system

Abstract

We provide the system. [Solution] A means of collecting purchase data, regional data, and customer behavior data from multiple data sources, A means for cleansing and normalizing the aforementioned collected data, A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model, A means for generating and visualizing a detailed report based on the aforementioned prediction results, Means for displaying the generated report to the user, A system that includes this.

Description

Technical Field

[0004] , , , ,

[0005] , , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many stores that have introduced cashless payment are showing a cautious attitude towards the introduction of a point program. The main reason is that they cannot specifically understand the impact of the point program on the business and regard it as an economic risk. In addition, due to the lack of means to quantitatively show the effect of the point program, it has become difficult to make business decisions. Therefore, there is a demand to specifically and detailedly show the effects such as an increase in sales and an improvement in customer loyalty due to the introduction of the point program.

Means for Solving the Problems

[0005] To solve this problem, the present invention proposes the following configuration. The present invention includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources. Next, it provides means for cleansing and normalizing the collected data. Then, it includes means for predicting sales after the introduction of a points program using a generated AI model based on the preprocessed data. Furthermore, it includes means for generating and visualizing a detailed report based on the prediction results, and means for displaying this report to the user. In this way, store managers can grasp the effects of introducing a points program in a concrete and detailed manner and make data-driven decisions that minimize economic risk.

[0006] A "data source" is a source of information that provides data such as purchase data, regional data, and customer behavior data.

[0007] "Purchase data" refers to information about the purchase history of a specific store or customer.

[0008] "Regional data" refers to economic, demographic, and social information relating to a specific geographical area.

[0009] "Customer behavior data" refers to data that shows customers' purchasing patterns, interests, preferences, and so on.

[0010] "Data cleansing" is the process of improving data quality by removing duplicates, inconsistencies, and missing data.

[0011] "Normalization" is the process of transforming data into a unified format and scaling it to facilitate comparison and analysis.

[0012] A "generative AI model" is a model trained using artificial intelligence to perform a specific task (in this case, sales forecasting).

[0013] "Sales forecasting" is the process of estimating future sales based on past data and related information.

[0014] "Visualization" is a technology that converts data and prediction results into graphs, charts, etc. to make them intuitively understandable.

[0015] A "report" is a document or data package that summarizes prediction results and their analysis and provides them as visual information.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiment for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0019] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), etc.

[0020] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] This invention relates to a system that uses AI to generate sales forecasts for stores that have implemented a points program and to generate detailed reports. This system is configured and implemented as follows.

[0038] Data collection

[0039] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It uses APIs and database connections to retrieve data in real time or at regular intervals, and stores it in a local database. For example, purchase data is collected from POS systems, regional data from publicly available government statistics, and customer behavior data from website analytics tools.

[0040] Data preprocessing

[0041] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format as needed. For example, if there is data with different date formats, it converts it to a unified format and scales numerical data to make it suitable for analysis.

[0042] Sales forecast

[0043] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of a points program. Because the pre-trained generative AI model learns the characteristics of the data, highly accurate predictions are possible. For example, it can predict sales increases after the introduction of a points program based on past sales data and customer purchasing behavior of a convenience store chain.

[0044] Report generation

[0045] The server generates and visualizes a detailed report based on the forecast results. The report provides information in a visually easy-to-understand format using graphs and charts, including not only projected sales growth figures but also detailed improvements in profits and customer loyalty resulting from the implementation of a points program.

[0046] Display Report

[0047] The terminal displays the generated report to the user. Users can review the report through a dedicated dashboard or web application to gain a concrete understanding of the effectiveness of the points program. For example, users can manipulate the dashboard graphs to compare different candidate scenarios.

[0048] Specific example

[0049] For example, suppose a convenience store chain in a certain region is considering introducing the PayPay points program. In this case, the server will collect the following data:

[0050] 1. Purchase data: Collect POS data for the past year.

[0051] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0052] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0053] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast sales after the introduction of the points program. Based on the forecast results, it then generates a detailed report, providing information visually using graphs and charts. Finally, the terminal displays this report to the store manager, supporting their decision-making regarding implementation based on specific figures and visualized information.

[0054] In this way, the system of the present invention can demonstrate the effects of introducing a points program in a concrete and detailed manner, enabling store managers to make data-driven decisions that minimize economic risk.

[0055] The following describes the processing flow.

[0056] Step 1:

[0057] The server collects purchase data, regional data, and customer behavior data from multiple data sources via APIs and database connections. For example, it obtains purchase data from POS systems, regional data from government statistics, and customer behavior data from website analytics tools. This data is then stored in a local database.

[0058] Step 2:

[0059] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and eliminates duplicate data. For example, it deletes records containing missing values ​​and corrects inaccurate data.

[0060] Step 3:

[0061] The server normalizes the cleansed data. By standardizing the data format and scaling it, it transforms it into a form that AI models can easily process. For example, it standardizes date formats and converts numerical data to a standard scale.

[0062] Step 4:

[0063] The server inputs pre-processed data into a generative AI model. It loads the generative AI model, extracts data features, and predicts sales after the introduction of a points program. For example, it uses past purchase history and customer behavior data to make predictions.

[0064] Step 5:

[0065] The server generates detailed reports based on the prediction results. These reports visually summarize predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing changes in total sales and charts showing changes in customer retention rates.

[0066] Step 6:

[0067] The terminal displays the generated report to the user. A dedicated dashboard or web application allows users to review the report's contents. For example, users can compare predictions for different scenarios and view detailed information on the dashboard.

[0068] Step 7:

[0069] Users make decisions about implementing a points program based on the displayed reports. They review detailed data and forecasts to determine whether to implement the program while minimizing financial risks. For example, if they determine that the projected sales increase will meet their targets, they proceed with the steps toward implementing the points program.

[0070] (Example 1)

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

[0072] Traditional sales forecasting methods for point programs involved cumbersome data collection and preprocessing, and did not adequately utilize generative AI models for accurate predictions. Furthermore, the generated reports were not provided in a visually easy-to-understand format, lacking the necessary information for management decision-making. Additionally, the absence of features to compare different scenarios meant insufficient support for optimal decision-making.

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

[0074] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the preprocessed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for enabling the comparison of multiple scenarios; and means for displaying the generated report to the user. This enables highly accurate data-driven sales forecasting and the generation of visually easy-to-understand detailed reports, providing support for managers to make optimal decisions.

[0075] "Multiple data sources" refers to a collection of materials obtained from different types and locations, and may include purchase data, geographical data, customer behavior data, etc.

[0076] "Purchase data" refers to records related to the buying and selling of goods and services, and primarily data obtained from POS systems.

[0077] "Regional data" refers to statistical information and economic indicators related to a specific geographical area, and may be obtained from publicly available government data, etc.

[0078] "Customer behavior data" refers to information about consumer behavior, including purchase history and visit history obtained from website analytics tools, etc.

[0079] "Cleaning" refers to data processing techniques used to improve the quality of raw data by removing missing or outlier values.

[0080] "Normalization" refers to a standardization technique that unifies the format of data and aligns numerical data of different scales to the same dimension.

[0081] A "generative AI model" is a predictive model built using machine learning or deep learning techniques, and refers to a system that makes predictions about new data based on a pre-trained dataset.

[0082] "Sales forecasting" refers to the process of estimating future increases or decreases in sales using historical data and generative AI models.

[0083] A "detailed report" is a document containing forecast and analysis results, which may include graphs and charts presented in a visually easy-to-understand format.

[0084] "Visualization" refers to the technique of visually displaying data and information using graphs and charts, and is a technology used to make things easier to understand.

[0085] "Scenario comparison" refers to the process of comparing multiple prediction results based on different conditions and settings to find the optimal option.

[0086] "Users" refer to the individuals or organizations that use this system, typically store owners or marketing personnel.

[0087] A "terminal" refers to a device used by a user to view system reports and data, and typically includes personal computers, tablets, and smartphones.

[0088] This invention relates to a system for accurately predicting the effectiveness of point programs in stores and generating detailed reports. This invention clearly separates the roles of the server, terminal, and user, and enables efficient and accurate sales forecasting and report generation through their coordinated operation.

[0089] Data collection

[0090] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it uses APIs and database connections to retrieve purchase data from POS systems in real time or at regular intervals, regional data from publicly available government statistics, and customer behavior data from website analytics tools. This data is stored in a local database.

[0091] Data preprocessing

[0092] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and standardizes date formats and numerical units. For example, it uses the Python Pandas library to convert data with different date formats to a unified format and standardize the scale of numerical data. This results in a dataset suitable for analysis.

[0093] Sales forecast

[0094] The server inputs pre-processed data into a generative AI model. Tensorflow® or PyTorch can be used as the generative AI model. The trained model accurately predicts sales after the introduction of a points program based on past purchase history, regional data, and customer behavior data. For example, it can use sales data from the past year to predict sales growth for the next year.

[0095] Report generation

[0096] The server generates and visualizes detailed reports based on the prediction results. Using Python's Matplotlib and Seaborn libraries, the predicted data is visually displayed as bar graphs and line graphs. The reports include not only sales forecast data but also the effects of increased profits and customer loyalty after implementing a points program.

[0097] Display Report

[0098] The terminal displays the generated reports to the user. Users can review the reports through a dedicated dashboard or web application. For example, users can use the dashboard to compare different scenarios and specifically evaluate the effectiveness of implementing a points program.

[0099] Specific example

[0100] For example, suppose a retail chain is considering introducing a new points program. In this case, the server collects the following data:

[0101] 1. Purchase data: Collect POS data for the past year.

[0102] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0103] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0104] Next, the server cleanses and normalizes this data and inputs it into a generating AI model to perform sales forecasting. Then, based on the forecast results, it generates a detailed report and provides visual information using a Python visualization library. Finally, the generated report is displayed to store managers via their terminals, providing decision-making support based on specific numbers and graphs.

[0105] Example of a prompt

[0106] "Based on retail chain purchasing data, regional data, and customer behavior data from the past year, please predict sales after the introduction of a points program. Based on the prediction results, please generate a detailed report and present the data in a visualized format."

[0107] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0108] Step 1: Data Collection

[0109] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Inputs are diverse, including POS systems, government statistical data APIs, and website analytics tools. Specifically, it uses the Python requests library to retrieve data from APIs and connects to POS system databases to collect purchase data. The output is raw data stored in a local database.

[0110] Step 2: Data Cleansing

[0111] The server cleanses the collected data. The input is raw data. Specifically, it uses the Python Pandas library to impute or remove missing values. It also detects outliers and performs appropriate processing. For example, if the date format is different, it converts it to a unified format. The output is the cleansed data.

[0112] Step 3: Data Normalization

[0113] The server normalizes the cleansed data. The input is the cleansed data. Specifically, it standardizes the format of each data point and scales numerical data. For example, if purchase amounts are listed in different units, it converts them to a unified unit. The output is the normalized data.

[0114] Step 4: Data entry and forecasting

[0115] The server inputs normalized data into a generative AI model. The input is normalized data. TensorFlow or PyTorch is used for the generative AI model. Specifically, a pre-trained model is loaded, and data is input to perform sales forecasting. For example, sales for the next year are predicted from purchase data for the past year. The output is sales forecast data after the introduction of a points program.

[0116] Step 5: Report Generation

[0117] The server generates a detailed report based on the forecast results. The input is sales forecast data. Specifically, it uses Python's Matplotlib and Seaborn libraries to create graphs and charts, providing information in a visually easy-to-understand format. The report also includes forecasts for sales growth and the profit-enhancing effects of implementing a points program. The output is a detailed report.

[0118] Step 6: Display Report

[0119] The terminal displays the generated report to the user. The input is a detailed report. The user views the report through a dedicated dashboard or web application. Specifically, front-end frameworks such as React or Angular are used to display and manipulate the report. For example, the user can compare different scenarios and manipulate graphs to view detailed information. The output is the report displayed to the user.

[0120] (Application Example 1)

[0121] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0122] In modern autonomous vehicles, dynamically predicting fares and revenues, and understanding the effects of point programs in real time, presents a significant challenge. Traditional systems fail to consider external factors such as traffic conditions and local events, making accurate revenue forecasting and pricing difficult. This has hindered the efficient operation and revenue maximization of autonomous vehicle services.

[0123] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0124] In this invention, the server includes means for collecting operational data, external data, and customer data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict fares and sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; and means for displaying the generated report on a display device. This makes it possible to dynamically set fares based on demand for the operation of autonomous vehicles and to grasp the effectiveness of the points program in real time.

[0125] "Operational data" refers to information about the operation of autonomous vehicles, such as their operating history, operating hours, boarding locations, and alighting locations.

[0126] "External data" refers to information about the external environment that affects the operation of autonomous vehicles, such as local traffic conditions, events, and weather forecasts.

[0127] "Customer data" refers to information about customer behavior and attributes, such as passenger boarding history and points program usage history.

[0128] "Cleaning" is a data preprocessing technique that removes missing or outlier values ​​from data and converts it into a format suitable for analysis.

[0129] "Normalization" is a data preprocessing technique that unifies the format of data and adjusts numerical data to a consistent scale.

[0130] A "generative AI model" is a type of artificial intelligence that uses generative learning algorithms to predict future sales and pricing based on past data.

[0131] "Price prediction" refers to dynamically setting prices using a generative AI model based on collected data.

[0132] "Sales forecasting" refers to predicting sales after the introduction of a points program using collected data and generated AI models.

[0133] "Report generation" refers to creating a detailed analytical report based on predicted results and visually representing it.

[0134] A "display device" is a device used to display generated reports in real time, and includes in-car displays and driver's dashboards.

[0135] This invention provides a system for dynamically predicting fares and revenues for the operation of autonomous vehicles and for understanding the effects of implementing a points program in real time. This system mainly includes a server, means for collecting data from various data sources, means for data preprocessing, a generation AI model, means for report generation and visualization, and a display device.

[0136] Data collection

[0137] The server collects operational data, external data, and customer data from multiple data sources. APIs and database connections are used for this collection. For example, operational data is obtained from the central control system of autonomous vehicles, external data from traffic information services and weather forecast services, and customer data from the database of a points program.

[0138] Data preprocessing

[0139] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format. For example, it converts data with different date formats to a unified format and scales numerical data.

[0140] Sales forecast and price forecast

[0141] The server inputs pre-processed data into a generating AI model to predict sales and appropriate pricing after the introduction of the points program. The generating AI model has learned from past operational data and customer behavior patterns, enabling highly accurate predictions. Specifically, it analyzes operational patterns and passenger behavior to suggest how to set fares for specific dates, times, and events.

[0142] Report generation and visualization

[0143] The server generates and visualizes a detailed report based on the prediction results. This report provides information in a visually easy-to-understand format using graphs and charts, as well as predicted sales and fee figures. Furthermore, it details the profits and customer loyalty improvements resulting from the implementation of the points program.

[0144] Display Report

[0145] The display device shows the generated report to the user. The user can review the report through the in-car display or driver's dashboard, gaining a concrete understanding of the effectiveness of the points program. For example, the user can manipulate the graphs on the dashboard to compare different scenarios.

[0146] Specific example

[0147] For example, suppose an autonomous taxi service in a city predicts when demand will be high based on local events and weather forecasts, and decides to implement a points program. In this case, the server collects the following data:

[0148] 1. Operational data: Collect operational data for the past year.

[0149] 2. External data: Obtain traffic conditions and weather forecasts for the target area.

[0150] 3. Customer data: Analyze the usage history of the points program.

