System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting historical shipment, inventory, and sales information; means for receiving and storing the information in a database; means for predicting future shipment quantities from the inputted information using a generative AI model; and means for generating and providing the prediction results to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Companies and warehouse managers managing logistics centers and warehouses face many challenges, including inventory surpluses and shortages and the difficulty of allocating personnel to meet shipping plans. This leads to reduced productivity and increased costs, negatively impacting corporate profits. With the expansion of e-commerce in particular, there is a demand for accurate forecasts of shipping quantities and proposals for appropriate sales strategies, but this is difficult to do manually. This invention solves these challenges and aims to optimize and streamline logistics. [Means for solving the problem]

[0005] The present invention provides a system that includes means for inputting past shipping data, inventory data, and sales data, receiving the data, and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, and means for generating and providing the user with prediction results. The system also includes means for generating optimal sales strategies based on the prediction results, means for simulating the effects of the sales strategies, and means for providing the user with the simulation results, thereby achieving accurate shipping forecasts and appropriate sales strategy proposals. Furthermore, the system also includes means for periodically inputting new data, receiving the data, and updating the database, means for retraining the prediction model based on the new data, and means for generating and providing the user with improved prediction results using the retrained prediction model, thereby continuously improving prediction accuracy.

[0006] "Shipping data" is information relating to the quantity, type, date, etc. of products shipped from a warehouse or logistics center within a certain period of time.

[0007] "Inventory data" refers to information regarding the quantity, type, and storage location of products currently stored in warehouses and logistics centers.

[0008] "Sales data" refers to information relating to the sales quantity, sales price, sales date and time, customer information, and the like of a product.

[0009] A "generative AI model" is a mathematical or algorithmic model that uses artificial intelligence techniques to make predictions or suggestions from data.

[0010] "Prediction" is the act or result of calculating future events or figures based on past data.

[0011] "Sales measures" are specific activities such as promotions, campaigns, and discounts that are carried out with the aim of promoting product sales.

[0012] "Simulation" refers to the act or result of testing the effectiveness or results of a system or measure under specific conditions or circumstances in a virtual environment.

[0013] "Self-learning" is the function or process by which a system improves its performance and predictive accuracy based on new data and experience.

[0014] A "predictive model" is a mathematical or algorithmic model that uses historical data to forecast future events or values.

[0015] A "database" is a system for efficiently storing, managing, and retrieving structured data. [Brief explanation of the drawings]

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

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

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

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

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

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

[0022] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0024] [First embodiment]

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

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

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

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

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

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

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

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

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

[0037] The system of the present invention begins when a logistics center or warehouse manager inputs past shipping data, inventory data, and sales data. This data is received by a server and stored in a database. The input data is then analyzed using a generative AI model to predict future shipping quantities. The prediction results are provided to the user.

[0038] Example 1: Data Entry

[0039] Users prepare shipping and inventory data from the past year and upload it to the system's data entry screen. Data can be entered in CSV or Excel format. For example, users can select and upload a file containing monthly shipping and inventory figures from January to December 2022.

[0040] Example 2: Data Receipt and Storage

[0041] The server receives files uploaded by users and stores them in storage. It then stores them in a database and centralizes the data. This allows past data to be efficiently organized and accessible at any time.

[0042] Example 3: Generating a predictive model

[0043] The server trains a generative AI model based on the received data. This process uses machine learning libraries such as TensorFlow and PyTorch. Once the training phase is complete, future shipment quantities are predicted. For example, the forecast shipment quantities for January to December 2023 are obtained.

[0044] Example 4: Providing prediction results

[0045] The server converts the forecast results into graphs and tables and provides them in an easy-to-understand format. Users can view these forecast results through the system's dashboard. This information can be used to make appropriate personnel allocation and inventory management.

[0046] Example 5: Proposal of optimal sales measures

[0047] The server also receives and analyzes past sales data. It uses a generative AI model to generate optimal sales strategies and simulate their effectiveness. For example, it proposes optimal discount rates and marketing strategies for promoting new products. These strategies are simulated and the results are provided to the user.

[0048] Example 6: Self-learning and accuracy improvement

[0049] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, you will get more accurate results than the first time.

[0050] As described above, the present invention is a system that enables efficient management of logistics centers and warehouses, and realizes optimization of shipping forecasts and sales strategies.

[0051] The processing flow will be explained below.

[0052] Generate shipment quantity forecasts

[0053] Step 1: Data entry

[0054] The user prepares past shipping data, inventory data, and sales data.

[0055] The user uploads past data in CSV or Excel file format from the system's data entry screen.

[0056] Step 2: Receiving and storing data

[0057] The server receives the uploaded file from the user.

[0058] The server stores the received data in temporary storage.

[0059] Step 3: Save the data to a database

[0060] The server reads the data stored in the storage and stores it in the database.

[0061] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[0062] Step 4: Generate a predictive model

[0063] The server retrieves the data stored in the database and performs preprocessing.

[0064] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[0065] Step 5: Run a prediction

[0066] The server uses the generated AI model to predict future shipment quantities.

[0067] The server retrieves and organizes the prediction results.

[0068] Step 6: Providing prediction results

[0069] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[0070] Proposing optimal sales strategies

[0071] Step 1: Enter your sales data

[0072] Users upload past sales and campaign data into the system.

[0073] Step 2: Receiving and storing sales data

[0074] A server receives sales data uploaded by users.

[0075] The server stores the received data in a database.

[0076] Step 3: Generate a sales execution model

[0077] The server analyzes the sales data and builds a sales strategy model.

[0078] The server uses the generated AI model to automatically generate optimal sales strategies.

[0079] Step 4: Run the simulation

[0080] The server simulates the effect of the automatically generated sales measures.

[0081] The server organizes the simulation results.

[0082] Step 5: Providing simulation results

[0083] The server displays the simulation results on a dashboard for the user.

[0084] Improved prediction accuracy through self-learning

[0085] Step 1: Enter new data

[0086] Users periodically upload the latest shipping and sales data to the system.

[0087] Step 2: Receive and store the latest data

[0088] The server receives the latest data and stores it in storage.

[0089] The server adds and saves the received data to the database.

[0090] Step 3: Retrain the model

[0091] The server retrains the existing predictive model using the latest data.

[0092] The server verifies the accuracy of the retrained model.

[0093] Step 4: Providing improved prediction results

[0094] The server uses the retrained model to make new predictions and generate improved prediction results.

[0095] The server provides the new prediction results to the user and displays them on a dashboard.

[0096] Through these processing steps, the system achieves highly accurate shipping forecasts and proposes optimal sales strategies, supporting the efficiency and optimization of logistics.

[0097] Example 1

[0098] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0099] Logistics centers and warehouses require highly accurate predictions of future shipment quantities and sales strategies based on past shipping, inventory, and sales data. However, previous systems did not centralize data management or improve prediction accuracy sufficiently, making it difficult to efficiently manage inventory and optimize sales strategies. Another challenge was continually improving the accuracy of prediction models by utilizing new data.

[0100] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0101] In this invention, the server includes a means for a user to input past data, a means for receiving the data, storing the data in a database, and centrally managing the data, a means for predicting future shipment quantities from the input data using a generative AI model, and a means for visualizing the prediction results and providing them to the user. This enables efficient data management and highly accurate shipment quantity predictions. The system also includes a means for generating optimal measures based on predictions made using the generative AI model and simulating their effects, thereby optimizing sales measures. Furthermore, the accuracy of predictions can be continuously improved by periodically inputting new data to update the database and retraining the prediction model.

[0102] "Historical data" refers to previous shipping data, inventory data, and sales data collected at distribution centers and warehouses.

[0103] "Users" refer to managers of logistics centers and warehouses who operate the system, input data, and utilize the prediction results.

