on the terminal.

[1321] A distinctive feature of this invention is the incorporation of an emotion engine. The device monitors the user's facial expressions and speech, and the emotion engine recognizes the user's emotions. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[1322] The emotion engine recognizes the user's emotions and uses them to dynamically adjust the visualization. For example, if the user expresses dissatisfaction or confusion, the server can provide more detailed visualizations or switch to a different display method based on the user's emotions.

[1323] Furthermore, user feedback is not just provided as text or a choice, but is also analyzed emotionally by an emotion engine. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[1324] The server identifies areas for improvement in the visualization based on the collected feedback and the results of sentiment analysis. It then updates the visualization based on the feedback and presents it to the user again. This allows the system to continuously improve and provide the most effective information to users.

[1325] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, and can provide information that allows companies to respond quickly and effectively to uncertain market environments, making it easier for companies to achieve their KPIs and enabling more accurate decision-making.

[1326] The processing flow will be explained below.

[1327] Step 1:

[1328] Users specify a data source and issue a data collection request, which can include sources such as market trend APIs or internal databases.

[1329] Step 2:

[1330] The server sends requests to designated data sources to retrieve the required data. For example, the server might send a request to a market trends API to retrieve external market data, while also querying an internal database to pull sales data.

[1331] Step 3:

[1332] The collected data is integrated by the server and organized into a single dataset, which is then prepared for analysis.

[1333] Step 4:

[1334] The server uses machine learning models and statistical algorithms to analyze the collected data, specifically sales and market activity data, to identify significant patterns and trends.

[1335] Step 5:

[1336] Based on the analysis results, the server generates visual representations, which can include graphs, heat maps, trend lines, etc. The server selects an appropriate visualization method to display the analysis results in an easy-to-understand manner.

[1337] Step 6:

[1338] The terminal displays the generated visual representation to the user, who can view the visualized information and intuitively understand the content and trends of the data.

[1339] Step 7:

[1340] The device monitors the user's facial expressions and speech, and recognizes the user's emotions using an emotion engine. For example, the device's camera and microphone collect the user's facial expressions and voice, and the emotion engine analyzes the data.

[1341] Step 8:

[1342] The user's emotions, as recognized by the emotion engine, are sent to the server, which then adjusts the visualization based on that information. For example, if the user is confused, the server can make the visualization more detailed or switch to a different display method.

[1343] Step 9:

[1344] The user can provide feedback on the displayed visualization, for example, by sending feedback to the server such as "I need more detailed sales data for the first quarter."

[1345] Step 10:

[1346] The server analyzes the collected feedback and identifies areas for improvement in the visualization. An emotion engine also performs emotional analysis. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to gain a deeper understanding of the feedback.

[1347] Step 11:

[1348] The server updates the visualization based on the feedback and the results of the sentiment analysis, and sends the improved visualization to the device for re-presentation to the user.

[1349] Step 12:

[1350] The device will then redisplay the improved visualization, allowing the user to review the updated information and develop a more specific action plan.

[1351] Example 2

[1352] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1353] Conventional data analysis systems focus on data collection, analysis, and visualization, but do not address the dynamic presentation of information that takes user emotions into account. This makes it difficult to provide information that takes into account the user's level of understanding and satisfaction, making effective decision-making difficult, especially when the market environment fluctuates in real time. To solve this problem, a system that recognizes user emotions and dynamically adjusts information presentation based on them is needed.

[1354] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1355] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, means for dynamically adjusting the visual display based on the recognized emotion, means for collecting and analyzing user feedback, and means for improving the visual display based on the collected feedback and the emotion recognition results. This makes it possible to dynamically adjust and provide information while taking user emotions into consideration, thereby helping companies to respond quickly and effectively to uncertain market environments.

[1356] A "data source" refers to a data provider, such as an external API or an internal database, from which the necessary information is obtained.

[1357] "Server" refers to a computer system that performs core functions of the system, such as data collection, analysis, visualization, emotion recognition, and feedback analysis.

[1358] "User" refers to the entity that uses this system to collect data, view analysis results, and provide feedback.