[0151] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast fares and revenues. It then generates a detailed report based on the forecast results, providing information visually using graphs and charts. Finally, the display device shows this report on the vehicle's display to help optimize the operational plan.

[0152] Example of a prompt

[0153] "Develop a system that uses autonomous vehicle operation data, local traffic conditions, and customer ride history to forecast sales after the introduction of a points program. Specifically, this includes data collection, preprocessing, sales forecasting using a generative AI model, and generating reports that visually display the forecast results."

[0154] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0155] Step 1:

[0156] The server collects operational data, external data, and customer data from multiple data sources. Specifically, operational data is obtained in real time from the central control system of autonomous vehicles, and external data is obtained from APIs of traffic information services and weather forecast services. Customer data is collected from a points program database. Input is raw data from each data source, and output is the collected integrated data.

[0157] Step 2:

[0158] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and scales numerical data. For example, it converts date data provided in different formats to a common format and reduces the variability of numerical data to a certain range. The input is the collected integrated data, and the output is the cleansed and normalized data.

[0159] Step 3:

[0160] The server inputs pre-processed data into a generative AI model to predict charges and revenue after the point program is implemented. Specifically, it uses pre-processed data to input into a pre-trained generative AI model to make highly accurate charges and revenue predictions. For example, it calculates what pricing is optimal for a specific date, time, or event based on past operating patterns and customer behavior data. The input is pre-processed data, and the output is the predicted charges and revenue results.

[0161] Step 4:

[0162] The server generates and visualizes detailed reports based on the forecast results. Specifically, it creates visually easy-to-understand reports using graphs and charts based on the price and sales forecast results. For example, it can represent the predicted sales changes with a line graph, making it easy to understand the effect of a points program. The input is the forecast results, and the output is a visualized report.

[0163] Step 5:

[0164] The terminal displays the generated reports to the user. Specifically, it displays visualized reports in real time through in-vehicle displays and driver dashboards. For example, drivers and fleet managers can review the reports to help optimize route planning and adjust fare settings. The input is the visualized reports, and the output is the information displayed on the display device.

[0165] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0166] The present invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. This system is configured and implemented as follows:

[0167] Data collection

[0168] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it becomes available for data analysis and model training.

[0169] Data preprocessing

[0170] The server cleanses the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[0171] Sales forecast

[0172] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[0173] Report generation

[0174] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0175] emotion recognition

[0176] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0177] Display Report

[0178] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0179] Specific example

[0180] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0181] 1. Purchase data: Collect POS data for the past year.

[0182] 2. Regional data: Obtain consumer demographic information for the target area.

[0183] 3. Customer behavior data: Collect data on website and app usage.

[0184] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0185] In this way, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further, by taking into account the user's emotions, provides more user-friendly and effective decision-making support.

[0186] The following describes the processing flow.

[0187] Step 1:

[0188] The server collects purchase data, regional data, and customer behavior data from multiple data sources. For example, it obtains historical purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is then stored in a local database.

[0189] Step 2:

[0190] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and organizes duplicate data. For example, if the collected date data is in different formats, it converts it to a unified format. It also deletes or imputes records that contain missing values.

[0191] Step 3:

[0192] The server normalizes the cleansed data. It standardizes the data format and performs scaling. For example, it converts numerical data to a standard scale so that AI models can learn effectively. This makes data analysis easier.

[0193] Step 4:

[0194] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. Specifically, the predictive model estimates the increase in sales after the introduction of the points program based on historical purchase data and customer behavior. For example, the AI ​​model learns trends and customer behavior patterns from past data and estimates sales based on that.

[0195] Step 5:

[0196] The server generates a detailed report based on the forecast results. It visually summarizes predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0197] Step 6:

[0198] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, click behavior, etc., to determine their emotions. For example, it analyzes facial expressions from camera images and reads emotions from voice input.

[0199] Step 7:

[0200] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. For example, if the user reacts negatively to the report, additional explanations and success stories will be displayed. Conversely, if the user reacts positively, positive predictions and benefits will be emphasized.

[0201] Step 8:

[0202] Users make decisions about implementing a points program based on the displayed reports. They refer to detailed data and forecasts, as well as supplementary information provided by the sentiment engine. For example, if they determine that the predicted sales increase is achievable, they proceed with the steps toward implementing the points program. In this way, users can make data-driven decisions that minimize financial risk.

[0203] Through the processing steps described above, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further provides more user-friendly and effective decision-making support by taking into account the user's emotions.

[0204] (Example 2)

[0205] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0206] Traditional sales forecasting systems lack dynamic reporting that takes user sentiment into account, which hinders their ability to effectively support user decision-making. Furthermore, insufficient cleansing and normalization of collected data can lead to decreased accuracy in forecasting models.

[0207] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0208] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using a generative AI model with the preprocessed data to predict sales after the introduction of a points program; means for generating and visualizing a detailed report based on the prediction results; means for recognizing the user's emotions in real time and dynamically changing the content of the report display based on emotion recognition; and means for displaying the generated report to the user. This enables the provision of highly accurate prediction results while also allowing for dynamic report display that responds to the user's emotions.

[0209] "Multiple data sources" refers to a collection of data sources that provide different types of information, such as purchase data, location data, and customer behavior data.

[0210] "Purchase data" refers to data that contains detailed information about when consumers purchase goods or services, specifically including the date of purchase, the items purchased, the quantity purchased, and the purchase price.

[0211] "Regional data" refers to statistical information about a specific region, including demographic information such as population, age groups, and income levels.

[0212] "Customer behavior data" refers to data about how consumers use websites and applications, including information such as page views, time spent on a site, and click-through rates.

[0213] "Data cleansing" is a process that improves data quality through steps such as removing missing values, eliminating outliers, and removing duplicate data.

[0214] "Normalization" is the process of maintaining data consistency by unifying data into a standard format and scale.

[0215] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn from past data and then makes predictions and classifications based on new data.

[0216] A "points program" is a program in which consumers can earn points by performing specific actions (e.g., making purchases), with the aim of improving consumer loyalty.

[0217] "Sales forecasting" is the process of estimating future sales based on past data and current trends.

[0218] "Emotion recognition" is a technology that uses devices such as cameras and microphones to analyze a user's facial expressions and tone of voice to infer their emotions.

[0219] "Dynamic changes" refer to the automatic, real-time modification of displayed content and format in response to user emotions and new information.

[0220] This invention relates to a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The system collects data from multiple data sources, cleanses and normalizes it, and then forecasts sales using a generative AI model. Furthermore, it recognizes user emotions in real time and dynamically displays reports.

[0221] Data collection

[0222] The server collects purchase data, regional data, and customer behavior data via APIs and database connections. Specifically, it obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is stored in a local database and used for subsequent data analysis and model training.

[0223] Data preprocessing

[0224] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. It also improves data quality by standardizing date formats and numerical data.

[0225] Sales forecast

[0226] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. This model uses machine learning algorithms to learn from past data and outputs prediction results. For example, it predicts increased sales and customer retention rates, and provides specific figures to store managers.

[0227] Report generation

[0228] The server generates and visualizes detailed reports based on the forecast results. Graphs and charts are used to visually demonstrate projected increases in sales and customer loyalty. For example, it can create graphs showing sales forecast trends and charts illustrating changes in customer behavior.

[0229] emotion recognition

[0230] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers user emotions based on facial expression analysis, speech recognition, and user actions. For example, it analyzes facial expressions using a camera and detects emotions from voice input.

[0231] Display Report

[0232] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0233] Specific example

[0234] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0235] 1. Purchase data: Collect POS data for the past year.

[0236] 2. Regional data: Obtain consumer demographic information for the target area.

[0237] 3. Customer behavior data: Collect data on website and app usage.

[0238] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0239] Examples of prompts to input into a generative AI model

[0240] "Using POS data from the past year, local consumer demographics, and website usage data, predict sales after the introduction of the points program."

[0241] This prompt allows the AI ​​model to make highly accurate sales forecasts based on the necessary data.

[0242] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0243] Step 1:

[0244] Data collection

[0245] The server first collects the necessary data from multiple data sources. Specifically, it sends API requests to retrieve purchase data from the POS system for the past year. Next, it collects local data (e.g., population, age groups, income) from publicly available government databases. Furthermore, it accesses web analytics tools (e.g., Google Analytics) to obtain customer behavior data (e.g., page views, time spent on site, click-through rate). All of this data is stored in a local database.

[0246] Inputs: Data collection APIs, POS systems, publicly available government databases, web analytics tools

[0247] Output: Purchase data, regional data, and customer behavior data stored in the local database.

[0248] Step 2:

[0249] Data preprocessing

[0250] The server cleanses and normalizes the collected data. It searches for and removes records containing missing values. It detects and removes outliers (e.g., values ​​outside the data range or obviously incorrect values). It also searches for and removes duplicate data. Furthermore, it unifies date formats if they differ and standardizes the scale of numerical data.

[0251] Input: Raw data from a local database

[0252] Output: Cleansed and normalized dataset

[0253] Step 3:

[0254] Sales forecast

[0255] The server provides pre-processed data as input to the generating AI model. The model uses an algorithm learned from past purchase data, regional data, and customer behavior data to predict sales after the introduction of the points program. Specific outputs of the prediction include future sales figures, customer return rates, and sales growth rates.

[0256] Input: Cleansed and normalized dataset

[0257] Output: Future sales forecast results (sales amount, customer return rate, sales growth rate)

[0258] Step 4:

[0259] Report generation

[0260] The server generates a detailed report based on the forecast results. The report includes graphs showing sales forecast trends and charts illustrating changes in customer behavior. These visual data are included to make the forecast results easier to understand. Text-based explanations and supplementary information are also included.

[0261] Input: Future sales forecast results

[0262] Output: A detailed report visualizing the prediction results (graphs, charts, and explanatory text).

[0263] Step 5:

[0264] emotion recognition

[0265] The server uses an emotion engine to recognize the user's emotions in real time. To do this, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected data is sent to the server, where the emotion engine analyzes it to infer the user's emotions (e.g., positive, negative, neutral).

[0266] Input: User facial expression data, voice data

[0267] Output: User sentiment information (positive, negative, neutral)

[0268] Step 6:

[0269] Display Report

[0270] The device displays the generated report to the user. The content and format of the display are dynamically changed based on the emotion recognition results. If the user expresses positive emotions, success stories and positive predictions are highlighted. Conversely, if the user is feeling anxious, supplementary information and specific success stories are displayed to alleviate their anxiety.

[0271] Input: Emotion engine results, visualized detailed report

[0272] Output: Dynamically modified report display based on user sentiment.

[0273] (Application Example 2)

[0274] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0275] Traditional sales forecasting systems simply displayed forecast results without considering user emotions. Therefore, it was difficult to dynamically provide supplementary information or explanations to alleviate user anxiety or doubts about the forecast results. Furthermore, they failed to appropriately highlight information that would attract user attention, resulting in ineffective decision support.

[0276] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for displaying the generated report to the user and recognizing the user's emotions in real time; and means for dynamically changing the display content and format based on the user's emotions. This enables dynamic report display that takes the user's emotions into consideration, alleviates the user's anxiety and doubts about the prediction results, and provides more effective decision-making support.

[0277] A "data source" refers to the system or device that serves as the starting point for collecting information.

[0278] "Data cleansing" refers to the process of improving data quality by removing missing or outlier values ​​and eliminating duplicates.

[0279] "Normalization" refers to the process of transforming data into a format suitable for analysis by standardizing its format and units.

[0280] A "generative AI model" refers to an artificial intelligence model trained to make predictions and classifications based on large amounts of data.

[0281] "Sales forecasting" refers to the process of estimating future sales based on past data.

[0282] A "report" refers to a document that visually presents the results and details of a transaction or activity.

[0283] "Visualization" refers to the process of displaying data in forms such as graphs and charts to make it easier to understand.

[0284] "Emotion recognition" refers to the technology of reading emotions from the user's expressions and voice tones.

[0285] "Real-time" means that data and information are processed and reflected immediately.

[0286] "Dynamic change" means that the display and content change automatically according to the situation and conditions.

[0287] This invention is a sales prediction system that includes the function of recognizing the user's emotions and dynamically displaying reports based on them. The following describes the detailed configuration and implementation method of this system.

[0288] Data collection

[0289] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from the POS system through API or database connection, obtains regional data from the government's public database, and collects customer behavior data from web analysis tools. By storing these data in the local database, they can be used for data analysis and model training.

[0290] Data preprocessing

[0291] The server cleans and normalizes the collected data. It removes missing values and outliers and eliminates duplicate data. For example, if the date formats are different, they are converted to a unified format, and numerical data is changed to a standard scale. By performing data cleaning, the quality of the data is improved.

[0292] Sales prediction

[0293] The server inputs the preprocessed data into the generated AI model to predict the sales after the introduction of the point program. The model is trained based on past purchase data and customer behavior data and can make highly accurate predictions. For example, it predicts the increasing sales amount and customer return rate and provides specific numerical values to the store operators.

[0294] Report generation

[0295] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0296] emotion recognition

[0297] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0298] Display Report

[0299] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0300] Hardware and software to be used

[0301] Camera (built-in or external): Used to recognize the user's facial expressions.

[0302] Smartphone (iOS or Android®): A device used by a user to run applications.

[0303] OpenCV: A library for facial recognition.

[0304] Keras: Provides a deep learning model for emotion recognition.

[0305] Requests: A library for communicating with the sales prediction API.

[0306] Specific example

[0307] For example, when the store manager of a certain convenience store chain uses an app to check the effect of introducing a new point program, if the store manager's expression is "Happy" through the camera, the app will highlight a success case along with the prediction result. Conversely, if the store manager is recognized as "Sad" or "Fear", past success cases or specific advice that can serve as reassuring materials will be additionally displayed.

[0308] Example of a prompt sentence

[0309] "The store manager is checking the sales prediction report of the new point program. Recognize his expression and highlight a success case if it is a positive reaction, or provide additional reassuring materials if it is a negative reaction."

[0310] The flow of the specific process in Application Example 2 will be described using FIG. 14.

[0311] Step 1:

[0312] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It obtains purchase data from the POS system, regional data from the government's public database, and customer behavior data from web analytics tools, and stores each data in the local database. API and database connection information are used as input, and the output is the collection result of various data.

[0313] Step 2:

[0314] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and converts numerical data to a standard scale. It uses raw data from a local database as input, and the output is normalized data. Data cleansing improves data quality and consistency.

[0315] Step 3:

[0316] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of the points program. The generative AI model, trained on historical purchase and customer behavior data, is used for sales forecasting. The model's input is normalized data, and its output is the sales forecast. The forecast includes estimated sales increases and customer retention rates.

[0317] Step 4:

[0318] The server generates a detailed report based on the forecast results. It creates graphs showing sales forecast trends and charts illustrating changes in customer behavior, and incorporates these into the report. The input is the sales forecast results, and the output is a visualized, detailed report. Various data visualization tools are used to generate the report.

[0319] Step 5:

[0320] The server uses a camera and an emotion engine to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize emotions. The input is the user's facial expression data and voice data, and the output is the recognized emotion information.

[0321] Step 6:

[0322] The terminal displays the generated report to the user, dynamically changing the content and format based on the user's emotions. Based on the emotion recognition results, it highlights information that the user is likely to be interested in and adds supplementary information and explanations. The input is the detailed report and emotion information, and the output is the dynamically changed display content.