[0104] "Database" refers to an information storage system for organizing and centrally managing received data.

[0105] A "generative AI model" refers to an artificial intelligence model that uses past data to predict future shipment volumes and optimal sales strategies.

[0106] "Visualization" refers to the process of converting prediction results into graphs, tables, or other formats and presenting them in a way that is easy for users to understand.

[0107] "Measures" refer to specific strategies and measures for formulating optimal action plans based on the prediction results.

[0108] "Simulation" refers to the process of estimating the effects of new measures in advance and verifying them on a trial basis.

[0109] "Retraining" refers to the training process of updating a generative AI model with new data to improve its predictive accuracy.

[0110] "Efficient data management" means quickly organizing and storing incoming data so that it remains easily accessible when needed.

[0111] "Prediction accuracy" refers to an indicator of how accurately a generative AI model can predict future shipment volumes and the effectiveness of sales strategies.

[0112] The system of the present invention is designed to enable managers of logistics centers and warehouses to efficiently forecast and optimize shipping quantities and sales strategies. This system is implemented in the following manner.

[0113] First, the user prepares shipping and inventory data for the past year and uploads it from the system's data input screen. This data is entered in CSV or Excel format. For example, an Excel file containing monthly shipping and inventory quantities from January to December 2022 can be selected and uploaded. An example of a specific prompt is, "Please upload shipping data for the past year (e.g., Excel file from January to December 2022)."

[0114] Next, the terminal sends the file selected by the user to the system. The server receives the file and saves it in storage. It then stores it in a database for centralized data management. For example, validation processing is performed to detect missing values ​​and outliers.

[0115] The server trains a generative AI model based on the received shipping and inventory data. This process uses machine learning libraries such as TensorFlow and PyTorch. The server performs feature engineering based on past data and converts the data into a form that can be input to the model. Once the training phase is complete, future shipping quantities are predicted. For example, shipping quantities from January to December 2023 are predicted.

[0116] Furthermore, the server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). Users can view these prediction results by opening the system's dashboard. The server also provides a function to update the dashboard in real time. An example of a specific prompt is "Please open the dashboard to check the prediction results."

[0117] In addition, the server analyzes past sales data and generates optimal sales measures using a generative AI model. A function to simulate the effects of these measures is also provided, and the optimal discount rate and marketing strategy for promoting new products are proposed. These proposals are provided to users via the dashboard. An example of a specific prompt is, "Please propose the optimal discount rate for promoting new products."

[0118] Finally, users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, the accuracy will be better than the first forecast.

[0119] Through the above steps, this system enables efficient management of logistics centers and warehouses, and realizes the optimization of shipping forecasts and sales strategies.

[0120] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0121] Step 1: The user uploads shipping and inventory data from the past year to the system's data input screen. The input is in CSV or Excel format, and includes files recording monthly shipping and inventory quantities from January to December 2022. The terminal sends these files to the system, where they are received by the server.

[0122] Step 2: The server saves the file received from the user in storage. The contents of this file are then stored in a database for centralized management. When the data is stored in the database, a validation process is performed to detect missing values ​​and outliers. The output of this stage is the data correctly stored and organized in the database.

[0123] Step 3: The server retrieves past shipping and inventory data from the database and uses this data to train a generative AI model. Specifically, training is performed using machine learning libraries such as TensorFlow and PyTorch. Feature engineering is performed based on the past data, and the data is converted into a form that can be input into the model. Future shipping quantities are predicted using the input past data and the AI ​​model. The output of this stage is predicted future shipping data.

[0124] Step 4: The server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). The user can then open the system's dashboard to view the prediction results. The dashboard displays the prediction results updated in real time. As an output, the prediction results are provided to the user in a visually easy-to-understand format.

[0125] Step 5: The server analyzes past sales data and generates optimal sales measures using a generative AI model. Specifically, the model proposes optimal discount rates and marketing strategies for promoting new products. The server then simulates the effects of these measures and provides them to the user. The user can use this as a reference to actually implement the measures. The output includes the simulation results and the proposed measures.

[0126] Step 6: Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data. The retrained predictive model can generate more accurate predictions. Finally, the predictions made by the retrained model are provided to the user. The output includes the improved predictions based on the retrained model.

[0127] (Application example 1)

[0128] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0129] To improve the accuracy of shipping forecasts and inventory management at logistics centers and warehouses, it is important not only to make forecasts based on past data, but also to quickly input data on-site and obtain real-time information. However, with conventional systems, data input was time-consuming and manual, and there were limited ways to check forecast results and sales measures in real time. This made it difficult to operate efficiently and plan optimal sales measures.

[0130] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0131] In this invention, the server includes: a means for inputting past shipping data, inventory data, and sales data; a means for receiving the data and storing it in a database; a means for predicting future shipping quantities from the input data using a generative AI model; a means for generating the prediction results and providing them to the user; a means for checking shipping prediction data in real time using a smart device; and a means for photographing past shipping and inventory data and inputting the data using OCR technology. This allows for quick and efficient data entry and confirmation of prediction results, enabling more efficient operation of logistics centers and warehouses and optimized inventory management. It also enables the planning and simulation of sales strategies based on the improved prediction results produced by the generative AI model.

[0132] "Past shipping data" refers to data that includes specific quantities, dates and times, and product information regarding shipments that have been made in advance.

[0133] "Inventory data" refers to data that indicates the quantity, type, and contents of products stored in warehouses and logistics centers.

[0134] "Sales data" refers to data that includes specific information regarding the sales quantity, sales destination, sales period, and sales amount of a product.

[0135] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze past data and generate future trends and predictions.

[0136] A "smart device" is a portable electronic device that can connect to the Internet, such as a smartphone or smart glasses.

[0137] "OCR technology" refers to optical character recognition technology, which extracts and digitizes character information from image data.

[0138] A "prompt" is a written instruction or question that is input to a generative AI model, and the AI ​​responds or analyzes based on this.

[0139] The system for realizing this invention is designed for efficient management in logistics centers and warehouses. A specific embodiment of this system is described below.

[0140] System Configuration

[0141] Hardware

[0142] Server: Receives, stores, analyzes data, and performs training and prediction processing for generated AI models. Examples include database servers and GPU servers for machine learning.

[0143] Smart devices: Smartphones and smart glasses are used to assist users in inputting and verifying data.

[0144] Camera: Cameras built into smartphones and smart glasses are used to capture inventory and shipping data.

[0145] software

[0146] Database: Used to centrally manage received data. Examples include MySQL and PostgreSQL.

[0147] Generative AI model: An AI model generated using TensorFlow and PyTorch that predicts future shipment quantities based on past data.

[0148] OCR technology: Optical character recognition technology is used to extract text information from image data. For example, Google Cloud Vision API is used.

[0149] Web application: Using frameworks such as Streamlit, we provide users with an interface that visualizes prediction results and sales strategies.

[0150] Detailed System Operation

[0151] The server provides a means to input past shipping data, inventory data, and sales data. Users can upload this data in the form of CSV files or photographed images and enter it into the system. Data can be easily entered from the field using a smart device.

[0152] The server then receives the uploaded data and stores it in a database, where it uses OCR technology to extract text information from the image data and store it as structured data.

[0153] The server uses a generative AI model based on the received data to predict future shipping quantities, which will improve the efficiency of future shipping and inventory management. The prediction results can be viewed in real time via smart devices and are provided to users in graph and table format.

[0154] Furthermore, the server generates optimal sales strategies based on the prediction results and simulates their effectiveness. Users can obtain these strategies in real time through the voice assistant of their smart device and check important information.

[0155] Specific examples

[0156] When a user says to the smart glasses, "I would like to check the shipment forecast data for March 2023," the voice assistant will provide a real-time shipment forecast.