[1359] An "emotion engine" refers to software or algorithms that recognize and analyze emotions from a user's facial expressions, voice, etc.

[1360] "Visualization" refers to the process of presenting analytical results in a visually understandable format, such as graphs, heat maps, or trend lines.

[1361] "Feedback" refers to the opinions and impressions that users provide regarding visualized information.

[1362] "Dynamic adjustment" refers to the process of changing the displayed information and its format in real time or incrementally based on the user's emotion recognition results and feedback.

[1363] A "machine learning model" is an algorithm used to analyze data, specifically to learn patterns and trends from data and make predictions or detect anomalies.

[1364] "Analysis" refers to the process of extracting trends and characteristics from collected data using statistical methods and algorithms.

[1365] "Collection" refers to the process of obtaining the necessary information from designated data sources and incorporating it into the system.

[1366] This invention is a system that visualizes the information necessary for companies to quickly respond to uncertain market environments and achieve key performance indicators (KPIs) with high quality. The system has functions for data collection, analysis, visualization, emotion recognition, and feedback analysis, thereby improving user understanding and satisfaction.

[1367] First, the user specifies the specific data they are interested in. For example, they input a request to the system such as, "I want to collect market trends and my company's sales data for the first quarter of 2023." At this time, the user also provides the API key and authentication information for the data source.

[1368] The server then sends requests to the specified data sources to collect the required data. Specifically, it obtains market trend data using external APIs (e.g., Eikon API) and pulls sales data from internal databases (e.g., Salesforce). The collected data is then stored in internal storage.

[1369] The server analyzes the data stored in the internal storage. For analysis, machine learning models such as (scikit-learn) and statistical algorithms are used to detect trends and outliers in the data. The results of these analyses are then converted into JSON format and used in the subsequent visualization process.

[1370] The analysis results are visualized by the server. Based on the analysis results, visual representations such as graphs, heat maps, and trend lines are generated using libraries such as (D3.js) and (Matplotlib). For example, a trend graph showing monthly sales increases or decreases, or a heat map showing market fluctuations by color intensity, are generated.

[1371] The device collects data using a camera and microphone to recognize emotional information such as the user's facial expressions and voice. The collected emotional data is analyzed in real time using OpenCV or IBM Watson. The results of the emotion analysis are sent to a server and used to dynamically adjust the visualization information.

[1372] For example, if the user expresses confusion or dissatisfaction, the server can adjust the visualization based on that emotion by providing more detail or a different display method, thereby providing information that matches the user's emotion. This process improves the user's understanding and satisfaction.

[1373] Furthermore, users can provide feedback on the visualized information. For example, if a user says, "This graph is difficult to understand," the emotion engine analyzes the tone and facial expression of the comment to deeply understand the content of the feedback. The server then identifies areas for improvement in the visualized information based on the collected feedback and the results of the emotion analysis, and updates the visualized information as necessary. The improved visualized information is then displayed again on the device and provided to the user.

[1374] Below are some specific examples of prompt sentences to input into the generative AI model.

[1375] "Describe a system that provides high-quality visualizations of the information companies need to quickly respond to uncertain market conditions. Also, detail how the system recognizes user emotions and dynamically adjusts visualizations."

[1376] In this way, the system of the present invention includes the steps of data collection, analysis, visualization, feedback, and emotion recognition, thereby providing high-quality information that enables companies to respond quickly and effectively to uncertain market environments.

[1377] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1378] Explaining the program's processing flow step by step

[1379] Step 1: Data collection

[1380] User

[1381] Input: Data collection request (e.g., market trend data and sales data), API key, and authentication information

[1382] Specific operation: The user inputs the required data type and authentication information into the interface.

[1383] server

[1384] Input: User's data collection request

[1385] Specific operation: The server sends a request to a data source (e.g., an external API or an internal database).

[1386] Data processing: The server receives the response to the request and extracts the necessary data.

[1387] Output: Collected market trend data and sales data (stored in internal storage)

[1388] Step 2: Data analysis

[1389] server

[1390] Input: Market trend data and sales data stored in internal storage

[1391] What it does: The server runs machine learning models and statistical algorithms to analyze the data, for example, using scikit-learn to detect outliers and perform future predictions.