[0323] For example, when a user launches the app, the camera activates and recognizes the user's facial expression. If the prediction is positive and the user is identified as "Happy," the device highlights the success story. Conversely, if the user's facial expression is identified as "Sad" or "Fear" in relation to the prediction, the device displays additional reassuring past success stories and specific advice.

[0324] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0325] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0326] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0327] [Second Embodiment]

[0328] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0329] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0330] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0331] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0332] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0333] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0334] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0335] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0336] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0337] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0338] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0339] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0340] This invention relates to a system that uses AI to generate sales forecasts for stores that have implemented a points program and to generate detailed reports. This system is configured and implemented as follows.

[0341] Data collection

[0342] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It uses APIs and database connections to retrieve data in real time or at regular intervals, and stores it in a local database. For example, purchase data is collected from POS systems, regional data from publicly available government statistics, and customer behavior data from website analytics tools.

[0343] Data preprocessing

[0344] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format as needed. For example, if there is data with different date formats, it converts it to a unified format and scales numerical data to make it suitable for analysis.

[0345] Sales forecast

[0346] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of a points program. Because the pre-trained generative AI model learns the characteristics of the data, highly accurate predictions are possible. For example, it can predict sales increases after the introduction of a points program based on past sales data and customer purchasing behavior of a convenience store chain.

[0347] Report generation

[0348] The server generates and visualizes a detailed report based on the forecast results. The report provides information in a visually easy-to-understand format using graphs and charts, including not only projected sales growth figures but also detailed improvements in profits and customer loyalty resulting from the implementation of a points program.

[0349] Display Report

[0350] The terminal displays the generated report to the user. Users can review the report through a dedicated dashboard or web application to gain a concrete understanding of the effectiveness of the points program. For example, users can manipulate the dashboard graphs to compare different candidate scenarios.

[0351] Specific example

[0352] For example, suppose a convenience store chain in a certain region is considering introducing the PayPay points program. In this case, the server will collect the following data:

[0353] 1. Purchase data: Collect POS data for the past year.

[0354] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0355] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0356] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast sales after the introduction of the points program. Based on the forecast results, it then generates a detailed report, providing information visually using graphs and charts. Finally, the terminal displays this report to the store manager, supporting their decision-making regarding implementation based on specific figures and visualized information.

[0357] In this way, the system of the present invention can demonstrate the effects of introducing a points program in a concrete and detailed manner, enabling store managers to make data-driven decisions that minimize economic risk.

[0358] The following describes the processing flow.

[0359] Step 1:

[0360] The server collects purchase data, regional data, and customer behavior data from multiple data sources via APIs and database connections. For example, it obtains purchase data from POS systems, regional data from government statistics, and customer behavior data from website analytics tools. This data is then stored in a local database.

[0361] Step 2:

[0362] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and eliminates duplicate data. For example, it deletes records containing missing values ​​and corrects inaccurate data.

[0363] Step 3:

[0364] The server normalizes the cleansed data. By standardizing the data format and scaling it, it transforms it into a form that AI models can easily process. For example, it standardizes date formats and converts numerical data to a standard scale.

[0365] Step 4:

[0366] The server inputs pre-processed data into a generative AI model. It loads the generative AI model, extracts data features, and predicts sales after the introduction of a points program. For example, it uses past purchase history and customer behavior data to make predictions.

[0367] Step 5:

[0368] The server generates detailed reports based on the prediction results. These reports visually summarize predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing changes in total sales and charts showing changes in customer retention rates.

[0369] Step 6:

[0370] The terminal displays the generated report to the user. A dedicated dashboard or web application allows users to review the report's contents. For example, users can compare predictions for different scenarios and view detailed information on the dashboard.

[0371] Step 7:

[0372] Users make decisions about implementing a points program based on the displayed reports. They review detailed data and forecasts to determine whether to implement the program while minimizing financial risks. For example, if they determine that the projected sales increase will meet their targets, they proceed with the steps toward implementing the points program.

[0373] (Example 1)

[0374] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0375] Traditional sales forecasting methods for point programs involved cumbersome data collection and preprocessing, and did not adequately utilize generative AI models for accurate predictions. Furthermore, the generated reports were not provided in a visually easy-to-understand format, lacking the necessary information for management decision-making. Additionally, the absence of features to compare different scenarios meant insufficient support for optimal decision-making.

[0376] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0377] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the preprocessed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for enabling the comparison of multiple scenarios; and means for displaying the generated report to the user. This enables highly accurate data-driven sales forecasting and the generation of visually easy-to-understand detailed reports, providing support for managers to make optimal decisions.

[0378] "Multiple data sources" refers to a collection of materials obtained from different types and locations, and may include purchase data, geographical data, customer behavior data, etc.

[0379] "Purchase data" refers to records related to the buying and selling of goods and services, and primarily data obtained from POS systems.

[0380] "Regional data" refers to statistical information and economic indicators related to a specific geographical area, and may be obtained from publicly available government data, etc.

[0381] "Customer behavior data" refers to information about consumer behavior, including purchase history and visit history obtained from website analytics tools, etc.

[0382] "Cleaning" refers to data processing techniques used to improve the quality of raw data by removing missing or outlier values.

[0383] "Normalization" refers to a standardization technique that unifies the format of data and aligns numerical data of different scales to the same dimension.

[0384] A "generative AI model" is a predictive model built using machine learning or deep learning techniques, and refers to a system that makes predictions about new data based on a pre-trained dataset.

[0385] "Sales forecasting" refers to the process of estimating future increases or decreases in sales using historical data and generative AI models.

[0386] A "detailed report" is a document containing forecast and analysis results, which may include graphs and charts presented in a visually easy-to-understand format.

[0387] "Visualization" refers to the technique of visually displaying data and information using graphs and charts, and is a technology used to make things easier to understand.

[0388] "Scenario comparison" refers to the process of comparing multiple prediction results based on different conditions and settings to find the optimal option.

[0389] "Users" refer to the individuals or organizations that use this system, typically store owners or marketing personnel.

[0390] A "terminal" refers to a device used by a user to view system reports and data, and typically includes personal computers, tablets, and smartphones.

[0391] This invention relates to a system for accurately predicting the effectiveness of point programs in stores and generating detailed reports. This invention clearly separates the roles of the server, terminal, and user, and enables efficient and accurate sales forecasting and report generation through their coordinated operation.

[0392] Data collection

[0393] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it uses APIs and database connections to retrieve purchase data from POS systems in real time or at regular intervals, regional data from publicly available government statistics, and customer behavior data from website analytics tools. This data is stored in a local database.

[0394] Data preprocessing

[0395] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and standardizes date formats and numerical units. For example, it uses the Python Pandas library to convert data with different date formats to a unified format and standardize the scale of numerical data. This results in a dataset suitable for analysis.

[0396] Sales forecast

[0397] The server inputs pre-processed data into a generative AI model. TensorFlow or PyTorch can be used as the generative AI model. The trained model accurately predicts sales after the introduction of a points program based on past purchase history, regional data, and customer behavior data. For example, it can use sales data from the past year to predict sales growth for the next year.

[0398] Report generation

[0399] The server generates and visualizes detailed reports based on the prediction results. Using Python's Matplotlib and Seaborn libraries, the predicted data is visually displayed as bar graphs and line graphs. The reports include not only sales forecast data but also the effects of increased profits and customer loyalty after implementing a points program.

[0400] Display Report

[0401] The terminal displays the generated reports to the user. Users can review the reports through a dedicated dashboard or web application. For example, users can use the dashboard to compare different scenarios and specifically evaluate the effectiveness of implementing a points program.

[0402] Specific example

[0403] For example, suppose a retail chain is considering introducing a new points program. In this case, the server collects the following data:

[0404] 1. Purchase data: Collect POS data for the past year.

[0405] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0406] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0407] Next, the server cleanses and normalizes this data and inputs it into a generating AI model to perform sales forecasting. Then, based on the forecast results, it generates a detailed report and provides visual information using a Python visualization library. Finally, the generated report is displayed to store managers via their terminals, providing decision-making support based on specific numbers and graphs.

[0408] Example of a prompt

[0409] "Based on retail chain purchasing data, regional data, and customer behavior data from the past year, please predict sales after the introduction of a points program. Based on the prediction results, please generate a detailed report and present the data in a visualized format."

[0410] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0411] Step 1: Data Collection

[0412] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Inputs are diverse, including POS systems, government statistical data APIs, and website analytics tools. Specifically, it uses the Python requests library to retrieve data from APIs and connects to POS system databases to collect purchase data. The output is raw data stored in a local database.

[0413] Step 2: Data Cleansing

[0414] The server cleanses the collected data. The input is raw data. Specifically, it uses the Python Pandas library to impute or remove missing values. It also detects outliers and performs appropriate processing. For example, if the date format is different, it converts it to a unified format. The output is the cleansed data.

[0415] Step 3: Data Normalization

[0416] The server normalizes the cleansed data. The input is the cleansed data. Specifically, it standardizes the format of each data point and scales numerical data. For example, if purchase amounts are listed in different units, it converts them to a unified unit. The output is the normalized data.

[0417] Step 4: Data entry and forecasting

[0418] The server inputs normalized data into a generative AI model. The input is normalized data. TensorFlow or PyTorch is used for the generative AI model. Specifically, a pre-trained model is loaded, and data is input to perform sales forecasting. For example, sales for the next year are predicted from purchase data for the past year. The output is sales forecast data after the introduction of a points program.

[0419] Step 5: Report Generation

[0420] The server generates a detailed report based on the forecast results. The input is sales forecast data. Specifically, it uses Python's Matplotlib and Seaborn libraries to create graphs and charts, providing information in a visually easy-to-understand format. The report also includes forecasts for sales growth and the profit-enhancing effects of implementing a points program. The output is a detailed report.

[0421] Step 6: Display Report

[0422] The terminal displays the generated report to the user. The input is a detailed report. The user views the report through a dedicated dashboard or web application. Specifically, front-end frameworks such as React or Angular are used to display and manipulate the report. For example, the user can compare different scenarios and manipulate graphs to view detailed information. The output is the report displayed to the user.

[0423] (Application Example 1)

[0424] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0425] In modern autonomous vehicles, dynamically predicting fares and revenues, and understanding the effects of point programs in real time, presents a significant challenge. Traditional systems fail to consider external factors such as traffic conditions and local events, making accurate revenue forecasting and pricing difficult. This has hindered the efficient operation and revenue maximization of autonomous vehicle services.

[0426] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0427] In this invention, the server includes means for collecting operational data, external data, and customer data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict fares and sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; and means for displaying the generated report on a display device. This makes it possible to dynamically set fares based on demand for the operation of autonomous vehicles and to grasp the effectiveness of the points program in real time.

[0428] "Operational data" refers to information about the operation of autonomous vehicles, such as their operating history, operating hours, boarding locations, and alighting locations.

[0429] "External data" refers to information about the external environment that affects the operation of autonomous vehicles, such as local traffic conditions, events, and weather forecasts.

[0430] "Customer data" refers to information about customer behavior and attributes, such as passenger boarding history and points program usage history.

[0431] "Cleaning" is a data preprocessing technique that removes missing or outlier values ​​from data and converts it into a format suitable for analysis.

[0432] "Normalization" is a data preprocessing technique that unifies the format of data and adjusts numerical data to a consistent scale.

[0433] A "generative AI model" is a type of artificial intelligence that uses generative learning algorithms to predict future sales and pricing based on past data.

[0434] "Price prediction" refers to dynamically setting prices using a generative AI model based on collected data.

[0435] "Sales forecasting" refers to predicting sales after the introduction of a points program using collected data and generated AI models.

[0436] "Report generation" refers to creating a detailed analytical report based on predicted results and visually representing it.

[0437] A "display device" is a device used to display generated reports in real time, and includes in-car displays and driver's dashboards.

[0438] This invention provides a system for dynamically predicting fares and revenues for the operation of autonomous vehicles and for understanding the effects of implementing a points program in real time. This system mainly includes a server, means for collecting data from various data sources, means for data preprocessing, a generation AI model, means for report generation and visualization, and a display device.

[0439] Data collection

[0440] The server collects operational data, external data, and customer data from multiple data sources. APIs and database connections are used for this collection. For example, operational data is obtained from the central control system of autonomous vehicles, external data from traffic information services and weather forecast services, and customer data from the database of a points program.

[0441] Data preprocessing

[0442] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format. For example, it converts data with different date formats to a unified format and scales numerical data.

[0443] Sales forecast and price forecast

[0444] The server inputs pre-processed data into a generating AI model to predict sales and appropriate pricing after the introduction of the points program. The generating AI model has learned from past operational data and customer behavior patterns, enabling highly accurate predictions. Specifically, it analyzes operational patterns and passenger behavior to suggest how to set fares for specific dates, times, and events.

[0445] Report generation and visualization

[0446] The server generates and visualizes a detailed report based on the prediction results. This report provides information in a visually easy-to-understand format using graphs and charts, as well as predicted sales and fee figures. Furthermore, it details the profits and customer loyalty improvements resulting from the implementation of the points program.

[0447] Display Report

[0448] The display device shows the generated report to the user. The user can review the report through the in-car display or driver's dashboard, gaining a concrete understanding of the effectiveness of the points program. For example, the user can manipulate the graphs on the dashboard to compare different scenarios.

[0449] Specific example

[0450] For example, suppose an autonomous taxi service in a city predicts when demand will be high based on local events and weather forecasts, and decides to implement a points program. In this case, the server collects the following data:

[0451] 1. Operational data: Collect operational data for the past year.

[0452] 2. External data: Obtain traffic conditions and weather forecasts for the target area.

[0453] 3. Customer data: Analyze the usage history of the points program.

[0454] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast fares and revenues. It then generates a detailed report based on the forecast results, providing information visually using graphs and charts. Finally, the display device shows this report on the vehicle's display to help optimize the operational plan.

[0455] Example of a prompt

[0456] "Develop a system that uses autonomous vehicle operation data, local traffic conditions, and customer ride history to forecast sales after the introduction of a points program. Specifically, this includes data collection, preprocessing, sales forecasting using a generative AI model, and generating reports that visually display the forecast results."

[0457] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0458] Step 1:

[0459] The server collects operational data, external data, and customer data from multiple data sources. Specifically, operational data is obtained in real time from the central control system of autonomous vehicles, and external data is obtained from APIs of traffic information services and weather forecast services. Customer data is collected from a points program database. Input is raw data from each data source, and output is the collected integrated data.

[0460] Step 2:

[0461] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and scales numerical data. For example, it converts date data provided in different formats to a common format and reduces the variability of numerical data to a certain range. The input is the collected integrated data, and the output is the cleansed and normalized data.

[0462] Step 3:

[0463] The server inputs pre-processed data into a generative AI model to predict charges and revenue after the point program is implemented. Specifically, it uses pre-processed data to input into a pre-trained generative AI model to make highly accurate charges and revenue predictions. For example, it calculates what pricing is optimal for a specific date, time, or event based on past operating patterns and customer behavior data. The input is pre-processed data, and the output is the predicted charges and revenue results.

[0464] Step 4:

[0465] The server generates and visualizes detailed reports based on the forecast results. Specifically, it creates visually easy-to-understand reports using graphs and charts based on the price and sales forecast results. For example, it can represent the predicted sales changes with a line graph, making it easy to understand the effect of a points program. The input is the forecast results, and the output is a visualized report.