[0157] Simply tap the "Upload inventory data" button on your smartphone and use the camera to take a photo of your inventory list. OCR technology will automatically convert the data into text and upload it to the system.

[0158] Prompt Sentence Examples

[0159] "Please upload shipping data for the past year."

[0160] "Generate a shipping forecast for the next month."

[0161] "Please show me the results of the sales strategy simulation."

[0162] This system will significantly improve the efficiency of shipping forecasts and inventory management at logistics centers and warehouses, enabling real-time information acquisition and policy planning.

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] The server provides a means for users to input past shipping data, inventory data, and sales data. Users can input data using their smart devices and upload data in CSV files or image format. The input data is converted into a format that can be saved in the database.

[0166] Input: CSV file, image data

[0167] Output: Converted data that can be saved in a database

[0168] Specific operation: The user takes a photo of the inventory list using their smartphone and uploads it to the system.

[0169] Step 2:

[0170] The server receives the uploaded data and stores it in a database. Using OCR technology, text information is extracted from the image data and stored as structured data. The data is then centrally managed with correlation.

[0171] Input: Converted data in input format

[0172] Output: Data converted to text, stored in a database

[0173] Specific operation: The server uses Google Cloud Vision API or similar to extract and save text information from image data.

[0174] Step 3:

[0175] The server trains a generative AI model based on the received data. The trained model is used to predict future shipment quantities. The generative AI model is built using TensorFlow and PyTorch to analyze the data.

[0176] Input: Structured data

[0177] Output: A trained generative AI model

[0178] Specific operation: The server launches TensorFlow and trains an AI model using the received data.

[0179] Step 4:

[0180] The server uses the trained generative AI model to predict future shipment quantities, and the results are converted into a format that users can view and provided via their smart devices, displayed in graphs and tables.

[0181] Input: Trained generative AI model, data needed to predict future shipments

[0182] Output: Shipping quantity forecast result

[0183] Specific operation: The prediction results are converted into graphs and tables and displayed on the user's smart device.

[0184] Step 5:

[0185] The server generates optimal sales strategies based on the prediction results and simulates their effectiveness. The simulation results are provided to the user in real time via the voice assistant.

[0186] Input: Forecast results, past sales data

[0187] Output: Sales strategies, simulation results

[0188] What it does: The voice assistant responds to user prompts and presents simulation results.

[0189] Step 6:

[0190] Users periodically input new shipping and sales data, which the server receives and updates the database, retraining the generative AI model and providing improved prediction results.

[0191] Input: New shipping data, sales data

[0192] Output: Updated database, improved prediction results

[0193] How it works: Users periodically upload data, and the server automatically updates and retrains the database.

[0194] Step 7:

[0195] The server responds in real time by providing the necessary data in response to prompts from the user. Examples of prompts include "Generate a shipping forecast for the next month" and "Display the results of a sales strategy simulation."

[0196] Input: prompt statement

[0197] Output: Real-time data, forecast data, simulation results

[0198] Specific behavior: The server parses the prompt, performs the necessary processing, and provides the answer to the user.

[0199] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0200] The system of the present invention incorporates a means for inputting past shipping data, inventory data, and sales data, as well as an emotion engine that recognizes the user's emotions, making it possible to provide information and propose sales measures that are more optimized for the user.

[0201] Example 1: Data entry and reception

[0202] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The server receives this data, saves it in storage, and then stores it in the database.

[0203] Example 2: Predictive model generation and prediction

[0204] The server trains a generative AI model based on the data stored in the database. Once trained, the model is used to predict future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables and displayed on a dashboard.

[0205] Example 3: Incorporating an Emotion Engine

[0206] The system is equipped with an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze that data. For example, it can obtain user emotion data through a camera or microphone.

[0207] Example 4: Adjusting display methods based on emotions

[0208] The server receives emotion data from the emotion engine and adjusts the display of prediction results depending on the user's state. For example, if the user is feeling stressed, the server may simplify the prediction results or display a message recommending a specific action.

[0209] Example 5: Proposal of optimal sales measures

[0210] The server generates optimal sales strategies based on the prediction results, taking into account emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will prioritize suggesting sales strategies with low risk. It also simulates the effects of the proposed sales strategies and provides the results to the user.

[0211] Example 6: Self-learning and accuracy improvement

[0212] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. By retraining the predictive model based on the new data, prediction accuracy is continuously improved. User emotion data recognized by the emotion engine is also used for retraining.

[0213] Specific examples

[0214] 1. Data Entry:

[0215] Users upload shipping, inventory, and sales data for 2022 into the system.

[0216] 2. Receiving and storing data:

[0217] The server receives the data and stores it in a database.

[0218] 3. Generate predictive models:

[0219] The server trains a generative AI model to predict shipment volumes for 2023.

[0220] 4. Use of Emotion Engine:

[0221] When a user operates the system, the emotion engine analyzes the user's facial expressions and voice to recognize emotions such as stress or joy.

[0222] 5. Adjust the display:

[0223] The server detects from the emotion data that the user is feeling stressed and simplifies the display content to make it easier to understand.

[0224] 6. Sales strategy proposal:

[0225] The server takes into account emotional data and prioritizes safe sales strategies.

[0226] 7. Self-learning and accuracy improvement:

[0227] Users upload their latest data, and the server uses that data to retrain the predictive model, also leveraging feedback from the emotion engine.

[0228] As described above, the system of the present invention realizes more accurate and user-friendly shipping forecasts and sales strategy proposals, and supports the efficient operation of logistics centers and warehouses.

[0229] The processing flow will be explained below.

[0230] Generate shipment volume forecasts and incorporate sentiment engines

[0231] Step 1: Data entry

[0232] The user prepares past shipping data, inventory data, and sales data.

[0233] Users upload this data in CSV or Excel file format through the system's data entry screen.

[0234] Step 2: Receiving and storing data

[0235] The server receives the uploaded file from the user.

[0236] The server stores the received data in temporary storage.

[0237] Step 3: Save the data to a database

[0238] The server reads the data stored in the storage and stores it in the database.

[0239] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[0240] Step 4: Generate a predictive model

[0241] The server retrieves the data stored in the database and performs preprocessing.

[0242] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[0243] Step 5: Run a prediction

[0244] The server uses the generated AI model to predict future shipment quantities.

[0245] The server retrieves and organizes the prediction results.

[0246] Step 6: Providing prediction results

[0247] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[0248] Proposing optimal sales strategies

[0249] Step 7: Enter sales data

[0250] Users upload past sales and campaign data into the system.

[0251] Step 8: Receiving and storing sales data

[0252] A server receives sales data uploaded by users.

[0253] The server stores the received data in a database.

[0254] Step 9: Generate execution models

[0255] The server analyzes the sales data and builds a sales strategy model.

[0256] The server uses the generated AI model to automatically generate optimal sales strategies.

[0257] Step 10: Run the simulation

[0258] The server simulates the effect of the automatically generated sales measures.

[0259] The server organizes the simulation results.

[0260] Step 11: Providing simulation results

[0261] The server displays the simulation results on a dashboard for the user.

[0262] Improved prediction accuracy through self-learning

[0263] Step 12: Enter new data

[0264] Users periodically upload the latest shipping and sales data to the system.

[0265] Step 13: Receive and store the latest data

[0266] The server receives the latest data and stores it in storage.

[0267] The server adds and saves the received data to the database.

[0268] Step 14: Retrain the model

[0269] The server retrains the existing predictive model using the latest data.

[0270] The server verifies the accuracy of the retrained model.

[0271] Step 15: Providing improved prediction results

[0272] The server uses the retrained model to make new predictions and generate improved prediction results.

[0273] The server provides the new prediction results to the user and displays them on a dashboard.