[1392] Data processing: Statistical processing and machine learning algorithms are used to detect specific trends and anomalies in the data.

[1393] Output: Analysis results (e.g., trend data and anomaly detection reports in JSON format)

[1394] Step 3: Visualization

[1395] server

[1396] Input: Analysis results (trend data and anomaly detection reports in JSON format)

[1397] What happens: The server uses a visualization library (e.g., D3.js or Matplotlib) to generate a visual representation.

[1398] Data processing: Converting analysis results into graphs, heat maps, trend lines, etc.

[1399] Output: Visualized data (graphs and heatmaps in SVG or HTML format)

[1400] Terminal

[1401] Input: Visualized data

[1402] Specific behavior: The device renders a UI to display the visualization data.

[1403] Output: Graphs and heatmaps displayed on the user's screen

[1404] Step 4: Emotion Recognition

[1405] Terminal

[1406] Input: User facial and voice data collected through the camera and microphone

[1407] Specific operation: The device uses (OpenCV) and (IBM Watson) to perform real-time sentiment analysis.

[1408] Data processing: Facial recognition and voice analysis algorithms are used to identify user emotions.

[1409] Output: Analyzed user emotion data (e.g., user is confused, satisfied, etc.)

[1410] server

[1411] Input: User emotion data sent from the device

[1412] Specific operation: The server analyzes the emotion data and uses it to adjust the visualization information.

[1413] Step 5: Dynamically adjust visualizations

[1414] server

[1415] Input: Parsed user emotion data

[1416] Specific behavior: The server dynamically adjusts the visualization based on the sentiment analysis results, for example, by increasing the details of the visualization or switching to a different visualization method.

[1417] Data manipulation: Re-rendering visualization data

[1418] Output: Adjusted visualization data (sent back to the terminal)

[1419] Terminal

[1420] Input: Reconciled visualization data

[1421] What happens: The device re-renders and displays the new visualization data.

[1422] Output: Information redisplayed on the user's screen

[1423] Step 6: Gather feedback and improve

[1424] User

[1425] Input: Feedback on the visualization (e.g., "This graph is difficult to understand")

[1426] Specific Action: The user provides feedback to the system.

[1427] Terminal

[1428] Input: User-provided feedback

[1429] Specific operation: The device collects feedback in text format and analyzes it using the emotion engine.

[1430] Data processing: Analysis of feedback and its tone

[1431] Output: Parsed feedback data (sent to server)

[1432] server

[1433] Input: Parsed feedback data

[1434] Specific operation: The server identifies areas for improvement in the visualization information based on the feedback data and updates the visualization data.

[1435] Data processing: generating new visualizations

[1436] Output: Visualized data reflecting the feedback (sent to the device)

[1437] Terminal

[1438] Input: Visualization data reflecting feedback

[1439] What happens: The device re-renders and displays the new visualization data.

[1440] Output: The improved information displayed on the user's screen

[1441] (Application example 2)

[1442] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1443] In autonomous vehicles, to optimize the user's driving experience and improve safety and comfort, it is necessary to accurately recognize the user's emotions and adjust the vehicle's operation and information display in real time based on that information. However, conventional systems have difficulty making such dynamic adjustments. A system that can solve this problem and provide a high-quality user experience is needed.

[1444] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1445] In this invention, the server includes means for collecting necessary data from data sources, means for analyzing the collected data, means for visually displaying the analysis results, means for recognizing a user's emotion, and means for dynamically adjusting the visualization information based on the recognized user's emotion, thereby enabling a high-quality driving experience for an autonomous vehicle and improving safety and comfort.

[1446] "Data source" refers to the information source or database from which the system gathers the information it needs.

[1447] "Means of analysis" refers to the function of analyzing collected data in various ways and extracting useful information.

[1448] "Means for visual display" refers to the function of converting the analysis results into visual representations such as graphs, heat maps, and trend lines in order to present them to the user in an easy-to-understand manner.

[1449] "Means for recognizing emotions" refers to machine learning models and sensors that automatically determine emotions from a user's facial expressions, voice, etc.