[0466] Step 5:

[0467] The terminal displays the generated reports to the user. Specifically, it displays visualized reports in real time through in-vehicle displays and driver dashboards. For example, drivers and fleet managers can review the reports to help optimize route planning and adjust fare settings. The input is the visualized reports, and the output is the information displayed on the display device.

[0468] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0469] The present invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. This system is configured and implemented as follows:

[0470] Data collection

[0471] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it becomes available for data analysis and model training.

[0472] Data preprocessing

[0473] The server cleanses the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[0474] Sales forecast

[0475] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[0476] Report generation

[0477] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0478] emotion recognition

[0479] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0480] Display Report

[0481] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0482] Specific example

[0483] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0484] 1. Purchase data: Collect POS data for the past year.

[0485] 2. Regional data: Obtain consumer demographic information for the target area.

[0486] 3. Customer behavior data: Collect data on website and app usage.

[0487] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0488] In this way, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further, by taking into account the user's emotions, provides more user-friendly and effective decision-making support.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The server collects purchase data, regional data, and customer behavior data from multiple data sources. For example, it obtains historical purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is then stored in a local database.

[0492] Step 2:

[0493] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and organizes duplicate data. For example, if the collected date data is in different formats, it converts it to a unified format. It also deletes or imputes records that contain missing values.

[0494] Step 3:

[0495] The server normalizes the cleansed data. It standardizes the data format and performs scaling. For example, it converts numerical data to a standard scale so that AI models can learn effectively. This makes data analysis easier.

[0496] Step 4:

[0497] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. Specifically, the predictive model estimates the increase in sales after the introduction of the points program based on historical purchase data and customer behavior. For example, the AI ​​model learns trends and customer behavior patterns from past data and estimates sales based on that.

[0498] Step 5:

[0499] The server generates a detailed report based on the forecast results. It visually summarizes predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0500] Step 6:

[0501] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, click behavior, etc., to determine their emotions. For example, it analyzes facial expressions from camera images and reads emotions from voice input.

[0502] Step 7:

[0503] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. For example, if the user reacts negatively to the report, additional explanations and success stories will be displayed. Conversely, if the user reacts positively, positive predictions and benefits will be emphasized.

[0504] Step 8:

[0505] Users make decisions about implementing a points program based on the displayed reports. They refer to detailed data and forecasts, as well as supplementary information provided by the sentiment engine. For example, if they determine that the predicted sales increase is achievable, they proceed with the steps toward implementing the points program. In this way, users can make data-driven decisions that minimize financial risk.

[0506] Through the processing steps described above, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further provides more user-friendly and effective decision-making support by taking into account the user's emotions.

[0507] (Example 2)

[0508] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0509] Traditional sales forecasting systems lack dynamic reporting that takes user sentiment into account, which hinders their ability to effectively support user decision-making. Furthermore, insufficient cleansing and normalization of collected data can lead to decreased accuracy in forecasting models.

[0510] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0511] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using a generative AI model with the preprocessed data to predict sales after the introduction of a points program; means for generating and visualizing a detailed report based on the prediction results; means for recognizing the user's emotions in real time and dynamically changing the content of the report display based on emotion recognition; and means for displaying the generated report to the user. This enables the provision of highly accurate prediction results while also allowing for dynamic report display that responds to the user's emotions.

[0512] "Multiple data sources" refers to a collection of data sources that provide different types of information, such as purchase data, location data, and customer behavior data.

[0513] "Purchase data" refers to data that contains detailed information about when consumers purchase goods or services, specifically including the date of purchase, the items purchased, the quantity purchased, and the purchase price.

[0514] "Regional data" refers to statistical information about a specific region, including demographic information such as population, age groups, and income levels.

[0515] "Customer behavior data" refers to data about how consumers use websites and applications, including information such as page views, time spent on a site, and click-through rates.

[0516] "Data cleansing" is a process that improves data quality through steps such as removing missing values, eliminating outliers, and removing duplicate data.

[0517] "Normalization" is the process of maintaining data consistency by unifying data into a standard format and scale.

[0518] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn from past data and then makes predictions and classifications based on new data.

[0519] A "points program" is a program in which consumers can earn points by performing specific actions (e.g., making purchases), with the aim of improving consumer loyalty.

[0520] "Sales forecasting" is the process of estimating future sales based on past data and current trends.

[0521] "Emotion recognition" is a technology that uses devices such as cameras and microphones to analyze a user's facial expressions and tone of voice to infer their emotions.

[0522] "Dynamic changes" refer to the automatic, real-time modification of displayed content and format in response to user emotions and new information.

[0523] This invention relates to a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The system collects data from multiple data sources, cleanses and normalizes it, and then forecasts sales using a generative AI model. Furthermore, it recognizes user emotions in real time and dynamically displays reports.

[0524] Data collection

[0525] The server collects purchase data, regional data, and customer behavior data via APIs and database connections. Specifically, it obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is stored in a local database and used for subsequent data analysis and model training.

[0526] Data preprocessing

[0527] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. It also improves data quality by standardizing date formats and numerical data.

[0528] Sales forecast

[0529] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. This model uses machine learning algorithms to learn from past data and outputs prediction results. For example, it predicts increased sales and customer retention rates, and provides specific figures to store managers.

[0530] Report generation

[0531] The server generates and visualizes detailed reports based on the forecast results. Graphs and charts are used to visually demonstrate projected increases in sales and customer loyalty. For example, it can create graphs showing sales forecast trends and charts illustrating changes in customer behavior.

[0532] emotion recognition

[0533] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers user emotions based on facial expression analysis, speech recognition, and user actions. For example, it analyzes facial expressions using a camera and detects emotions from voice input.

[0534] Display Report

[0535] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0536] Specific example

[0537] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0538] 1. Purchase data: Collect POS data for the past year.

[0539] 2. Regional data: Obtain consumer demographic information for the target area.

[0540] 3. Customer behavior data: Collect data on website and app usage.

[0541] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0542] Examples of prompts to input into a generative AI model

[0543] "Using POS data from the past year, local consumer demographics, and website usage data, predict sales after the introduction of the points program."

[0544] This prompt allows the AI ​​model to make highly accurate sales forecasts based on the necessary data.

[0545] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0546] Step 1:

[0547] Data collection

[0548] The server first collects the necessary data from multiple data sources. Specifically, it sends API requests to retrieve purchase data from the POS system for the past year. Next, it collects local data (e.g., population, age groups, income) from publicly available government databases. Furthermore, it accesses web analytics tools (e.g., Google Analytics) to obtain customer behavior data (e.g., page views, time spent on site, click-through rate). All of this data is stored in a local database.

[0549] Inputs: Data collection APIs, POS systems, publicly available government databases, web analytics tools

[0550] Output: Purchase data, regional data, and customer behavior data stored in the local database.

[0551] Step 2:

[0552] Data preprocessing

[0553] The server cleanses and normalizes the collected data. It searches for and removes records containing missing values. It detects and removes outliers (e.g., values ​​outside the data range or obviously incorrect values). It also searches for and removes duplicate data. Furthermore, it unifies date formats if they differ and standardizes the scale of numerical data.

[0554] Input: Raw data from a local database

[0555] Output: Cleansed and normalized dataset

[0556] Step 3:

[0557] Sales forecast

[0558] The server provides pre-processed data as input to the generating AI model. The model uses an algorithm learned from past purchase data, regional data, and customer behavior data to predict sales after the introduction of the points program. Specific outputs of the prediction include future sales figures, customer return rates, and sales growth rates.

[0559] Input: Cleansed and normalized dataset

[0560] Output: Future sales forecast results (sales amount, customer return rate, sales growth rate)

[0561] Step 4:

[0562] Report generation

[0563] The server generates a detailed report based on the forecast results. The report includes graphs showing sales forecast trends and charts illustrating changes in customer behavior. These visual data are included to make the forecast results easier to understand. Text-based explanations and supplementary information are also included.

[0564] Input: Future sales forecast results

[0565] Output: A detailed report visualizing the prediction results (graphs, charts, and explanatory text).

[0566] Step 5:

[0567] emotion recognition

[0568] The server uses an emotion engine to recognize the user's emotions in real time. To do this, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected data is sent to the server, where the emotion engine analyzes it to infer the user's emotions (e.g., positive, negative, neutral).

[0569] Input: User facial expression data, voice data

[0570] Output: User sentiment information (positive, negative, neutral)

[0571] Step 6:

[0572] Display Report

[0573] The device displays the generated report to the user. The content and format of the display are dynamically changed based on the emotion recognition results. If the user expresses positive emotions, success stories and positive predictions are highlighted. Conversely, if the user is feeling anxious, supplementary information and specific success stories are displayed to alleviate their anxiety.

[0574] Input: Emotion engine results, visualized detailed report

[0575] Output: Dynamically modified report display based on user sentiment.

[0576] (Application Example 2)

[0577] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0578] Traditional sales forecasting systems simply displayed forecast results without considering user emotions. Therefore, it was difficult to dynamically provide supplementary information or explanations to alleviate user anxiety or doubts about the forecast results. Furthermore, they failed to appropriately highlight information that would attract user attention, resulting in ineffective decision support.

[0579] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for displaying the generated report to the user and recognizing the user's emotions in real time; and means for dynamically changing the display content and format based on the user's emotions. This enables dynamic report display that takes the user's emotions into consideration, alleviates the user's anxiety and doubts about the prediction results, and provides more effective decision-making support.

[0580] A "data source" refers to the system or device that serves as the starting point for collecting information.

[0581] "Data cleansing" refers to the process of improving data quality by removing missing or outlier values ​​and eliminating duplicates.

[0582] "Normalization" refers to the process of transforming data into a format suitable for analysis by standardizing its format and units.

[0583] A "generative AI model" refers to an artificial intelligence model trained to make predictions and classifications based on large amounts of data.

[0584] "Sales forecasting" refers to the process of estimating future sales based on past data.

[0585] A "report" refers to a document that visually presents the results and details of a transaction or activity.

[0586] "Visualization" refers to the process of displaying data in forms such as graphs and charts to make it easier to understand.

[0587] "Emotion recognition" refers to the technology that reads emotions from a user's facial expressions and tone of voice.

[0588] "Real-time" refers to the immediate processing and reflection of data and information.

[0589] "Dynamic modification" refers to the automatic change of display or content depending on the situation or conditions.

[0590] This invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The detailed configuration and implementation method of this system are described below.

[0591] Data collection

[0592] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it can be used for data analysis and model training.

[0593] Data preprocessing

[0594] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[0595] Sales forecast

[0596] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[0597] Report generation

[0598] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0599] emotion recognition

[0600] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0601] Display Report

[0602] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0603] Hardware and software to be used

[0604] Camera (built-in or external): Used to recognize the user's facial expressions.

[0605] Smartphone (iOS or Android): A device used by a user to run applications.

[0606] OpenCV: A library for facial recognition.

[0607] Keras: Provides deep learning models for emotion recognition.

[0608] Requests: A library for communicating with the sales forecasting API.

[0609] Specific example

[0610] For example, if a store manager at a convenience store chain uses the app to check the effectiveness of a new points program, and the manager's facial expression through the camera is "Happy," the app will highlight success stories along with the predicted results. Conversely, if the manager is perceived as "Sad" or "Fear," the app will display additional reassuring past success stories and specific advice.

[0611] Example of a prompt

[0612] "The store manager is reviewing the sales forecast report for the new points program. Pay attention to his expression; if he has a positive reaction, highlight the success stories, and if he has a negative reaction, provide additional reassurance."

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools, storing each type of data in a local database. It uses APIs and database connection information as input, and outputs the results of various data collections.

[0616] Step 2:

[0617] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and converts numerical data to a standard scale. It uses raw data from a local database as input, and the output is normalized data. Data cleansing improves data quality and consistency.

[0618] Step 3:

[0619] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of the points program. The generative AI model, trained on historical purchase and customer behavior data, is used for sales forecasting. The model's input is normalized data, and its output is the sales forecast. The forecast includes estimated sales increases and customer retention rates.

[0620] Step 4:

[0621] The server generates a detailed report based on the forecast results. It creates graphs showing sales forecast trends and charts illustrating changes in customer behavior, and incorporates these into the report. The input is the sales forecast results, and the output is a visualized, detailed report. Various data visualization tools are used to generate the report.

[0622] Step 5:

[0623] The server uses a camera and an emotion engine to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize emotions. The input is the user's facial expression data and voice data, and the output is the recognized emotion information.

[0624] Step 6:

[0625] The terminal displays the generated report to the user, dynamically changing the content and format based on the user's emotions. Based on the emotion recognition results, it highlights information that the user is likely to be interested in and adds supplementary information and explanations. The input is the detailed report and emotion information, and the output is the dynamically changed display content.

[0626] For example, when a user launches the app, the camera activates and recognizes the user's facial expression. If the prediction is positive and the user is identified as "Happy," the device highlights the success story. Conversely, if the user's facial expression is identified as "Sad" or "Fear" in relation to the prediction, the device displays additional reassuring past success stories and specific advice.

[0627] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0628] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0629] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0630] [Third Embodiment]

[0631] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0632] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0633] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0634] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0635] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0636] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0637] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0638] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0639] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0640] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0641] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0642] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0643] This invention relates to a system that uses AI to generate sales forecasts for stores that have implemented a points program and to generate detailed reports. This system is configured and implemented as follows.

[0644] Data collection

[0645] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It uses APIs and database connections to retrieve data in real time or at regular intervals, and stores it in a local database. For example, purchase data is collected from POS systems, regional data from publicly available government statistics, and customer behavior data from website analytics tools.

[0646] Data preprocessing

[0647] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format as needed. For example, if there is data with different date formats, it converts it to a unified format and scales numerical data to make it suitable for analysis.

[0648] Sales forecast

[0649] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of a points program. Because the pre-trained generative AI model learns the characteristics of the data, highly accurate predictions are possible. For example, it can predict sales increases after the introduction of a points program based on past sales data and customer purchasing behavior of a convenience store chain.

[0650] Report generation

[0651] The server generates and visualizes a detailed report based on the forecast results. The report provides information in a visually easy-to-understand format using graphs and charts, including not only projected sales growth figures but also detailed improvements in profits and customer loyalty resulting from the implementation of a points program.

[0652] Display Report

[0653] The terminal displays the generated report to the user. Users can review the report through a dedicated dashboard or web application to gain a concrete understanding of the effectiveness of the points program. For example, users can manipulate the dashboard graphs to compare different candidate scenarios.

[0654] Specific example

[0655] For example, suppose a convenience store chain in a certain region is considering introducing the PayPay points program. In this case, the server will collect the following data:

[0656] 1. Purchase data: Collect POS data for the past year.

[0657] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0658] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0659] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast sales after the introduction of the points program. Based on the forecast results, it then generates a detailed report, providing information visually using graphs and charts. Finally, the terminal displays this report to the store manager, supporting their decision-making regarding implementation based on specific figures and visualized information.

[0660] In this way, the system of the present invention can demonstrate the effects of introducing a points program in a concrete and detailed manner, enabling store managers to make data-driven decisions that minimize economic risk.

[0661] The following describes the processing flow.

[0662] Step 1:

[0663] The server collects purchase data, regional data, and customer behavior data from multiple data sources via APIs and database connections. For example, it obtains purchase data from POS systems, regional data from government statistics, and customer behavior data from website analytics tools. This data is then stored in a local database.