[0274] Incorporating an emotion engine

[0275] Step 16: Obtaining Emotion Data

[0276] The device (e.g., camera or microphone) captures the user's facial expression and voice data.

[0277] The emotion data acquired by the device is sent to the server in real time.

[0278] Step 17: Analyze the emotion data

[0279] The server uses an emotion engine to analyze the transmitted emotion data and recognize the user's emotional state.

[0280] Step 18: Adjust the display

[0281] The server adjusts how the prediction results are displayed based on the recognized user emotion.

[0282] The server makes adjustments such as simplifying and displaying prediction results when the user is feeling stressed.

[0283] Step 19: Adjust your sales strategy

[0284] The server adjusts the optimal sales strategy proposals based on the emotional data.

[0285] The server makes adjustments, such as prioritizing sales strategies with low risk.

[0286] Step 20: Feedback to the predictive model

[0287] The server uses the user's emotion data recognized by the emotion engine to retrain the prediction model.

[0288] The server makes new predictions with the retrained model, continually improving its accuracy.

[0289] This enables the system to take user emotions into account to provide more accurate and user-friendly shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[0290] Example 2

[0291] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0292] While conventional logistics and sales forecasting systems can perform predictions based on shipping and sales data, they are often not optimized to take user emotions into account. This can lead to users feeling stressed or being unable to properly understand the information, potentially resulting in reduced work efficiency and incorrect decision-making. Furthermore, incorporating emotion engine functionality is expected to improve user-friendliness in information provision and the accuracy of policy proposals, but implementation is not easy.

[0293] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for converting the prediction results into graphs or tables and providing them to the user, means for acquiring emotion data using an emotion engine that recognizes the user's emotions, and means for analyzing the emotion data and adjusting the display method of the prediction results depending on the user's state. This makes it possible to provide optimal information and propose sales measures that take the user's emotions into consideration.

[0294] "Historical Shipping Data" refers to information relating to the actual delivery or transportation of goods or materials within a specified period of time.

[0295] "Inventory data" refers to information about the quantity and types of products and goods currently stored in warehouses and stores.

[0296] "Sales Data" means information regarding the quantity and value of goods or services actually sold within a particular period of time.

[0297] "Database" refers to a collection of digital information that is organized, managed, and stored in a searchable and accessible format.

[0298] A "generative AI model" is a type of algorithm created using machine learning and deep learning techniques to analyze data and predict future behavior or states.

[0299] An "emotion engine" refers to a software or hardware system that recognizes and analyzes a user's emotional state from facial expressions, voice, etc.

[0300] "Emotion data" refers to information that expresses the user's emotional state as numerical values ​​or categories.

[0301] "Prediction results" refers to information that estimates future shipment volumes, sales trends, etc. based on the generated AI model.

[0302] "Sales tactics" refers to specific strategies and action plans for achieving sales and marketing goals.

[0303] "Simulation" refers to a method for predicting the outcomes of specific actions or events under hypothetical environments or conditions.

[0304] "Retraining" refers to the process of retraining a generative AI model with new data to improve its performance and accuracy.

[0305] The system of the present invention includes a means for inputting past shipping data, inventory data, and sales data, a means for receiving the data and storing it in a database, a means for making predictions using a generative AI model, a means for providing the prediction results to a user, a means for acquiring emotion data using an emotion engine, and a means for analyzing the emotion data and adjusting the display method.

[0306] First, the user uploads past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The terminal inputs this data via the user interface and sends it to the server. The server receives the data, saves it in storage, and then stores it in the database.

[0307] The server then trains a generative AI model based on the data stored in the database. Specific software used includes TensorFlow and PyTorch. Once the model is trained, the server predicts future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables using tools such as Matplotlib and displayed on the user dashboard.

[0308] The system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze the data. The user's emotion data is acquired through the device's camera and microphone, and technologies such as OpenCV and Google Cloud Speech-to-Text are used. The server receives this data, and the emotion engine analyzes it to determine the user's emotional state.

[0309] Once the user's emotional data is acquired, the server adjusts the way predictions are displayed depending on the user's emotional state. For example, if the user is stressed, the server may display simplified information or messages recommending specific actions. If the user is relaxed, the server may display detailed data and complex graphs.

[0310] The server then generates optimal sales strategies based on the prediction results. It uses rule engines such as ACT-R and RETE to consider emotional data and provide strategies suited to the user. The server then simulates these strategies and provides the results to the user in a detailed report.

[0311] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data, and also uses user emotion data recognized by the emotion engine to improve prediction accuracy.

[0312] As a specific example, the prompt text is entered as follows: "Please upload your shipping data, inventory data, and sales data for the past five years. The system will then generate a shipping quantity forecast and display it on a dashboard. It will also adjust the way the information is displayed based on the user's emotional state and suggest optimal sales strategies."

[0313] As described above, the system of the present invention performs a comprehensive process from data input to prediction, emotion recognition, optimal policy proposals, and self-learning, thereby enabling user-friendly and highly accurate shipping forecasts and sales policy proposals, thereby supporting the efficient operation of logistics centers and warehouses.

[0314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0315] Step 1:

[0316] Users upload past shipping data, inventory data, and sales data to the system.

[0317] The user opens the system's data entry screen from their terminal, clicks the "Data Upload" button, selects the target CSV or Excel file, and clicks "Upload."

[0318] Input: CSV or Excel file of 2022 shipping, inventory, and sales data.

[0319] Output: The data file sent to the server.

[0320] Step 2:

[0321] The server receives the uploaded data files and processes them for storage in a database.

[0322] After receiving the data files, the server classifies each data item into "shipping data," "inventory data," and "sales data," and temporarily stores it in storage. It then organizes and stores the data in a database.

[0323] Input: Data file received from user.

[0324] Output: Organized data stored in a database.

[0325] Step 3:

[0326] The server performs preprocessing to train the generative AI model based on the data stored in the database.

[0327] The server retrieves the necessary data from the database, cleans the data, imputes missing values, and normalizes it.

[0328] Input: Shipping data, inventory data, sales data in the database.

[0329] Output: The preprocessed dataset.

[0330] Step 4:

[0331] The server trains the generative AI model.

[0332] The server uses the preprocessed data to train an AI model using a machine learning framework (e.g., TensorFlow or PyTorch).

[0333] Input: The preprocessed dataset.

[0334] Output: A trained generative AI model.

[0335] Step 5:

[0336] Use a trained generative AI model to predict future shipment quantities.

[0337] Based on the newly acquired data, the server inputs it into a forecasting model to predict future shipment quantities.

[0338] Input: A trained generative AI model and data for the time period you want to predict.

[0339] Output: Forecast results of future shipment quantities.

[0340] Step 6:

[0341] The prediction results are converted into graphs and tables and displayed on the user's dashboard.

[0342] The server visualizes the prediction results using libraries such as Matplotlib and D3.js and displays them on a dashboard in real time.

[0343] Input: Prediction results.

[0344] Output: Graphs and tables on a dashboard.

[0345] Step 7:

[0346] Emotion data is acquired using an emotion engine that recognizes the user's emotions.

[0347] The user's facial expressions and voice are captured through the camera and microphone installed on the device, and emotion data is generated using OpenCV, Google Cloud Speech-to-Text, etc.

[0348] Input: User's facial expression images and voice data.

[0349] Output: Emotion data.

[0350] Step 8:

[0351] The server analyzes the emotion data and adjusts the display method according to the user's state.

[0352] The server analyzes the emotional data received from the emotion engine and dynamically adjusts the way prediction results are displayed based on the user's mental state. For example, if stress is detected, the information displayed will be simplified.

[0353] Input: Emotion data.

[0354] Output: Adjusted dashboard display.

[0355] Step 9:

[0356] The server generates optimal sales strategies based on the prediction results and takes into account emotional data.