[1450] "Means for dynamic adjustment" refers to the ability to automatically change the system's visualizations and behavior in real time based on perceived changes in the user's emotions.

[1451] An "autonomous vehicle" is a vehicle that has the ability to travel automatically to a destination without direct operation by a driver.

[1452] "Safety" refers to the ability of a system or automated vehicle to minimize risk to the user.

[1453] "Comfort" refers to the sense of security and satisfaction that users feel when using the system or autonomous vehicle.

[1454] The embodiment of the present invention is a system for optimizing the driving experience of a user in an autonomous vehicle and improving safety and comfort, which mainly includes means for data collection, data analysis, visualization, emotion recognition, and dynamic adjustment.

[1455] Explanation of program processing

[1456] First, the server collects the necessary data from data sources, such as market trend data from external APIs and internal sales databases. Then, it analyzes the collected data using machine learning models and statistical algorithms to identify sales trends and market changes.

[1457] The analysis results are displayed visually, using graphs, heat maps, trend lines, and other visual representations to provide users with an easy-to-understand view of the data and its trends.

[1458] Next, the device recognizes the user's emotions. For this purpose, the smartphone's built-in camera and microphone are used. The camera is used to capture the user's facial expressions, and emotions are recognized using a deep learning model (using Keras and dlib). Voice data is also analyzed to help with emotion recognition.

[1459] Finally, the visualization and the autonomous vehicle's behavior can be dynamically adjusted based on the user's perceived emotions: for example, if the user expresses dissatisfaction or confusion, the visualization can be switched to a more detailed display, or the temperature or music in the car can be adjusted.

[1460] Hardware and software used

[1461] Deep learning model (Keras)

[1462] Face detection and landmark acquisition (dlib)

[1463] Image processing (OpenCV)

[1464] Sending API requests (Requests)

[1465] Specific examples

[1466] Market data visualization shows sales trend graphs and consumer behavior patterns, and controls the temperature and music in the car to enhance user comfort.

[1467] Prompt Sentence Examples

[1468] "If a user is confused, show them detailed market data and change the music in their car to something more relaxing."

[1469] "If the user is angry, prepare for an emergency shutdown."

[1470] Through these processes, the server can improve the user's driving experience, enhancing safety and comfort.

[1471] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1472] Step 1:

[1473] The server collects the required data from data sources. Data sources can include, for example, market trend data from external APIs or internal sales databases. The server sends requests to these data sources to collect the data. The input is an API request or a database query, and the output is the collected raw data.

[1474] Step 2:

[1475] The server analyzes the collected data. Specifically, it analyzes the collected sales data and market trend data using machine learning models and statistical algorithms. The input is the raw data collected in step 1, and the output is the analyzed results, such as sales trends and market changes.

[1476] Step 3:

[1477] The server visually displays the analysis results. It converts the analysis results into visual representations such as graphs, heat maps, and trend lines and provides them to the user in an easy-to-understand format. The input is the analysis results obtained in step 2, and the output is the visual display data.

[1478] Step 4:

[1479] The device recognizes the user's emotions. It uses the smartphone's built-in camera and microphone to capture the user's facial expressions and voice, and recognizes emotions using a deep learning model (using Keras and dlib). The input is camera images and audio data, and the output is the recognized user's emotions.

[1480] Step 5:

[1481] Based on the recognized user emotion, the server dynamically adjusts the visualization information and the behavior of the autonomous vehicle. For example, if the user expresses dissatisfaction or confusion, the server can switch to a more detailed information display or adjust the temperature or music inside the vehicle. The input is the user emotion recognized in step 4, and the output is the adjusted visualization information and vehicle behavior.

[1482] Through these steps, cooperation between servers, terminals, and users will be possible to improve the driving experience of autonomous vehicles, and to enhance safety and comfort.

[1483] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1484] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1485] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1486] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1487] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1488] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1489] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1490] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1491] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1492] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1493] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1494] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1495] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1496] 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.

[1497] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1498] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1499] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1500] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1501] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1502] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1503] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1504] The following is further disclosed regarding the above embodiment.