[0664] Step 2:

[0665] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and eliminates duplicate data. For example, it deletes records containing missing values ​​and corrects inaccurate data.

[0666] Step 3:

[0667] The server normalizes the cleansed data. By standardizing the data format and scaling it, it transforms it into a form that AI models can easily process. For example, it standardizes date formats and converts numerical data to a standard scale.

[0668] Step 4:

[0669] The server inputs pre-processed data into a generative AI model. It loads the generative AI model, extracts data features, and predicts sales after the introduction of a points program. For example, it uses past purchase history and customer behavior data to make predictions.

[0670] Step 5:

[0671] The server generates detailed reports based on the prediction results. These reports visually summarize predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing changes in total sales and charts showing changes in customer retention rates.

[0672] Step 6:

[0673] The terminal displays the generated report to the user. A dedicated dashboard or web application allows users to review the report's contents. For example, users can compare predictions for different scenarios and view detailed information on the dashboard.

[0674] Step 7:

[0675] Users make decisions about implementing a points program based on the displayed reports. They review detailed data and forecasts to determine whether to implement the program while minimizing financial risks. For example, if they determine that the projected sales increase will meet their targets, they proceed with the steps toward implementing the points program.

[0676] (Example 1)

[0677] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0678] Traditional sales forecasting methods for point programs involved cumbersome data collection and preprocessing, and did not adequately utilize generative AI models for accurate predictions. Furthermore, the generated reports were not provided in a visually easy-to-understand format, lacking the necessary information for management decision-making. Additionally, the absence of features to compare different scenarios meant insufficient support for optimal decision-making.

[0679] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0680] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the preprocessed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for enabling the comparison of multiple scenarios; and means for displaying the generated report to the user. This enables highly accurate data-driven sales forecasting and the generation of visually easy-to-understand detailed reports, providing support for managers to make optimal decisions.

[0681] "Multiple data sources" refers to a collection of materials obtained from different types and locations, and may include purchase data, geographical data, customer behavior data, etc.

[0682] "Purchase data" refers to records related to the buying and selling of goods and services, and primarily data obtained from POS systems.

[0683] "Regional data" refers to statistical information and economic indicators related to a specific geographical area, and may be obtained from publicly available government data, etc.

[0684] "Customer behavior data" refers to information about consumer behavior, including purchase history and visit history obtained from website analytics tools, etc.

[0685] "Cleaning" refers to data processing techniques used to improve the quality of raw data by removing missing or outlier values.

[0686] "Normalization" refers to a standardization technique that unifies the format of data and aligns numerical data of different scales to the same dimension.

[0687] A "generative AI model" is a predictive model built using machine learning or deep learning techniques, and refers to a system that makes predictions about new data based on a pre-trained dataset.

[0688] "Sales forecasting" refers to the process of estimating future increases or decreases in sales using historical data and generative AI models.

[0689] A "detailed report" is a document containing forecast and analysis results, which may include graphs and charts presented in a visually easy-to-understand format.

[0690] "Visualization" refers to the technique of visually displaying data and information using graphs and charts, and is a technology used to make things easier to understand.

[0691] "Scenario comparison" refers to the process of comparing multiple prediction results based on different conditions and settings to find the optimal option.

[0692] "Users" refer to the individuals or organizations that use this system, typically store owners or marketing personnel.

[0693] A "terminal" refers to a device used by a user to view system reports and data, and typically includes personal computers, tablets, and smartphones.

[0694] This invention relates to a system for accurately predicting the effectiveness of point programs in stores and generating detailed reports. This invention clearly separates the roles of the server, terminal, and user, and enables efficient and accurate sales forecasting and report generation through their coordinated operation.

[0695] Data collection

[0696] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it uses APIs and database connections to retrieve purchase data from POS systems in real time or at regular intervals, regional data from publicly available government statistics, and customer behavior data from website analytics tools. This data is stored in a local database.

[0697] Data preprocessing

[0698] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and standardizes date formats and numerical units. For example, it uses the Python Pandas library to convert data with different date formats to a unified format and standardize the scale of numerical data. This results in a dataset suitable for analysis.

[0699] Sales forecast

[0700] The server inputs pre-processed data into a generative AI model. TensorFlow or PyTorch can be used as the generative AI model. The trained model accurately predicts sales after the introduction of a points program based on past purchase history, regional data, and customer behavior data. For example, it can use sales data from the past year to predict sales growth for the next year.

[0701] Report generation

[0702] The server generates and visualizes detailed reports based on the prediction results. Using Python's Matplotlib and Seaborn libraries, the predicted data is visually displayed as bar graphs and line graphs. The reports include not only sales forecast data but also the effects of increased profits and customer loyalty after implementing a points program.

[0703] Display Report

[0704] The terminal displays the generated reports to the user. Users can review the reports through a dedicated dashboard or web application. For example, users can use the dashboard to compare different scenarios and specifically evaluate the effectiveness of implementing a points program.

[0705] Specific example

[0706] For example, suppose a retail chain is considering introducing a new points program. In this case, the server collects the following data:

[0707] 1. Purchase data: Collect POS data for the past year.

[0708] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0709] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0710] Next, the server cleanses and normalizes this data and inputs it into a generating AI model to perform sales forecasting. Then, based on the forecast results, it generates a detailed report and provides visual information using a Python visualization library. Finally, the generated report is displayed to store managers via their terminals, providing decision-making support based on specific numbers and graphs.

[0711] Example of a prompt

[0712] "Based on retail chain purchasing data, regional data, and customer behavior data from the past year, please predict sales after the introduction of a points program. Based on the prediction results, please generate a detailed report and present the data in a visualized format."

[0713] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0714] Step 1: Data Collection

[0715] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Inputs are diverse, including POS systems, government statistical data APIs, and website analytics tools. Specifically, it uses the Python requests library to retrieve data from APIs and connects to POS system databases to collect purchase data. The output is raw data stored in a local database.

[0716] Step 2: Data Cleansing

[0717] The server cleanses the collected data. The input is raw data. Specifically, it uses the Python Pandas library to impute or remove missing values. It also detects outliers and performs appropriate processing. For example, if the date format is different, it converts it to a unified format. The output is the cleansed data.

[0718] Step 3: Data Normalization

[0719] The server normalizes the cleansed data. The input is the cleansed data. Specifically, it standardizes the format of each data point and scales numerical data. For example, if purchase amounts are listed in different units, it converts them to a unified unit. The output is the normalized data.

[0720] Step 4: Data entry and forecasting

[0721] The server inputs normalized data into a generative AI model. The input is normalized data. TensorFlow or PyTorch is used for the generative AI model. Specifically, a pre-trained model is loaded, and data is input to perform sales forecasting. For example, sales for the next year are predicted from purchase data for the past year. The output is sales forecast data after the introduction of a points program.

[0722] Step 5: Report Generation

[0723] The server generates a detailed report based on the forecast results. The input is sales forecast data. Specifically, it uses Python's Matplotlib and Seaborn libraries to create graphs and charts, providing information in a visually easy-to-understand format. The report also includes forecasts for sales growth and the profit-enhancing effects of implementing a points program. The output is a detailed report.

[0724] Step 6: Display Report

[0725] The terminal displays the generated report to the user. The input is a detailed report. The user views the report through a dedicated dashboard or web application. Specifically, front-end frameworks such as React or Angular are used to display and manipulate the report. For example, the user can compare different scenarios and manipulate graphs to view detailed information. The output is the report displayed to the user.

[0726] (Application Example 1)

[0727] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0728] In modern autonomous vehicles, dynamically predicting fares and revenues, and understanding the effects of point programs in real time, presents a significant challenge. Traditional systems fail to consider external factors such as traffic conditions and local events, making accurate revenue forecasting and pricing difficult. This has hindered the efficient operation and revenue maximization of autonomous vehicle services.

[0729] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0730] In this invention, the server includes means for collecting operational data, external data, and customer data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict fares and sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; and means for displaying the generated report on a display device. This makes it possible to dynamically set fares based on demand for the operation of autonomous vehicles and to grasp the effectiveness of the points program in real time.

[0731] "Operational data" refers to information about the operation of autonomous vehicles, such as their operating history, operating hours, boarding locations, and alighting locations.

[0732] "External data" refers to information about the external environment that affects the operation of autonomous vehicles, such as local traffic conditions, events, and weather forecasts.

[0733] "Customer data" refers to information about customer behavior and attributes, such as passenger boarding history and points program usage history.

[0734] "Cleaning" is a data preprocessing technique that removes missing or outlier values ​​from data and converts it into a format suitable for analysis.

[0735] "Normalization" is a data preprocessing technique that unifies the format of data and adjusts numerical data to a consistent scale.

[0736] A "generative AI model" is a type of artificial intelligence that uses generative learning algorithms to predict future sales and pricing based on past data.

[0737] "Price prediction" refers to dynamically setting prices using a generative AI model based on collected data.

[0738] "Sales forecasting" refers to predicting sales after the introduction of a points program using collected data and generated AI models.

[0739] "Report generation" refers to creating a detailed analytical report based on predicted results and visually representing it.

[0740] A "display device" is a device used to display generated reports in real time, and includes in-car displays and driver's dashboards.

[0741] This invention provides a system for dynamically predicting fares and revenues for the operation of autonomous vehicles and for understanding the effects of implementing a points program in real time. This system mainly includes a server, means for collecting data from various data sources, means for data preprocessing, a generation AI model, means for report generation and visualization, and a display device.

[0742] Data collection

[0743] The server collects operational data, external data, and customer data from multiple data sources. APIs and database connections are used for this collection. For example, operational data is obtained from the central control system of autonomous vehicles, external data from traffic information services and weather forecast services, and customer data from the database of a points program.

[0744] Data preprocessing

[0745] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format. For example, it converts data with different date formats to a unified format and scales numerical data.

[0746] Sales forecast and price forecast

[0747] The server inputs pre-processed data into a generating AI model to predict sales and appropriate pricing after the introduction of the points program. The generating AI model has learned from past operational data and customer behavior patterns, enabling highly accurate predictions. Specifically, it analyzes operational patterns and passenger behavior to suggest how to set fares for specific dates, times, and events.

[0748] Report generation and visualization

[0749] The server generates and visualizes a detailed report based on the prediction results. This report provides information in a visually easy-to-understand format using graphs and charts, as well as predicted sales and fee figures. Furthermore, it details the profits and customer loyalty improvements resulting from the implementation of the points program.

[0750] Display Report

[0751] The display device shows the generated report to the user. The user can review the report through the in-car display or driver's dashboard, gaining a concrete understanding of the effectiveness of the points program. For example, the user can manipulate the graphs on the dashboard to compare different scenarios.

[0752] Specific example

[0753] For example, suppose an autonomous taxi service in a city predicts when demand will be high based on local events and weather forecasts, and decides to implement a points program. In this case, the server collects the following data:

[0754] 1. Operational data: Collect operational data for the past year.

[0755] 2. External data: Obtain traffic conditions and weather forecasts for the target area.

[0756] 3. Customer data: Analyze the usage history of the points program.

[0757] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast fares and revenues. It then generates a detailed report based on the forecast results, providing information visually using graphs and charts. Finally, the display device shows this report on the vehicle's display to help optimize the operational plan.

[0758] Example of a prompt

[0759] "Develop a system that uses autonomous vehicle operation data, local traffic conditions, and customer ride history to forecast sales after the introduction of a points program. Specifically, this includes data collection, preprocessing, sales forecasting using a generative AI model, and generating reports that visually display the forecast results."

[0760] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0761] Step 1:

[0762] The server collects operational data, external data, and customer data from multiple data sources. Specifically, operational data is obtained in real time from the central control system of autonomous vehicles, and external data is obtained from APIs of traffic information services and weather forecast services. Customer data is collected from a points program database. Input is raw data from each data source, and output is the collected integrated data.

[0763] Step 2:

[0764] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and scales numerical data. For example, it converts date data provided in different formats to a common format and reduces the variability of numerical data to a certain range. The input is the collected integrated data, and the output is the cleansed and normalized data.

[0765] Step 3:

[0766] The server inputs pre-processed data into a generative AI model to predict charges and revenue after the point program is implemented. Specifically, it uses pre-processed data to input into a pre-trained generative AI model to make highly accurate charges and revenue predictions. For example, it calculates what pricing is optimal for a specific date, time, or event based on past operating patterns and customer behavior data. The input is pre-processed data, and the output is the predicted charges and revenue results.

[0767] Step 4:

[0768] The server generates and visualizes detailed reports based on the forecast results. Specifically, it creates visually easy-to-understand reports using graphs and charts based on the price and sales forecast results. For example, it can represent the predicted sales changes with a line graph, making it easy to understand the effect of a points program. The input is the forecast results, and the output is a visualized report.

[0769] Step 5:

[0770] The terminal displays the generated reports to the user. Specifically, it displays visualized reports in real time through in-vehicle displays and driver dashboards. For example, drivers and fleet managers can review the reports to help optimize route planning and adjust fare settings. The input is the visualized reports, and the output is the information displayed on the display device.

[0771] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0772] The present invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. This system is configured and implemented as follows:

[0773] Data collection

[0774] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it becomes available for data analysis and model training.

[0775] Data preprocessing

[0776] The server cleanses the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[0777] Sales forecast

[0778] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[0779] Report generation

[0780] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0781] emotion recognition

[0782] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0783] Display Report

[0784] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0785] Specific example

[0786] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0787] 1. Purchase data: Collect POS data for the past year.

[0788] 2. Regional data: Obtain consumer demographic information for the target area.

[0789] 3. Customer behavior data: Collect data on website and app usage.

[0790] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0791] In this way, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further, by taking into account the user's emotions, provides more user-friendly and effective decision-making support.

[0792] The following describes the processing flow.

[0793] Step 1:

[0794] The server collects purchase data, regional data, and customer behavior data from multiple data sources. For example, it obtains historical purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is then stored in a local database.

[0795] Step 2:

[0796] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and organizes duplicate data. For example, if the collected date data is in different formats, it converts it to a unified format. It also deletes or imputes records that contain missing values.

[0797] Step 3:

[0798] The server normalizes the cleansed data. It standardizes the data format and performs scaling. For example, it converts numerical data to a standard scale so that AI models can learn effectively. This makes data analysis easier.

[0799] Step 4:

[0800] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. Specifically, the predictive model estimates the increase in sales after the introduction of the points program based on historical purchase data and customer behavior. For example, the AI ​​model learns trends and customer behavior patterns from past data and estimates sales based on that.

[0801] Step 5:

[0802] The server generates a detailed report based on the forecast results. It visually summarizes predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0803] Step 6:

[0804] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, click behavior, etc., to determine their emotions. For example, it analyzes facial expressions from camera images and reads emotions from voice input.

[0805] Step 7:

[0806] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. For example, if the user reacts negatively to the report, additional explanations and success stories will be displayed. Conversely, if the user reacts positively, positive predictions and benefits will be emphasized.

[0807] Step 8:

[0808] Users make decisions about implementing a points program based on the displayed reports. They refer to detailed data and forecasts, as well as supplementary information provided by the sentiment engine. For example, if they determine that the predicted sales increase is achievable, they proceed with the steps toward implementing the points program. In this way, users can make data-driven decisions that minimize financial risk.

[0809] Through the processing steps described above, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further provides more user-friendly and effective decision-making support by taking into account the user's emotions.