[0357] The server generates sales strategies based on the generated predictions and optimizes them using emotional data, using rule engines such as ACT-R and RETE.

[0358] Input: Prediction results, emotion data.

[0359] Output: Optimized sales execution.

[0360] Step 10:

[0361] The server simulates the effects of the sales measures and provides the results to the user.

[0362] The server uses a simulation engine to evaluate the hypothetical effects of the proposed sales measures and provides the results to the user in the form of a detailed report.

[0363] Input: Optimized merchandising.

[0364] Output: Report of simulation results.

[0365] Step 11:

[0366] Users periodically upload new shipping and sales data to the system, which the server receives and updates the database.

[0367] Input: New shipping data, sales data.

[0368] Output: The updated database.

[0369] Step 12:

[0370] The server retrains the predictive model based on new data, including sentiment data.

[0371] Input: The updated database.

[0372] Output: A retrained generative AI model and improved prediction results.

[0373] Through the above steps, the system of the present invention realizes user-friendly and highly accurate shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[0374] (Application example 2)

[0375] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0376] Conventional shipping forecasting systems only make predictions based on past data and are unable to consider the user's emotional state. This can make it difficult for users to understand the prediction results, and can result in insufficient proposals for appropriate sales strategies. Furthermore, it is difficult to provide customized customer service and product proposals in response to customer emotions in physical stores, which can hinder the system's ability to improve customer satisfaction.

[0377] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for analyzing the data using an emotion engine that recognizes the user's emotions, means for generating and providing the prediction results to the user, and means for adjusting the display method of the prediction results based on the user's emotions. This makes it easier to understand the prediction results and makes it possible to propose optimal sales measures based on the user's emotional state. Furthermore, in physical stores, customized customer service and product suggestions based on customer emotions can be provided, improving customer satisfaction.

[0378] "Past shipping data" refers to information about shipments that the system has recorded in the past.

[0379] "Inventory data" is information describing current and past inventory status.

[0380] "Sales data" refers to information relating to sales, such as product sales records and customer information.

[0381] "Means of input" refers to the interface or method by which a user provides data to the system.

[0382] "Means for receiving data and storing it in a database" refers to the method or infrastructure by which the system receives input data and stores it in a database.

[0383] A "generative AI model" is an artificial intelligence model designed to make predictions and judgments based on large amounts of data.

[0384] A "means of forecasting" is a method or process for calculating future shipment quantities, etc. based on input data.

[0385] An "emotion engine" is a technology or algorithm that analyzes a user's facial expressions and voice and recognizes their emotions.

[0386] "Analytical tools" are methods and tools used to analyze data and information and find meaning.

[0387] The "means for generating a prediction result and providing it to a user" refers to a method for creating predicted information and displaying or notifying it to a user.

[0388] The "means for adjusting the display method of the prediction result based on the emotion" is a method for changing the format and content of the information to be displayed depending on the emotional state of the user.

[0389] The "means for generating optimal sales measures" is a method for devising the most effective sales strategy based on prediction results and emotional data.

[0390] A "means for simulating the effectiveness of sales measures" is a method for estimating in advance how successful a proposed sales strategy will be.

[0391] "Means for providing simulation results to users" refers to processes and tools for presenting the results of the simulation to users.

[0392] "Means for retraining a predictive model based on new data" refers to a method for updating an existing predictive model using newly obtained data to improve its accuracy.

[0393] The "means for generating improved prediction results using a retrained prediction model" is a process for using an updated prediction model to derive more accurate prediction results.

[0394] This invention provides a customer service support system that responds to customer emotions in brick-and-mortar stores. The system includes a means for inputting past shipping data, inventory data, and sales data, and a means for receiving this data and storing it in a database. Each of these means and the operation of the system are described in detail below.

[0395] The server receives past shipping data, inventory data, and sales data and stores it in a database. Users provide this data by uploading it in CSV or Excel file format. The server receives the uploaded data and stores it in a database. This provides the basis for the data used in the next steps.

[0396] Next, the server uses a generative AI model to predict future shipment quantities from the data stored in the database. A large amount of past data is used to train the AI ​​model. The prediction results are displayed in graphs and tables on a dashboard and provided to the user. This predictive model is retrained each time new data is input, improving its prediction accuracy. The server manages this entire process.

[0397] The smart glasses are also equipped with an emotion engine that recognizes the user's emotions in real time. This emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses. The captured data is sent to a server and analyzed in real time. The analyzed emotion data is used to adjust the way prediction results are displayed based on the user's emotional state.

[0398] For example, if a salesperson wearing smart glasses analyzes a customer's emotional state and determines that the customer is feeling "stressed," the system can use that information to simplify product explanations or display messages to reassure the customer. If the customer is feeling "happy," a message suggesting an upsell product will be displayed.

[0399] Based on the analysis results of this emotion engine, the server also proposes optimal sales strategies. These proposals are adjusted taking into account the user's emotions, so if the user is feeling anxious, for example, the server will prioritize sales strategies with less risk.

[0400] Consider the following scenario as a concrete example: Customer A is shopping in a store. Salesperson B uses smart glasses to observe Customer A and analyzes his / her emotions from his / her facial expressions and voice. If Customer A is recognized as "happy," a "new product suggestion" will appear on the display of Salesperson B's glasses, and Salesperson B will suggest, "Please take a look at these new products."

[0401] Example prompt sentence:

[0402] "Implement a smart glasses application that analyzes customer emotions in real time and provides personalized product recommendations and customer service based on those emotions. If the customer is recognized as 'happy,' the glasses will display a message suggesting new products to the store clerk, who will then make the recommendation to the customer."

[0403] In this way, the present invention adjusts prediction results and sales strategies based on user emotions, thereby improving customer satisfaction in physical stores.

[0404] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0405] Step 1:

[0406] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format through the system's data input screen. The input data is used to forecast past shipments and improve the accuracy of the results. This data is sent from the user's device.

[0407] Step 2:

[0408] The server receives the data uploaded by the user and stores it in a database. The input data is used for subsequent data analysis and predictive model training. The database stores various data categories (shipment data, inventory data, sales data) appropriately.

[0409] Step 3:

[0410] The server trains the generative AI model using past shipping, inventory, and sales data stored in the database. During this process, the data is processed (for example, missing value completion, data standardization, etc.) for use as training data. Meaningful features are extracted from the input data and used to generate the AI ​​model.

[0411] Step 4:

[0412] Using the generative AI model, the server predicts future shipment quantities. New input data is fed into the model to obtain predictions. These predictions are then converted into graphs and tables.

[0413] Step 5:

[0414] The server provides the prediction results to the user, and displays them in an easy-to-understand dashboard for easy access by the user.

[0415] Step 6:

[0416] The emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses, and transmits this data to the server in real time. This data becomes input data for emotion recognition.

[0417] Step 7:

[0418] The server analyzes the acquired emotional data using an emotion engine. It identifies the user's emotional state using facial expression recognition algorithms and voice analysis algorithms. The analysis results (e.g., stress, joy, etc.) are obtained.

[0419] Step 8:

[0420] The server adjusts the way predictions are displayed based on the emotional data. For example, if the user is feeling stressed, it simplifies the prediction or displays a reassuring message. This information is reflected on the smart glasses display or the device screen.

[0421] Step 9:

[0422] The server generates optimal sales strategies based on the prediction results and emotion data. It then simulates the effectiveness of the generated sales strategies and provides the results to the user. The simulation also includes risk assessment and profit forecasting, providing the user with detailed analysis results.

[0423] Step 10:

[0424] Every time a user periodically uploads new shipping or sales data, the server updates the database with this data and retrains the predictive model. Emotional data is also incorporated into the retraining process to improve the accuracy of the predictive model. The prediction results provided to users are always highly accurate and based on the latest data.