[1505] (Claim 1)

[1506] A means of collecting the required data from the data sources;

[1507] a means for analyzing the collected data;

[1508] A system including a means for visually displaying the analysis results.

[1509] (Claim 2)

[1510] 10. The system of claim 1, wherein the collected data is analyzed using a machine learning model.

[1511] (Claim 3)

[1512] 10. The system of claim 1, wherein the analysis results are converted into a visual representation such as a graph, heat map, or trend line.

[1513] (Claim 4)

[1514] 10. The system of claim 1, further comprising means for collecting feedback from a user and updating the visualization information.

[1515] "Example 1"

[1516] (Claim 1)

[1517] a means for a user to specify the information required from the data source;

[1518] a means for collecting information based on user-specified data sources;

[1519] A means of analyzing the collected information using machine learning models and statistical algorithms;

[1520] A means of converting analytical results into visual representations such as graphs, heat maps, and trend lines;

[1521] means for displaying a visual representation on a terminal;

[1522] a means for collecting and analyzing user feedback;

[1523] a means of improving the visual representation based on feedback;

[1524] A system including:

[1525] (Claim 2)

[1526] 2. The system of claim 1, wherein the collected information is analyzed using machine learning models and statistical algorithms.

[1527] (Claim 3)

[1528] The system of claim 1, wherein the analysis results are converted into visual representations such as graphs, heat maps, trend lines, etc., and displayed on a terminal.

[1529] "Application Example 1"

[1530] (Claim 1)

[1531] A means of collecting the required data from the data sources;

[1532] a means for analyzing the collected data;

[1533] a means for visually displaying the analysis results;

[1534] a means for users to provide feedback;

[1535] means for updating the visualization based on the feedback;

[1536] A means of collecting sales data from the store's sales database and a means of obtaining market trend data from an API.

[1537] A means of analyzing sales and market trend data using machine learning models; and

[1538] means for generating sales trend graphs, inventory heat maps, and graphs showing market changes;

[1539] A system including:

[1540] (Claim 2)

[1541] 10. The system of claim 1, wherein the collected data is analyzed using a machine learning model.

[1542] (Claim 3)

[1543] 10. The system of claim 1, wherein the analysis results are converted into a visual representation such as a graph, heat map, or trend line.

[1544] "Example 2: Combining Emotion Engines"

[1545] (Claim 1)

[1546] A means of collecting the required data from the data sources;

[1547] a means for analyzing the collected data;

[1548] a means for visually displaying the analysis results;

[1549] means for recognizing a user's emotion;

[1550] means for dynamically adjusting the visual display based on the recognized emotion;

[1551] a means for collecting and analyzing user feedback;

[1552] The system includes a means for improving the visual display based on collected feedback and emotion recognition results.

[1553] (Claim 2)

[1554] 10. The system of claim 1, wherein the collected data is analyzed using a machine learning model.

[1555] (Claim 3)

[1556] 10. The system of claim 1, wherein the analysis results are converted into a visual representation such as a graph, heat map, or trend line.

[1557] "Application example 2 when combining emotion engines"

[1558] (Claim 1)

[1559] A means of collecting the required data from the data sources;

[1560] a means for analyzing the collected data;

[1561] a means for visually displaying the analysis results;

[1562] means for recognizing a user's emotion;

[1563] means for dynamically adjusting the visualization information based on the recognized user emotion;

[1564] A system including:

[1565] (Claim 2)

[1566] 10. The system of claim 1, wherein the collected data is analyzed using a machine learning model.

[1567] (Claim 3)

[1568] 10. The system of claim 1, wherein the analysis results are converted into a visual representation such as a graph, heat map, or trend line. [Explanation of symbols]

[1569] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting the required data from the data sources; a means for analyzing the collected data; A system including a means for visually displaying the analysis results.

2. The system of claim 1 , wherein the collected data is analyzed using a machine learning model.

3. The system of claim 1 , wherein the analysis results are converted into a visual representation such as a graph, heat map, or trend line.

4. The system of claim 1 further comprising means for collecting feedback from a user and updating the visualization information.

Images