[0810] (Example 2)

[0811] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0812] Traditional sales forecasting systems lack dynamic reporting that takes user sentiment into account, which hinders their ability to effectively support user decision-making. Furthermore, insufficient cleansing and normalization of collected data can lead to decreased accuracy in forecasting models.

[0813] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0814] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using a generative AI model with the preprocessed data to predict sales after the introduction of a points program; means for generating and visualizing a detailed report based on the prediction results; means for recognizing the user's emotions in real time and dynamically changing the content of the report display based on emotion recognition; and means for displaying the generated report to the user. This enables the provision of highly accurate prediction results while also allowing for dynamic report display that responds to the user's emotions.

[0815] "Multiple data sources" refers to a collection of data sources that provide different types of information, such as purchase data, location data, and customer behavior data.

[0816] "Purchase data" refers to data that contains detailed information about when consumers purchase goods or services, specifically including the date of purchase, the items purchased, the quantity purchased, and the purchase price.

[0817] "Regional data" refers to statistical information about a specific region, including demographic information such as population, age groups, and income levels.

[0818] "Customer behavior data" refers to data about how consumers use websites and applications, including information such as page views, time spent on a site, and click-through rates.

[0819] "Data cleansing" is a process that improves data quality through steps such as removing missing values, eliminating outliers, and removing duplicate data.

[0820] "Normalization" is the process of maintaining data consistency by unifying data into a standard format and scale.

[0821] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn from past data and then makes predictions and classifications based on new data.

[0822] A "points program" is a program in which consumers can earn points by performing specific actions (e.g., making purchases), with the aim of improving consumer loyalty.

[0823] "Sales forecasting" is the process of estimating future sales based on past data and current trends.

[0824] "Emotion recognition" is a technology that uses devices such as cameras and microphones to analyze a user's facial expressions and tone of voice to infer their emotions.

[0825] "Dynamic changes" refer to the automatic, real-time modification of displayed content and format in response to user emotions and new information.

[0826] This invention relates to a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The system collects data from multiple data sources, cleanses and normalizes it, and then forecasts sales using a generative AI model. Furthermore, it recognizes user emotions in real time and dynamically displays reports.

[0827] Data collection

[0828] The server collects purchase data, regional data, and customer behavior data via APIs and database connections. Specifically, it obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is stored in a local database and used for subsequent data analysis and model training.

[0829] Data preprocessing

[0830] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. It also improves data quality by standardizing date formats and numerical data.

[0831] Sales forecast

[0832] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. This model uses machine learning algorithms to learn from past data and outputs prediction results. For example, it predicts increased sales and customer retention rates, and provides specific figures to store managers.

[0833] Report generation

[0834] The server generates and visualizes detailed reports based on the forecast results. Graphs and charts are used to visually demonstrate projected increases in sales and customer loyalty. For example, it can create graphs showing sales forecast trends and charts illustrating changes in customer behavior.

[0835] emotion recognition

[0836] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers user emotions based on facial expression analysis, speech recognition, and user actions. For example, it analyzes facial expressions using a camera and detects emotions from voice input.

[0837] Display Report

[0838] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0839] Specific example

[0840] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[0841] 1. Purchase data: Collect POS data for the past year.

[0842] 2. Regional data: Obtain consumer demographic information for the target area.

[0843] 3. Customer behavior data: Collect data on website and app usage.

[0844] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[0845] Examples of prompts to input into a generative AI model

[0846] "Using POS data from the past year, local consumer demographics, and website usage data, predict sales after the introduction of the points program."

[0847] This prompt allows the AI ​​model to make highly accurate sales forecasts based on the necessary data.

[0848] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0849] Step 1:

[0850] Data collection

[0851] The server first collects the necessary data from multiple data sources. Specifically, it sends API requests to retrieve purchase data from the POS system for the past year. Next, it collects local data (e.g., population, age groups, income) from publicly available government databases. Furthermore, it accesses web analytics tools (e.g., Google Analytics) to obtain customer behavior data (e.g., page views, time spent on site, click-through rate). All of this data is stored in a local database.

[0852] Inputs: Data collection APIs, POS systems, publicly available government databases, web analytics tools

[0853] Output: Purchase data, regional data, and customer behavior data stored in the local database.

[0854] Step 2:

[0855] Data preprocessing

[0856] The server cleanses and normalizes the collected data. It searches for and removes records containing missing values. It detects and removes outliers (e.g., values ​​outside the data range or obviously incorrect values). It also searches for and removes duplicate data. Furthermore, it unifies date formats if they differ and standardizes the scale of numerical data.

[0857] Input: Raw data from a local database

[0858] Output: Cleansed and normalized dataset

[0859] Step 3:

[0860] Sales forecast

[0861] The server provides pre-processed data as input to the generating AI model. The model uses an algorithm learned from past purchase data, regional data, and customer behavior data to predict sales after the introduction of the points program. Specific outputs of the prediction include future sales figures, customer return rates, and sales growth rates.

[0862] Input: Cleansed and normalized dataset

[0863] Output: Future sales forecast results (sales amount, customer return rate, sales growth rate)

[0864] Step 4:

[0865] Report generation

[0866] The server generates a detailed report based on the forecast results. The report includes graphs showing sales forecast trends and charts illustrating changes in customer behavior. These visual data are included to make the forecast results easier to understand. Text-based explanations and supplementary information are also included.

[0867] Input: Future sales forecast results

[0868] Output: A detailed report visualizing the prediction results (graphs, charts, and explanatory text).

[0869] Step 5:

[0870] emotion recognition

[0871] The server uses an emotion engine to recognize the user's emotions in real time. To do this, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected data is sent to the server, where the emotion engine analyzes it to infer the user's emotions (e.g., positive, negative, neutral).

[0872] Input: User facial expression data, voice data

[0873] Output: User sentiment information (positive, negative, neutral)

[0874] Step 6:

[0875] Display Report

[0876] The device displays the generated report to the user. The content and format of the display are dynamically changed based on the emotion recognition results. If the user expresses positive emotions, success stories and positive predictions are highlighted. Conversely, if the user is feeling anxious, supplementary information and specific success stories are displayed to alleviate their anxiety.

[0877] Input: Emotion engine results, visualized detailed report

[0878] Output: Dynamically modified report display based on user sentiment.

[0879] (Application Example 2)

[0880] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0881] Traditional sales forecasting systems simply displayed forecast results without considering user emotions. Therefore, it was difficult to dynamically provide supplementary information or explanations to alleviate user anxiety or doubts about the forecast results. Furthermore, they failed to appropriately highlight information that would attract user attention, resulting in ineffective decision support.

[0882] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for displaying the generated report to the user and recognizing the user's emotions in real time; and means for dynamically changing the display content and format based on the user's emotions. This enables dynamic report display that takes the user's emotions into consideration, alleviates the user's anxiety and doubts about the prediction results, and provides more effective decision-making support.

[0883] A "data source" refers to the system or device that serves as the starting point for collecting information.

[0884] "Data cleansing" refers to the process of improving data quality by removing missing or outlier values ​​and eliminating duplicates.

[0885] "Normalization" refers to the process of transforming data into a format suitable for analysis by standardizing its format and units.

[0886] A "generative AI model" refers to an artificial intelligence model trained to make predictions and classifications based on large amounts of data.

[0887] "Sales forecasting" refers to the process of estimating future sales based on past data.

[0888] A "report" refers to a document that visually presents the results and details of a transaction or activity.

[0889] "Visualization" refers to the process of displaying data in forms such as graphs and charts to make it easier to understand.

[0890] "Emotion recognition" refers to the technology that reads emotions from a user's facial expressions and tone of voice.

[0891] "Real-time" refers to the immediate processing and reflection of data and information.

[0892] "Dynamic modification" refers to the automatic change of display or content depending on the situation or conditions.

[0893] This invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The detailed configuration and implementation method of this system are described below.

[0894] Data collection

[0895] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it can be used for data analysis and model training.

[0896] Data preprocessing

[0897] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[0898] Sales forecast

[0899] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[0900] Report generation

[0901] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[0902] emotion recognition

[0903] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[0904] Display Report

[0905] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[0906] Hardware and software to be used

[0907] Camera (built-in or external): Used to recognize the user's facial expressions.

[0908] Smartphone (iOS or Android): A device used by a user to run applications.

[0909] OpenCV: A library for facial recognition.

[0910] Keras: Provides deep learning models for emotion recognition.

[0911] Requests: A library for communicating with the sales forecasting API.

[0912] Specific example

[0913] For example, if a store manager at a convenience store chain uses the app to check the effectiveness of a new points program, and the manager's facial expression through the camera is "Happy," the app will highlight success stories along with the predicted results. Conversely, if the manager is perceived as "Sad" or "Fear," the app will display additional reassuring past success stories and specific advice.

[0914] Example of a prompt

[0915] "The store manager is reviewing the sales forecast report for the new points program. Pay attention to his expression; if he has a positive reaction, highlight the success stories, and if he has a negative reaction, provide additional reassurance."

[0916] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0917] Step 1:

[0918] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools, storing each type of data in a local database. It uses APIs and database connection information as input, and outputs the results of various data collections.

[0919] Step 2:

[0920] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and converts numerical data to a standard scale. It uses raw data from a local database as input, and the output is normalized data. Data cleansing improves data quality and consistency.

[0921] Step 3:

[0922] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of the points program. The generative AI model, trained on historical purchase and customer behavior data, is used for sales forecasting. The model's input is normalized data, and its output is the sales forecast. The forecast includes estimated sales increases and customer retention rates.

[0923] Step 4:

[0924] The server generates a detailed report based on the forecast results. It creates graphs showing sales forecast trends and charts illustrating changes in customer behavior, and incorporates these into the report. The input is the sales forecast results, and the output is a visualized, detailed report. Various data visualization tools are used to generate the report.

[0925] Step 5:

[0926] The server uses a camera and an emotion engine to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize emotions. The input is the user's facial expression data and voice data, and the output is the recognized emotion information.

[0927] Step 6:

[0928] The terminal displays the generated report to the user, dynamically changing the content and format based on the user's emotions. Based on the emotion recognition results, it highlights information that the user is likely to be interested in and adds supplementary information and explanations. The input is the detailed report and emotion information, and the output is the dynamically changed display content.

[0929] For example, when a user launches the app, the camera activates and recognizes the user's facial expression. If the prediction is positive and the user is identified as "Happy," the device highlights the success story. Conversely, if the user's facial expression is identified as "Sad" or "Fear" in relation to the prediction, the device displays additional reassuring past success stories and specific advice.

[0930] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0931] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0932] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0933] [Fourth Embodiment]

[0934] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0935] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0936] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0937] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0938] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0939] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0940] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0941] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0942] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0943] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0944] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0945] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0946] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0947] This invention relates to a system that uses AI to generate sales forecasts for stores that have implemented a points program and to generate detailed reports. This system is configured and implemented as follows.

[0948] Data collection

[0949] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It uses APIs and database connections to retrieve data in real time or at regular intervals, and stores it in a local database. For example, purchase data is collected from POS systems, regional data from publicly available government statistics, and customer behavior data from website analytics tools.

[0950] Data preprocessing

[0951] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format as needed. For example, if there is data with different date formats, it converts it to a unified format and scales numerical data to make it suitable for analysis.

[0952] Sales forecast

[0953] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of a points program. Because the pre-trained generative AI model learns the characteristics of the data, highly accurate predictions are possible. For example, it can predict sales increases after the introduction of a points program based on past sales data and customer purchasing behavior of a convenience store chain.

[0954] Report generation

[0955] The server generates and visualizes a detailed report based on the forecast results. The report provides information in a visually easy-to-understand format using graphs and charts, including not only projected sales growth figures but also detailed improvements in profits and customer loyalty resulting from the implementation of a points program.

[0956] Display Report

[0957] The terminal displays the generated report to the user. Users can review the report through a dedicated dashboard or web application to gain a concrete understanding of the effectiveness of the points program. For example, users can manipulate the dashboard graphs to compare different candidate scenarios.

[0958] Specific example

[0959] For example, suppose a convenience store chain in a certain region is considering introducing the PayPay points program. In this case, the server will collect the following data:

[0960] 1. Purchase data: Collect POS data for the past year.

[0961] 2. Regional data: Obtain demographic and economic indicators for the target region.

[0962] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[0963] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast sales after the introduction of the points program. Based on the forecast results, it then generates a detailed report, providing information visually using graphs and charts. Finally, the terminal displays this report to the store manager, supporting their decision-making regarding implementation based on specific figures and visualized information.

[0964] In this way, the system of the present invention can demonstrate the effects of introducing a points program in a concrete and detailed manner, enabling store managers to make data-driven decisions that minimize economic risk.

[0965] The following describes the processing flow.

[0966] Step 1:

[0967] The server collects purchase data, regional data, and customer behavior data from multiple data sources via APIs and database connections. For example, it obtains purchase data from POS systems, regional data from government statistics, and customer behavior data from website analytics tools. This data is then stored in a local database.

[0968] Step 2:

[0969] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and eliminates duplicate data. For example, it deletes records containing missing values ​​and corrects inaccurate data.

[0970] Step 3:

[0971] The server normalizes the cleansed data. By standardizing the data format and scaling it, it transforms it into a form that AI models can easily process. For example, it standardizes date formats and converts numerical data to a standard scale.

[0972] Step 4:

[0973] The server inputs pre-processed data into a generative AI model. It loads the generative AI model, extracts data features, and predicts sales after the introduction of a points program. For example, it uses past purchase history and customer behavior data to make predictions.

[0974] Step 5:

[0975] The server generates detailed reports based on the prediction results. These reports visually summarize predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing changes in total sales and charts showing changes in customer retention rates.

[0976] Step 6:

[0977] The terminal displays the generated report to the user. A dedicated dashboard or web application allows users to review the report's contents. For example, users can compare predictions for different scenarios and view detailed information on the dashboard.

[0978] Step 7:

[0979] Users make decisions about implementing a points program based on the displayed reports. They review detailed data and forecasts to determine whether to implement the program while minimizing financial risks. For example, if they determine that the projected sales increase will meet their targets, they proceed with the steps toward implementing the points program.

[0980] (Example 1)

[0981] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0982] Traditional sales forecasting methods for point programs involved cumbersome data collection and preprocessing, and did not adequately utilize generative AI models for accurate predictions. Furthermore, the generated reports were not provided in a visually easy-to-understand format, lacking the necessary information for management decision-making. Additionally, the absence of features to compare different scenarios meant insufficient support for optimal decision-making.

[0983] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0984] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the preprocessed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for enabling the comparison of multiple scenarios; and means for displaying the generated report to the user. This enables highly accurate data-driven sales forecasting and the generation of visually easy-to-understand detailed reports, providing support for managers to make optimal decisions.

[0985] "Multiple data sources" refers to a collection of materials obtained from different types and locations, and may include purchase data, geographical data, customer behavior data, etc.

[0986] "Purchase data" refers to records related to the buying and selling of goods and services, and primarily data obtained from POS systems.

[0987] "Regional data" refers to statistical information and economic indicators related to a specific geographical area, and may be obtained from publicly available government data, etc.

[0988] "Customer behavior data" refers to information about consumer behavior, including purchase history and visit history obtained from website analytics tools, etc.

[0989] "Cleaning" refers to data processing techniques used to improve the quality of raw data by removing missing or outlier values.

[0990] "Normalization" refers to a standardization technique that unifies the format of data and aligns numerical data of different scales to the same dimension.