[0425] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0426] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0427] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0428] [Second embodiment]

[0429] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0430] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0431] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0432] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0433] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0434] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0435] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0436] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0437] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0438] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0439] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0440] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0441] The system of the present invention begins when a logistics center or warehouse manager inputs past shipping data, inventory data, and sales data. This data is received by a server and stored in a database. The input data is then analyzed using a generative AI model to predict future shipping quantities. The prediction results are provided to the user.

[0442] Example 1: Data Entry

[0443] Users prepare shipping and inventory data from the past year and upload it to the system's data entry screen. Data can be entered in CSV or Excel format. For example, users can select and upload a file containing monthly shipping and inventory figures from January to December 2022.

[0444] Example 2: Data Receipt and Storage

[0445] The server receives files uploaded by users and stores them in storage. It then stores them in a database and centralizes the data. This allows past data to be efficiently organized and accessible at any time.

[0446] Example 3: Generating a predictive model

[0447] The server trains a generative AI model based on the received data. This process uses machine learning libraries such as TensorFlow and PyTorch. Once the training phase is complete, future shipment quantities are predicted. For example, the forecast shipment quantities for January to December 2023 are obtained.

[0448] Example 4: Providing prediction results

[0449] The server converts the forecast results into graphs and tables and provides them in an easy-to-understand format. Users can view these forecast results through the system's dashboard. This information can be used to make appropriate personnel allocation and inventory management.

[0450] Example 5: Proposal of optimal sales measures

[0451] The server also receives and analyzes past sales data. It uses a generative AI model to generate optimal sales strategies and simulate their effectiveness. For example, it proposes optimal discount rates and marketing strategies for promoting new products. These strategies are simulated and the results are provided to the user.

[0452] Example 6: Self-learning and accuracy improvement

[0453] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, you will get more accurate results than the first time.

[0454] As described above, the present invention is a system that enables efficient management of logistics centers and warehouses, and realizes optimization of shipping forecasts and sales strategies.

[0455] The processing flow will be explained below.

[0456] Generate shipment quantity forecasts

[0457] Step 1: Data entry

[0458] The user prepares past shipping data, inventory data, and sales data.

[0459] The user uploads past data in CSV or Excel file format from the system's data entry screen.

[0460] Step 2: Receiving and storing data

[0461] The server receives the uploaded file from the user.

[0462] The server stores the received data in temporary storage.

[0463] Step 3: Save the data to a database

[0464] The server reads the data stored in the storage and stores it in the database.

[0465] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[0466] Step 4: Generate a predictive model

[0467] The server retrieves the data stored in the database and performs preprocessing.

[0468] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[0469] Step 5: Run a prediction

[0470] The server uses the generated AI model to predict future shipment quantities.

[0471] The server retrieves and organizes the prediction results.

[0472] Step 6: Providing prediction results

[0473] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[0474] Proposing optimal sales strategies

[0475] Step 1: Enter your sales data

[0476] Users upload past sales and campaign data into the system.

[0477] Step 2: Receiving and storing sales data

[0478] A server receives sales data uploaded by users.

[0479] The server stores the received data in a database.

[0480] Step 3: Generate a sales execution model

[0481] The server analyzes the sales data and builds a sales strategy model.

[0482] The server uses the generated AI model to automatically generate optimal sales strategies.

[0483] Step 4: Run the simulation

[0484] The server simulates the effect of the automatically generated sales measures.

[0485] The server organizes the simulation results.

[0486] Step 5: Providing simulation results

[0487] The server displays the simulation results on a dashboard for the user.

[0488] Improved prediction accuracy through self-learning

[0489] Step 1: Enter new data

[0490] Users periodically upload the latest shipping and sales data to the system.

[0491] Step 2: Receive and store the latest data

[0492] The server receives the latest data and stores it in storage.

[0493] The server adds and saves the received data to the database.

[0494] Step 3: Retrain the model

[0495] The server retrains the existing predictive model using the latest data.

[0496] The server verifies the accuracy of the retrained model.

[0497] Step 4: Providing improved prediction results

[0498] The server uses the retrained model to make new predictions and generate improved prediction results.

[0499] The server provides the new prediction results to the user and displays them on a dashboard.

[0500] Through these processing steps, the system achieves highly accurate shipping forecasts and proposes optimal sales strategies, supporting the efficiency and optimization of logistics.

[0501] Example 1

[0502] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0503] Logistics centers and warehouses require highly accurate predictions of future shipment quantities and sales strategies based on past shipping, inventory, and sales data. However, previous systems did not centralize data management or improve prediction accuracy sufficiently, making it difficult to efficiently manage inventory and optimize sales strategies. Another challenge was continually improving the accuracy of prediction models by utilizing new data.

[0504] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0505] In this invention, the server includes a means for a user to input past data, a means for receiving the data, storing the data in a database, and centrally managing the data, a means for predicting future shipment quantities from the input data using a generative AI model, and a means for visualizing the prediction results and providing them to the user. This enables efficient data management and highly accurate shipment quantity predictions. The system also includes a means for generating optimal measures based on predictions made using the generative AI model and simulating their effects, thereby optimizing sales measures. Furthermore, the accuracy of predictions can be continuously improved by periodically inputting new data to update the database and retraining the prediction model.

[0506] "Historical data" refers to previous shipping data, inventory data, and sales data collected at distribution centers and warehouses.

[0507] "Users" refer to managers of logistics centers and warehouses who operate the system, input data, and utilize the prediction results.

[0508] "Database" refers to an information storage system for organizing and centrally managing received data.

[0509] A "generative AI model" refers to an artificial intelligence model that uses past data to predict future shipment volumes and optimal sales strategies.

[0510] "Visualization" refers to the process of converting prediction results into graphs, tables, or other formats and presenting them in a way that is easy for users to understand.

[0511] "Measures" refer to specific strategies and measures for formulating optimal action plans based on the prediction results.

[0512] "Simulation" refers to the process of estimating the effects of new measures in advance and verifying them on a trial basis.

[0513] "Retraining" refers to the training process of updating a generative AI model with new data to improve its predictive accuracy.

[0514] "Efficient data management" means quickly organizing and storing incoming data so that it remains easily accessible when needed.

[0515] "Prediction accuracy" refers to an indicator of how accurately a generative AI model can predict future shipment volumes and the effectiveness of sales strategies.

[0516] The system of the present invention is designed to enable managers of logistics centers and warehouses to efficiently forecast and optimize shipping quantities and sales strategies. This system is implemented in the following manner.

[0517] First, the user prepares shipping and inventory data for the past year and uploads it from the system's data input screen. This data is entered in CSV or Excel format. For example, an Excel file containing monthly shipping and inventory quantities from January to December 2022 can be selected and uploaded. An example of a specific prompt is, "Please upload shipping data for the past year (e.g., Excel file from January to December 2022)."

[0518] Next, the terminal sends the file selected by the user to the system. The server receives the file and saves it in storage. It then stores it in a database for centralized data management. For example, validation processing is performed to detect missing values ​​and outliers.

[0519] The server trains a generative AI model based on the received shipping and inventory data. This process uses machine learning libraries such as TensorFlow and PyTorch. The server performs feature engineering based on past data and converts the data into a form that can be input to the model. Once the training phase is complete, future shipping quantities are predicted. For example, shipping quantities from January to December 2023 are predicted.

[0520] Furthermore, the server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). Users can view these prediction results by opening the system's dashboard. The server also provides a function to update the dashboard in real time. An example of a specific prompt is "Please open the dashboard to check the prediction results."

[0521] In addition, the server analyzes past sales data and generates optimal sales measures using a generative AI model. A function to simulate the effects of these measures is also provided, and the optimal discount rate and marketing strategy for promoting new products are proposed. These proposals are provided to users via the dashboard. An example of a specific prompt is, "Please propose the optimal discount rate for promoting new products."

[0522] Finally, users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, the accuracy will be better than the first forecast.

[0523] Through the above steps, this system enables efficient management of logistics centers and warehouses, and realizes the optimization of shipping forecasts and sales strategies.

[0524] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0525] Step 1: The user uploads shipping and inventory data from the past year to the system's data input screen. The input is in CSV or Excel format, and includes files recording monthly shipping and inventory quantities from January to December 2022. The terminal sends these files to the system, where they are received by the server.

[0526] Step 2: The server saves the file received from the user in storage. The contents of this file are then stored in a database for centralized management. When the data is stored in the database, a validation process is performed to detect missing values ​​and outliers. The output of this stage is the data correctly stored and organized in the database.

[0527] Step 3: The server retrieves past shipping and inventory data from the database and uses this data to train a generative AI model. Specifically, training is performed using machine learning libraries such as TensorFlow and PyTorch. Feature engineering is performed based on the past data, and the data is converted into a form that can be input into the model. Future shipping quantities are predicted using the input past data and the AI ​​model. The output of this stage is predicted future shipping data.

[0528] Step 4: The server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). The user can then open the system's dashboard to view the prediction results. The dashboard displays the prediction results updated in real time. As an output, the prediction results are provided to the user in a visually easy-to-understand format.

[0529] Step 5: The server analyzes past sales data and generates optimal sales measures using a generative AI model. Specifically, the model proposes optimal discount rates and marketing strategies for promoting new products. The server then simulates the effects of these measures and provides them to the user. The user can use this as a reference to actually implement the measures. The output includes the simulation results and the proposed measures.

[0530] Step 6: Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data. The retrained predictive model can generate more accurate predictions. Finally, the predictions made by the retrained model are provided to the user. The output includes the improved predictions based on the retrained model.

[0531] (Application example 1)

[0532] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0533] To improve the accuracy of shipping forecasts and inventory management at logistics centers and warehouses, it is important not only to make forecasts based on past data, but also to quickly input data on-site and obtain real-time information. However, with conventional systems, data input was time-consuming and manual, and there were limited ways to check forecast results and sales measures in real time. This made it difficult to operate efficiently and plan optimal sales measures.

[0534] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0535] In this invention, the server includes: a means for inputting past shipping data, inventory data, and sales data; a means for receiving the data and storing it in a database; a means for predicting future shipping quantities from the input data using a generative AI model; a means for generating the prediction results and providing them to the user; a means for checking shipping prediction data in real time using a smart device; and a means for photographing past shipping and inventory data and inputting the data using OCR technology. This allows for quick and efficient data entry and confirmation of prediction results, enabling more efficient operation of logistics centers and warehouses and optimized inventory management. It also enables the planning and simulation of sales strategies based on the improved prediction results produced by the generative AI model.

[0536] "Past shipping data" refers to data that includes specific quantities, dates and times, and product information regarding shipments that have been made in advance.

[0537] "Inventory data" refers to data that indicates the quantity, type, and contents of products stored in warehouses and logistics centers.

[0538] "Sales data" refers to data that includes specific information regarding the sales quantity, sales destination, sales period, and sales amount of a product.

[0539] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze past data and generate future trends and predictions.

[0540] A "smart device" is a portable electronic device that can connect to the Internet, such as a smartphone or smart glasses.

[0541] "OCR technology" refers to optical character recognition technology, which extracts and digitizes character information from image data.

[0542] A "prompt" is a written instruction or question that is input to a generative AI model, and the AI ​​responds or analyzes based on this.

[0543] The system for realizing this invention is designed for efficient management in logistics centers and warehouses. A specific embodiment of this system is described below.

[0544] System Configuration

[0545] Hardware

[0546] Server: Receives, stores, analyzes data, and performs training and prediction processing for generated AI models. Examples include database servers and GPU servers for machine learning.

[0547] Smart devices: Smartphones and smart glasses are used to assist users in inputting and verifying data.

[0548] Camera: Cameras built into smartphones and smart glasses are used to capture inventory and shipping data.

[0549] software

[0550] Database: Used to centrally manage received data. Examples include MySQL and PostgreSQL.

[0551] Generative AI model: An AI model generated using TensorFlow and PyTorch that predicts future shipment quantities based on past data.

[0552] OCR technology: Optical character recognition technology is used to extract text information from image data. For example, Google Cloud Vision API is used.

[0553] Web application: Using frameworks such as Streamlit, we provide users with an interface that visualizes prediction results and sales strategies.

[0554] Detailed System Operation

[0555] The server provides a means to input past shipping data, inventory data, and sales data. Users can upload this data in the form of CSV files or photographed images and enter it into the system. Data can be easily entered from the field using a smart device.

[0556] The server then receives the uploaded data and stores it in a database, where it uses OCR technology to extract text information from the image data and store it as structured data.

[0557] The server uses a generative AI model based on the received data to predict future shipping quantities, which will improve the efficiency of future shipping and inventory management. The prediction results can be viewed in real time via smart devices and are provided to users in graph and table format.

[0558] Furthermore, the server generates optimal sales strategies based on the prediction results and simulates their effectiveness. Users can obtain these strategies in real time through the voice assistant of their smart device and check important information.

[0559] Specific examples

[0560] When a user says to the smart glasses, "I would like to check the shipment forecast data for March 2023," the voice assistant will provide a real-time shipment forecast.

[0561] Simply tap the "Upload inventory data" button on your smartphone and use the camera to take a photo of your inventory list. OCR technology will automatically convert the data into text and upload it to the system.

[0562] Prompt Sentence Examples

[0563] "Please upload shipping data for the past year."

[0564] "Generate a shipping forecast for the next month."

[0565] "Please show me the results of the sales strategy simulation."

[0566] This system will significantly improve the efficiency of shipping forecasts and inventory management at logistics centers and warehouses, enabling real-time information acquisition and policy planning.

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

[0568] Step 1:

[0569] The server provides a means for users to input past shipping data, inventory data, and sales data. Users can input data using their smart devices and upload data in CSV files or image format. The input data is converted into a format that can be saved in the database.

[0570] Input: CSV file, image data

[0571] Output: Converted data that can be saved in a database

[0572] Specific operation: The user takes a photo of the inventory list using their smartphone and uploads it to the system.

[0573] Step 2:

[0574] The server receives the uploaded data and stores it in a database. Using OCR technology, text information is extracted from the image data and stored as structured data. The data is then centrally managed with correlation.

[0575] Input: Converted data in input format

[0576] Output: Data converted to text, stored in a database

[0577] Specific operation: The server uses Google Cloud Vision API or similar to extract and save text information from image data.

[0578] Step 3:

[0579] The server trains a generative AI model based on the received data. The trained model is used to predict future shipment quantities. The generative AI model is built using TensorFlow and PyTorch to analyze the data.

[0580] Input: Structured data

[0581] Output: A trained generative AI model

[0582] Specific operation: The server launches TensorFlow and trains an AI model using the received data.

[0583] Step 4:

[0584] The server uses the trained generative AI model to predict future shipment quantities, and the results are converted into a format that users can view and provided via their smart devices, displayed in graphs and tables.

[0585] Input: Trained generative AI model, data needed to predict future shipments

[0586] Output: Shipping quantity forecast result

[0587] Specific operation: The prediction results are converted into graphs and tables and displayed on the user's smart device.

[0588] Step 5:

[0589] The server generates optimal sales strategies based on the prediction results and simulates their effectiveness. The simulation results are provided to the user in real time via the voice assistant.

[0590] Input: Forecast results, past sales data

[0591] Output: Sales strategies, simulation results

[0592] What it does: The voice assistant responds to user prompts and presents simulation results.