[0991] A "generative AI model" is a predictive model built using machine learning or deep learning techniques, and refers to a system that makes predictions about new data based on a pre-trained dataset.

[0992] "Sales forecasting" refers to the process of estimating future increases or decreases in sales using historical data and generative AI models.

[0993] A "detailed report" is a document containing forecast and analysis results, which may include graphs and charts presented in a visually easy-to-understand format.

[0994] "Visualization" refers to the technique of visually displaying data and information using graphs and charts, and is a technology used to make things easier to understand.

[0995] "Scenario comparison" refers to the process of comparing multiple prediction results based on different conditions and settings to find the optimal option.

[0996] "Users" refer to the individuals or organizations that use this system, typically store owners or marketing personnel.

[0997] A "terminal" refers to a device used by a user to view system reports and data, and typically includes personal computers, tablets, and smartphones.

[0998] This invention relates to a system for accurately predicting the effectiveness of point programs in stores and generating detailed reports. This invention clearly separates the roles of the server, terminal, and user, and enables efficient and accurate sales forecasting and report generation through their coordinated operation.

[0999] Data collection

[1000] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it uses APIs and database connections to retrieve purchase data from POS systems in real time or at regular intervals, regional data from publicly available government statistics, and customer behavior data from website analytics tools. This data is stored in a local database.

[1001] Data preprocessing

[1002] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and standardizes date formats and numerical units. For example, it uses the Python Pandas library to convert data with different date formats to a unified format and standardize the scale of numerical data. This results in a dataset suitable for analysis.

[1003] Sales forecast

[1004] The server inputs pre-processed data into a generative AI model. TensorFlow or PyTorch can be used as the generative AI model. The trained model accurately predicts sales after the introduction of a points program based on past purchase history, regional data, and customer behavior data. For example, it can use sales data from the past year to predict sales growth for the next year.

[1005] Report generation

[1006] The server generates and visualizes detailed reports based on the prediction results. Using Python's Matplotlib and Seaborn libraries, the predicted data is visually displayed as bar graphs and line graphs. The reports include not only sales forecast data but also the effects of increased profits and customer loyalty after implementing a points program.

[1007] Display Report

[1008] The terminal displays the generated reports to the user. Users can review the reports through a dedicated dashboard or web application. For example, users can use the dashboard to compare different scenarios and specifically evaluate the effectiveness of implementing a points program.

[1009] Specific example

[1010] For example, suppose a retail chain is considering introducing a new points program. In this case, the server collects the following data:

[1011] 1. Purchase data: Collect POS data for the past year.

[1012] 2. Regional data: Obtain demographic and economic indicators for the target region.

[1013] 3. Customer behavior data: Analyze customer purchase history from websites and stores.

[1014] Next, the server cleanses and normalizes this data and inputs it into a generating AI model to perform sales forecasting. Then, based on the forecast results, it generates a detailed report and provides visual information using a Python visualization library. Finally, the generated report is displayed to store managers via their terminals, providing decision-making support based on specific numbers and graphs.

[1015] Example of a prompt

[1016] "Based on retail chain purchasing data, regional data, and customer behavior data from the past year, please predict sales after the introduction of a points program. Based on the prediction results, please generate a detailed report and present the data in a visualized format."

[1017] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1018] Step 1: Data Collection

[1019] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Inputs are diverse, including POS systems, government statistical data APIs, and website analytics tools. Specifically, it uses the Python requests library to retrieve data from APIs and connects to POS system databases to collect purchase data. The output is raw data stored in a local database.

[1020] Step 2: Data Cleansing

[1021] The server cleanses the collected data. The input is raw data. Specifically, it uses the Python Pandas library to impute or remove missing values. It also detects outliers and performs appropriate processing. For example, if the date format is different, it converts it to a unified format. The output is the cleansed data.

[1022] Step 3: Data Normalization

[1023] The server normalizes the cleansed data. The input is the cleansed data. Specifically, it standardizes the format of each data point and scales numerical data. For example, if purchase amounts are listed in different units, it converts them to a unified unit. The output is the normalized data.

[1024] Step 4: Data entry and forecasting

[1025] The server inputs normalized data into a generative AI model. The input is normalized data. TensorFlow or PyTorch is used for the generative AI model. Specifically, a pre-trained model is loaded, and data is input to perform sales forecasting. For example, sales for the next year are predicted from purchase data for the past year. The output is sales forecast data after the introduction of a points program.

[1026] Step 5: Report Generation

[1027] The server generates a detailed report based on the forecast results. The input is sales forecast data. Specifically, it uses Python's Matplotlib and Seaborn libraries to create graphs and charts, providing information in a visually easy-to-understand format. The report also includes forecasts for sales growth and the profit-enhancing effects of implementing a points program. The output is a detailed report.

[1028] Step 6: Display Report

[1029] The terminal displays the generated report to the user. The input is a detailed report. The user views the report through a dedicated dashboard or web application. Specifically, front-end frameworks such as React or Angular are used to display and manipulate the report. For example, the user can compare different scenarios and manipulate graphs to view detailed information. The output is the report displayed to the user.

[1030] (Application Example 1)

[1031] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1032] In modern autonomous vehicles, dynamically predicting fares and revenues, and understanding the effects of point programs in real time, presents a significant challenge. Traditional systems fail to consider external factors such as traffic conditions and local events, making accurate revenue forecasting and pricing difficult. This has hindered the efficient operation and revenue maximization of autonomous vehicle services.

[1033] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1034] In this invention, the server includes means for collecting operational data, external data, and customer data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict fares and sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; and means for displaying the generated report on a display device. This makes it possible to dynamically set fares based on demand for the operation of autonomous vehicles and to grasp the effectiveness of the points program in real time.

[1035] "Operational data" refers to information about the operation of autonomous vehicles, such as their operating history, operating hours, boarding locations, and alighting locations.

[1036] "External data" refers to information about the external environment that affects the operation of autonomous vehicles, such as local traffic conditions, events, and weather forecasts.

[1037] "Customer data" refers to information about customer behavior and attributes, such as passenger boarding history and points program usage history.

[1038] "Cleaning" is a data preprocessing technique that removes missing or outlier values ​​from data and converts it into a format suitable for analysis.

[1039] "Normalization" is a data preprocessing technique that unifies the format of data and adjusts numerical data to a consistent scale.

[1040] A "generative AI model" is a type of artificial intelligence that uses generative learning algorithms to predict future sales and pricing based on past data.

[1041] "Price prediction" refers to dynamically setting prices using a generative AI model based on collected data.

[1042] "Sales forecasting" refers to predicting sales after the introduction of a points program using collected data and generated AI models.

[1043] "Report generation" refers to creating a detailed analytical report based on predicted results and visually representing it.

[1044] A "display device" is a device used to display generated reports in real time, and includes in-car displays and driver's dashboards.

[1045] This invention provides a system for dynamically predicting fares and revenues for the operation of autonomous vehicles and for understanding the effects of implementing a points program in real time. This system mainly includes a server, means for collecting data from various data sources, means for data preprocessing, a generation AI model, means for report generation and visualization, and a display device.

[1046] Data collection

[1047] The server collects operational data, external data, and customer data from multiple data sources. APIs and database connections are used for this collection. For example, operational data is obtained from the central control system of autonomous vehicles, external data from traffic information services and weather forecast services, and customer data from the database of a points program.

[1048] Data preprocessing

[1049] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values ​​and standardizes the data format. For example, it converts data with different date formats to a unified format and scales numerical data.

[1050] Sales forecast and price forecast

[1051] The server inputs pre-processed data into a generating AI model to predict sales and appropriate pricing after the introduction of the points program. The generating AI model has learned from past operational data and customer behavior patterns, enabling highly accurate predictions. Specifically, it analyzes operational patterns and passenger behavior to suggest how to set fares for specific dates, times, and events.

[1052] Report generation and visualization

[1053] The server generates and visualizes a detailed report based on the prediction results. This report provides information in a visually easy-to-understand format using graphs and charts, as well as predicted sales and fee figures. Furthermore, it details the profits and customer loyalty improvements resulting from the implementation of the points program.

[1054] Display Report

[1055] The display device shows the generated report to the user. The user can review the report through the in-car display or driver's dashboard, gaining a concrete understanding of the effectiveness of the points program. For example, the user can manipulate the graphs on the dashboard to compare different scenarios.

[1056] Specific example

[1057] For example, suppose an autonomous taxi service in a city predicts when demand will be high based on local events and weather forecasts, and decides to implement a points program. In this case, the server collects the following data:

[1058] 1. Operational data: Collect operational data for the past year.

[1059] 2. External data: Obtain traffic conditions and weather forecasts for the target area.

[1060] 3. Customer data: Analyze the usage history of the points program.

[1061] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to forecast fares and revenues. It then generates a detailed report based on the forecast results, providing information visually using graphs and charts. Finally, the display device shows this report on the vehicle's display to help optimize the operational plan.

[1062] Example of a prompt

[1063] "Develop a system that uses autonomous vehicle operation data, local traffic conditions, and customer ride history to forecast sales after the introduction of a points program. Specifically, this includes data collection, preprocessing, sales forecasting using a generative AI model, and generating reports that visually display the forecast results."

[1064] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1065] Step 1:

[1066] The server collects operational data, external data, and customer data from multiple data sources. Specifically, operational data is obtained in real time from the central control system of autonomous vehicles, and external data is obtained from APIs of traffic information services and weather forecast services. Customer data is collected from a points program database. Input is raw data from each data source, and output is the collected integrated data.

[1067] Step 2:

[1068] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and scales numerical data. For example, it converts date data provided in different formats to a common format and reduces the variability of numerical data to a certain range. The input is the collected integrated data, and the output is the cleansed and normalized data.

[1069] Step 3:

[1070] The server inputs pre-processed data into a generative AI model to predict charges and revenue after the point program is implemented. Specifically, it uses pre-processed data to input into a pre-trained generative AI model to make highly accurate charges and revenue predictions. For example, it calculates what pricing is optimal for a specific date, time, or event based on past operating patterns and customer behavior data. The input is pre-processed data, and the output is the predicted charges and revenue results.

[1071] Step 4:

[1072] The server generates and visualizes detailed reports based on the forecast results. Specifically, it creates visually easy-to-understand reports using graphs and charts based on the price and sales forecast results. For example, it can represent the predicted sales changes with a line graph, making it easy to understand the effect of a points program. The input is the forecast results, and the output is a visualized report.

[1073] Step 5:

[1074] The terminal displays the generated reports to the user. Specifically, it displays visualized reports in real time through in-vehicle displays and driver dashboards. For example, drivers and fleet managers can review the reports to help optimize route planning and adjust fare settings. The input is the visualized reports, and the output is the information displayed on the display device.

[1075] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1076] The present invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. This system is configured and implemented as follows:

[1077] Data collection

[1078] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it becomes available for data analysis and model training.

[1079] Data preprocessing

[1080] The server cleanses the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[1081] Sales forecast

[1082] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[1083] Report generation

[1084] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[1085] emotion recognition

[1086] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[1087] Display Report

[1088] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[1089] Specific example

[1090] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[1091] 1. Purchase data: Collect POS data for the past year.

[1092] 2. Regional data: Obtain consumer demographic information for the target area.

[1093] 3. Customer behavior data: Collect data on website and app usage.

[1094] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[1095] In this way, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further, by taking into account the user's emotions, provides more user-friendly and effective decision-making support.

[1096] The following describes the processing flow.

[1097] Step 1:

[1098] The server collects purchase data, regional data, and customer behavior data from multiple data sources. For example, it obtains historical purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is then stored in a local database.

[1099] Step 2:

[1100] The server cleanses the collected data. Specifically, it removes missing and outlier values ​​and organizes duplicate data. For example, if the collected date data is in different formats, it converts it to a unified format. It also deletes or imputes records that contain missing values.

[1101] Step 3:

[1102] The server normalizes the cleansed data. It standardizes the data format and performs scaling. For example, it converts numerical data to a standard scale so that AI models can learn effectively. This makes data analysis easier.

[1103] Step 4:

[1104] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. Specifically, the predictive model estimates the increase in sales after the introduction of the points program based on historical purchase data and customer behavior. For example, the AI ​​model learns trends and customer behavior patterns from past data and estimates sales based on that.

[1105] Step 5:

[1106] The server generates a detailed report based on the forecast results. It visually summarizes predicted sales increases and improvements in customer loyalty using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[1107] Step 6:

[1108] The server uses an emotion engine to recognize the user's emotions. The emotion engine analyzes the user's facial expressions, voice tone, click behavior, etc., to determine their emotions. For example, it analyzes facial expressions from camera images and reads emotions from voice input.

[1109] Step 7:

[1110] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. For example, if the user reacts negatively to the report, additional explanations and success stories will be displayed. Conversely, if the user reacts positively, positive predictions and benefits will be emphasized.

[1111] Step 8:

[1112] Users make decisions about implementing a points program based on the displayed reports. They refer to detailed data and forecasts, as well as supplementary information provided by the sentiment engine. For example, if they determine that the predicted sales increase is achievable, they proceed with the steps toward implementing the points program. In this way, users can make data-driven decisions that minimize financial risk.

[1113] Through the processing steps described above, the system of the present invention demonstrates the effects of introducing a points program in a concrete and detailed manner, and further provides more user-friendly and effective decision-making support by taking into account the user's emotions.

[1114] (Example 2)

[1115] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1116] Traditional sales forecasting systems lack dynamic reporting that takes user sentiment into account, which hinders their ability to effectively support user decision-making. Furthermore, insufficient cleansing and normalization of collected data can lead to decreased accuracy in forecasting models.

[1117] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1118] In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using a generative AI model with the preprocessed data to predict sales after the introduction of a points program; means for generating and visualizing a detailed report based on the prediction results; means for recognizing the user's emotions in real time and dynamically changing the content of the report display based on emotion recognition; and means for displaying the generated report to the user. This enables the provision of highly accurate prediction results while also allowing for dynamic report display that responds to the user's emotions.

[1119] "Multiple data sources" refers to a collection of data sources that provide different types of information, such as purchase data, location data, and customer behavior data.

[1120] "Purchase data" refers to data that contains detailed information about when consumers purchase goods or services, specifically including the date of purchase, the items purchased, the quantity purchased, and the purchase price.

[1121] "Regional data" refers to statistical information about a specific region, including demographic information such as population, age groups, and income levels.

[1122] "Customer behavior data" refers to data about how consumers use websites and applications, including information such as page views, time spent on a site, and click-through rates.

[1123] "Data cleansing" is a process that improves data quality through steps such as removing missing values, eliminating outliers, and removing duplicate data.

[1124] "Normalization" is the process of maintaining data consistency by unifying data into a standard format and scale.

[1125] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to learn from past data and then makes predictions and classifications based on new data.

[1126] A "points program" is a program in which consumers can earn points by performing specific actions (e.g., making purchases), with the aim of improving consumer loyalty.

[1127] "Sales forecasting" is the process of estimating future sales based on past data and current trends.

[1128] "Emotion recognition" is a technology that uses devices such as cameras and microphones to analyze a user's facial expressions and tone of voice to infer their emotions.

[1129] "Dynamic changes" refer to the automatic, real-time modification of displayed content and format in response to user emotions and new information.

[1130] This invention relates to a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The system collects data from multiple data sources, cleanses and normalizes it, and then forecasts sales using a generative AI model. Furthermore, it recognizes user emotions in real time and dynamically displays reports.

[1131] Data collection

[1132] The server collects purchase data, regional data, and customer behavior data via APIs and database connections. Specifically, it obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools. This data is stored in a local database and used for subsequent data analysis and model training.

[1133] Data preprocessing

[1134] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. It also improves data quality by standardizing date formats and numerical data.

[1135] Sales forecast

[1136] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of the points program. This model uses machine learning algorithms to learn from past data and outputs prediction results. For example, it predicts increased sales and customer retention rates, and provides specific figures to store managers.

[1137] Report generation

[1138] The server generates and visualizes detailed reports based on the forecast results. Graphs and charts are used to visually demonstrate projected increases in sales and customer loyalty. For example, it can create graphs showing sales forecast trends and charts illustrating changes in customer behavior.

[1139] emotion recognition

[1140] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers user emotions based on facial expression analysis, speech recognition, and user actions. For example, it analyzes facial expressions using a camera and detects emotions from voice input.

[1141] Display Report

[1142] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[1143] Specific example

[1144] For example, if a small restaurant chain is considering implementing a points program, the server will collect the following data:

[1145] 1. Purchase data: Collect POS data for the past year.

[1146] 2. Regional data: Obtain consumer demographic information for the target area.

[1147] 3. Customer behavior data: Collect data on website and app usage.

[1148] Next, the server cleanses and normalizes the collected data and inputs it into a generating AI model to predict sales after the introduction of the points program. Based on the prediction results, it generates a detailed report and dynamically displays the report while recognizing the user's emotions using an emotion engine. For example, if a restaurant chain manager looks anxious when reviewing the report, specific success stories will be displayed to alleviate their anxiety.

[1149] Examples of prompts to input into a generative AI model

[1150] "Using POS data from the past year, local consumer demographics, and website usage data, predict sales after the introduction of the points program."

[1151] This prompt allows the AI ​​model to make highly accurate sales forecasts based on the necessary data.

[1152] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1153] Step 1:

[1154] Data collection

[1155] The server first collects the necessary data from multiple data sources. Specifically, it sends API requests to retrieve purchase data from the POS system for the past year. Next, it collects local data (e.g., population, age groups, income) from publicly available government databases. Furthermore, it accesses web analytics tools (e.g., Google Analytics) to obtain customer behavior data (e.g., page views, time spent on site, click-through rate). All of this data is stored in a local database.

[1156] Inputs: Data collection APIs, POS systems, publicly available government databases, web analytics tools

[1157] Output: Purchase data, regional data, and customer behavior data stored in the local database.

[1158] Step 2:

[1159] Data preprocessing

[1160] The server cleanses and normalizes the collected data. It searches for and removes records containing missing values. It detects and removes outliers (e.g., values ​​outside the data range or obviously incorrect values). It also searches for and removes duplicate data. Furthermore, it unifies date formats if they differ and standardizes the scale of numerical data.

[1161] Input: Raw data from a local database

[1162] Output: Cleansed and normalized dataset

[1163] Step 3:

[1164] Sales forecast

[1165] The server provides pre-processed data as input to the generating AI model. The model uses an algorithm learned from past purchase data, regional data, and customer behavior data to predict sales after the introduction of the points program. Specific outputs of the prediction include future sales figures, customer return rates, and sales growth rates.

[1166] Input: Cleansed and normalized dataset

[1167] Output: Future sales forecast results (sales amount, customer return rate, sales growth rate)

[1168] Step 4:

[1169] Report generation

[1170] The server generates a detailed report based on the forecast results. The report includes graphs showing sales forecast trends and charts illustrating changes in customer behavior. These visual data are included to make the forecast results easier to understand. Text-based explanations and supplementary information are also included.

[1171] Input: Future sales forecast results

[1172] Output: A detailed report visualizing the prediction results (graphs, charts, and explanatory text).

[1173] Step 5:

[1174] emotion recognition

[1175] The server uses an emotion engine to recognize the user's emotions in real time. To do this, the device uses a camera and microphone to collect the user's facial expressions and voice. The collected data is sent to the server, where the emotion engine analyzes it to infer the user's emotions (e.g., positive, negative, neutral).

[1176] Input: User facial expression data, voice data

[1177] Output: User sentiment information (positive, negative, neutral)

[1178] Step 6:

[1179] Display Report

[1180] The device displays the generated report to the user. The content and format of the display are dynamically changed based on the emotion recognition results. If the user expresses positive emotions, success stories and positive predictions are highlighted. Conversely, if the user is feeling anxious, supplementary information and specific success stories are displayed to alleviate their anxiety.

[1181] Input: Emotion engine results, visualized detailed report

[1182] Output: Dynamically modified report display based on user sentiment.

[1183] (Application Example 2)

[1184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1185] Traditional sales forecasting systems simply displayed forecast results without considering user emotions. Therefore, it was difficult to dynamically provide supplementary information or explanations to alleviate user anxiety or doubts about the forecast results. Furthermore, they failed to appropriately highlight information that would attract user attention, resulting in ineffective decision support.

[1186] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting purchase data, regional data, and customer behavior data from multiple data sources; means for cleansing and normalizing the collected data; means for using the pre-processed data to predict sales after the introduction of a points program using a generated AI model; means for generating and visualizing a detailed report based on the prediction results; means for displaying the generated report to the user and recognizing the user's emotions in real time; and means for dynamically changing the display content and format based on the user's emotions. This enables dynamic report display that takes the user's emotions into consideration, alleviates the user's anxiety and doubts about the prediction results, and provides more effective decision-making support.

[1187] A "data source" refers to the system or device that serves as the starting point for collecting information.

[1188] "Data cleansing" refers to the process of improving data quality by removing missing or outlier values ​​and eliminating duplicates.

[1189] "Normalization" refers to the process of transforming data into a format suitable for analysis by standardizing its format and units.

[1190] A "generative AI model" refers to an artificial intelligence model trained to make predictions and classifications based on large amounts of data.

[1191] "Sales forecasting" refers to the process of estimating future sales based on past data.

[1192] A "report" refers to a document that visually presents the results and details of a transaction or activity.

[1193] "Visualization" refers to the process of displaying data in forms such as graphs and charts to make it easier to understand.

[1194] "Emotion recognition" refers to the technology that reads emotions from a user's facial expressions and tone of voice.

[1195] "Real-time" refers to the immediate processing and reflection of data and information.

[1196] "Dynamic modification" refers to the automatic change of display or content depending on the situation or conditions.

[1197] This invention is a sales forecasting system that includes a function to recognize user emotions and dynamically display reports based on them. The detailed configuration and implementation method of this system are described below.

[1198] Data collection

[1199] The server collects purchase data, regional data, and customer behavior data from multiple data sources. Specifically, it obtains purchase data from POS systems via APIs and database connections, regional data from publicly available government databases, and customer behavior data from web analytics tools. By storing this data in a local database, it can be used for data analysis and model training.

[1200] Data preprocessing

[1201] The server cleanses and normalizes the collected data. It removes missing and outlier values ​​and eliminates duplicate data. For example, it converts different date formats to a unified format and changes numerical data to a standard scale. Data cleansing improves data quality.

[1202] Sales forecast

[1203] The server inputs pre-processed data into a generating AI model to predict sales after the introduction of a points program. The model is trained on past purchase and customer behavior data, enabling highly accurate predictions. For example, it predicts increased sales and customer retention rates, providing store managers with concrete figures.

[1204] Report generation

[1205] The server generates a detailed report based on the forecast results. It summarizes predicted sales increases and improvements in customer loyalty in a visually easy-to-understand format using graphs and charts. For example, it creates graphs showing sales forecast trends and charts showing changes in customer behavior, and incorporates them into the report.

[1206] emotion recognition

[1207] The server uses an emotion engine to recognize user emotions in real time. The emotion engine infers how the user feels about the report based on facial expression analysis, speech recognition, and user actions. For example, it analyzes the user's facial expressions with a camera and reads emotions from voice input.

[1208] Display Report

[1209] When displaying generated reports to the user, the device dynamically changes the content and format based on the user's emotions. Based on the results of emotion recognition, it highlights information that the user is likely to be interested in, and adds supplementary information or explanations if the user is feeling anxious. For example, if the user shows a positive reaction, success stories and positive predictions will be highlighted.

[1210] Hardware and software to be used

[1211] Camera (built-in or external): Used to recognize the user's facial expressions.

[1212] Smartphone (iOS or Android): A device used by a user to run applications.

[1213] OpenCV: A library for facial recognition.

[1214] Keras: Provides deep learning models for emotion recognition.

[1215] Requests: A library for communicating with the sales forecasting API.

[1216] Specific example

[1217] For example, if a store manager at a convenience store chain uses the app to check the effectiveness of a new points program, and the manager's facial expression through the camera is "Happy," the app will highlight success stories along with the predicted results. Conversely, if the manager is perceived as "Sad" or "Fear," the app will display additional reassuring past success stories and specific advice.

[1218] Example of a prompt

[1219] "The store manager is reviewing the sales forecast report for the new points program. Pay attention to his expression; if he has a positive reaction, highlight the success stories, and if he has a negative reaction, provide additional reassurance."

[1220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1221] Step 1:

[1222] The server collects purchase data, regional data, and customer behavior data from multiple data sources. It obtains purchase data from POS systems, regional data from publicly available government databases, and customer behavior data from web analytics tools, storing each type of data in a local database. It uses APIs and database connection information as input, and outputs the results of various data collections.

[1223] Step 2:

[1224] The server cleanses and normalizes the collected data. Specifically, it removes missing and outlier values, standardizes date formats, and converts numerical data to a standard scale. It uses raw data from a local database as input, and the output is normalized data. Data cleansing improves data quality and consistency.

[1225] Step 3:

[1226] The server inputs pre-processed data into a generative AI model to predict sales after the introduction of the points program. The generative AI model, trained on historical purchase and customer behavior data, is used for sales forecasting. The model's input is normalized data, and its output is the sales forecast. The forecast includes estimated sales increases and customer retention rates.

[1227] Step 4:

[1228] The server generates a detailed report based on the forecast results. It creates graphs showing sales forecast trends and charts illustrating changes in customer behavior, and incorporates these into the report. The input is the sales forecast results, and the output is a visualized, detailed report. Various data visualization tools are used to generate the report.

[1229] Step 5:

[1230] The server uses a camera and an emotion engine to recognize the user's emotions in real time. It analyzes the user's facial expressions and voice to recognize emotions. The input is the user's facial expression data and voice data, and the output is the recognized emotion information.

[1231] Step 6:

[1232] The terminal displays the generated report to the user, dynamically changing the content and format based on the user's emotions. Based on the emotion recognition results, it highlights information that the user is likely to be interested in and adds supplementary information and explanations. The input is the detailed report and emotion information, and the output is the dynamically changed display content.

[1233] For example, when a user launches the app, the camera activates and recognizes the user's facial expression. If the prediction is positive and the user is identified as "Happy," the device highlights the success story. Conversely, if the user's facial expression is identified as "Sad" or "Fear" in relation to the prediction, the device displays additional reassuring past success stories and specific advice.

[1234] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1235] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1236] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1237] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1238] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1239] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1240] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1241] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1242] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1243] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1244] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1245] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1246] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1247] 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.

[1248] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1249] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1250] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1251] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1252] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1253] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1254] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1255] The following is further disclosed regarding the embodiments described above.

[1256] (Claim 1)

[1257] A means of collecting purchase data, regional data, and customer behavior data from multiple data sources,

[1258] A means for cleansing and normalizing the aforementioned collected data,

[1259] A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model,

[1260] A means for generating and visualizing a detailed report based on the aforementioned prediction results,

[1261] Means for displaying the generated report to the user,

[1262] A system that includes this.

[1263] (Claim 2)

[1264] The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining purchase data, regional data, and customer behavior data.

[1265] (Claim 3)

[1266] The system according to claim 1, which loads a generated AI model using the pre-processed data and performs sales forecasting after the introduction of the points program.

[1267] "Example 1"

[1268] (Claim 1)

[1269] A means of collecting purchase data, regional data, and customer behavior data from multiple data sources,

[1270] A means for cleansing and normalizing the aforementioned collected data,

[1271] A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model,

[1272] A means for generating and visualizing a detailed report based on the aforementioned prediction results,

[1273] Means for displaying the generated report to the user,

[1274] A means to enable the comparison of multiple scenarios,

[1275] A system that includes this.

[1276] (Claim 2)

[1277] The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining purchase data, regional data, and customer behavior data.

[1278] (Claim 3)

[1279] The system according to claim 1, which loads a generated AI model using the pre-processed data and performs sales forecasting after the introduction of the points program.

[1280] "Application Example 1"

[1281] (Claim 1)

[1282] A means of collecting operational data, external data, and customer data from multiple data sources,

[1283] A means for cleansing and normalizing the aforementioned collected data,

[1284] A means for predicting fees and sales after the introduction of a points program using the aforementioned preprocessed data and a generating AI model,

[1285] A means for generating and visualizing a detailed report based on the aforementioned prediction results,

[1286] Means for displaying the generated report on a display device,

[1287] A system that includes this.

[1288] (Claim 2)

[1289] The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining operational data, external data, and customer data.

[1290] (Claim 3)

[1291] The system according to claim 1, which loads a generated AI model using the pre-processed data and performs a forecast of charges and sales after the introduction of the points program.

[1292] "Example 2 of combining an emotion engine"

[1293] (Claim 1)

[1294] A means of collecting purchase data, regional data, and customer behavior data from multiple data sources,

[1295] A means for cleansing and normalizing the aforementioned collected data,

[1296] A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model,

[1297] A means for generating and visualizing a detailed report based on the aforementioned prediction results,

[1298] A means for recognizing the user's emotions in real time and dynamically changing the content of the report based on the emotion recognition,

[1299] Means for displaying the generated report to the user,

[1300] A system that includes this.

[1301] (Claim 2)

[1302] The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining purchase data, regional data, and customer behavior data.

[1303] (Claim 3)

[1304] The system according to claim 1, which loads a generated AI model using the pre-processed data and performs sales forecasting after the introduction of the points program.

[1305] "Application example 2 of combining emotional engines"

[1306] (Claim 1)

[1307] A means of collecting purchase data, regional data, and customer behavior data from multiple data sources,

[1308] A means for cleansing and normalizing the aforementioned collected data,

[1309] A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model,

[1310] A means for generating and visualizing a detailed report based on the aforementioned prediction results,

[1311] A means for displaying the generated report to the user and recognizing the user's emotions in real time,

[1312] A means of dynamically changing the displayed content and format based on the user's emotions,

[1313] A system that includes this.

[1314] (Claim 2)

[1315] The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining purchase data, regional data, and customer behavior data.

[1316] (Claim 3)

[1317] The system according to claim 1, which loads a generated AI model using the pre-processed data and performs sales forecasting after the introduction of the points program. [Explanation of Symbols]

[1318] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting purchase data, regional data, and customer behavior data from multiple data sources, A means for cleansing and normalizing the aforementioned collected data, A means for predicting sales after the introduction of a points program using the aforementioned preprocessed data and a generated AI model, A means for generating and visualizing a detailed report based on the aforementioned prediction results, Means for displaying the generated report to the user, A system that includes this.

2. The system according to claim 1, wherein the data collection from the aforementioned multiple data sources includes obtaining purchase data, regional data, and customer behavior data.

3. The system according to claim 1, which loads a generated AI model using the pre-processed data and performs sales forecasting after the introduction of the points program.

Images