[0593] Step 6:

[0594] Users periodically input new shipping and sales data, which the server receives and updates the database, retraining the generative AI model and providing improved prediction results.

[0595] Input: New shipping data, sales data

[0596] Output: Updated database, improved prediction results

[0597] How it works: Users periodically upload data, and the server automatically updates and retrains the database.

[0598] Step 7:

[0599] The server responds in real time by providing the necessary data in response to prompts from the user. Examples of prompts include "Generate a shipping forecast for the next month" and "Display the results of a sales strategy simulation."

[0600] Input: prompt statement

[0601] Output: Real-time data, forecast data, simulation results

[0602] Specific behavior: The server parses the prompt, performs the necessary processing, and provides the answer to the user.

[0603] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0604] The system of the present invention incorporates a means for inputting past shipping data, inventory data, and sales data, as well as an emotion engine that recognizes the user's emotions, making it possible to provide information and propose sales measures that are more optimized for the user.

[0605] Example 1: Data entry and reception

[0606] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The server receives this data, saves it in storage, and then stores it in the database.

[0607] Example 2: Predictive model generation and prediction

[0608] The server trains a generative AI model based on the data stored in the database. Once trained, the model is used to predict future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables and displayed on a dashboard.

[0609] Example 3: Incorporating an Emotion Engine

[0610] The system is equipped with an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze that data. For example, it can obtain user emotion data through a camera or microphone.

[0611] Example 4: Adjusting display methods based on emotions

[0612] The server receives emotion data from the emotion engine and adjusts the display of prediction results depending on the user's state. For example, if the user is feeling stressed, the server may simplify the prediction results or display a message recommending a specific action.

[0613] Example 5: Proposal of optimal sales measures

[0614] The server generates optimal sales strategies based on the prediction results, taking into account emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will prioritize suggesting sales strategies with low risk. It also simulates the effects of the proposed sales strategies and provides the results to the user.

[0615] Example 6: Self-learning and accuracy improvement

[0616] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. By retraining the predictive model based on the new data, prediction accuracy is continuously improved. User emotion data recognized by the emotion engine is also used for retraining.

[0617] Specific examples

[0618] 1. Data Entry:

[0619] Users upload shipping, inventory, and sales data for 2022 into the system.

[0620] 2. Receiving and storing data:

[0621] The server receives the data and stores it in a database.

[0622] 3. Generate predictive models:

[0623] The server trains a generative AI model to predict shipment volumes for 2023.

[0624] 4. Use of Emotion Engine:

[0625] When a user operates the system, the emotion engine analyzes the user's facial expressions and voice to recognize emotions such as stress or joy.

[0626] 5. Adjust the display:

[0627] The server detects from the emotion data that the user is feeling stressed and simplifies the display content to make it easier to understand.

[0628] 6. Sales strategy proposal:

[0629] The server takes into account emotional data and prioritizes safe sales strategies.

[0630] 7. Self-learning and accuracy improvement:

[0631] Users upload their latest data, and the server uses that data to retrain the predictive model, also leveraging feedback from the emotion engine.

[0632] As described above, the system of the present invention realizes more accurate and user-friendly shipping forecasts and sales strategy proposals, and supports the efficient operation of logistics centers and warehouses.

[0633] The processing flow will be explained below.

[0634] Generate shipment volume forecasts and incorporate sentiment engines

[0635] Step 1: Data entry

[0636] The user prepares past shipping data, inventory data, and sales data.

[0637] Users upload this data in CSV or Excel file format through the system's data entry screen.

[0638] Step 2: Receiving and storing data

[0639] The server receives the uploaded file from the user.

[0640] The server stores the received data in temporary storage.

[0641] Step 3: Save the data to a database

[0642] The server reads the data stored in the storage and stores it in the database.

[0643] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[0644] Step 4: Generate a predictive model

[0645] The server retrieves the data stored in the database and performs preprocessing.

[0646] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[0647] Step 5: Run a prediction

[0648] The server uses the generated AI model to predict future shipment quantities.

[0649] The server retrieves and organizes the prediction results.

[0650] Step 6: Providing prediction results

[0651] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[0652] Proposing optimal sales strategies

[0653] Step 7: Enter sales data

[0654] Users upload past sales and campaign data into the system.

[0655] Step 8: Receiving and storing sales data

[0656] A server receives sales data uploaded by users.

[0657] The server stores the received data in a database.

[0658] Step 9: Generate execution models

[0659] The server analyzes the sales data and builds a sales strategy model.

[0660] The server uses the generated AI model to automatically generate optimal sales strategies.

[0661] Step 10: Run the simulation

[0662] The server simulates the effect of the automatically generated sales measures.

[0663] The server organizes the simulation results.

[0664] Step 11: Providing simulation results

[0665] The server displays the simulation results on a dashboard for the user.

[0666] Improved prediction accuracy through self-learning

[0667] Step 12: Enter new data

[0668] Users periodically upload the latest shipping and sales data to the system.

[0669] Step 13: Receive and store the latest data

[0670] The server receives the latest data and stores it in storage.

[0671] The server adds and saves the received data to the database.

[0672] Step 14: Retrain the model

[0673] The server retrains the existing predictive model using the latest data.

[0674] The server verifies the accuracy of the retrained model.

[0675] Step 15: Providing improved prediction results

[0676] The server uses the retrained model to make new predictions and generate improved prediction results.

[0677] The server provides the new prediction results to the user and displays them on a dashboard.

[0678] Incorporating an emotion engine

[0679] Step 16: Obtaining Emotion Data

[0680] The device (e.g., camera or microphone) captures the user's facial expression and voice data.

[0681] The emotion data acquired by the device is sent to the server in real time.

[0682] Step 17: Analyze the emotion data

[0683] The server uses an emotion engine to analyze the transmitted emotion data and recognize the user's emotional state.

[0684] Step 18: Adjust the display

[0685] The server adjusts how the prediction results are displayed based on the recognized user emotion.

[0686] The server makes adjustments such as simplifying and displaying prediction results when the user is feeling stressed.

[0687] Step 19: Adjust your sales strategy

[0688] The server adjusts the optimal sales strategy proposals based on the emotional data.

[0689] The server makes adjustments, such as prioritizing sales strategies with low risk.

[0690] Step 20: Feedback to the predictive model

[0691] The server uses the user's emotion data recognized by the emotion engine to retrain the prediction model.

[0692] The server makes new predictions with the retrained model, continually improving its accuracy.

[0693] This enables the system to take user emotions into account to provide more accurate and user-friendly shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[0694] Example 2

[0695] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0696] While conventional logistics and sales forecasting systems can perform predictions based on shipping and sales data, they are often not optimized to take user emotions into account. This can lead to users feeling stressed or being unable to properly understand the information, potentially resulting in reduced work efficiency and incorrect decision-making. Furthermore, incorporating emotion engine functionality is expected to improve user-friendliness in information provision and the accuracy of policy proposals, but implementation is not easy.

[0697] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for converting the prediction results into graphs or tables and providing them to the user, means for acquiring emotion data using an emotion engine that recognizes the user's emotions, and means for analyzing the emotion data and adjusting the display method of the prediction results depending on the user's state. This makes it possible to provide optimal information and propose sales measures that take the user's emotions into consideration.

[0698] "Historical Shipping Data" refers to information relating to the actual delivery or transportation of goods or materials within a specified period of time.

[0699] "Inventory data" refers to information about the quantity and types of products and goods currently stored in warehouses and stores.

[0700] "Sales Data" means information regarding the quantity and value of goods or services actually sold within a particular period of time.

[0701] "Database" refers to a collection of digital information that is organized, managed, and stored in a searchable and accessible format.

[0702] A "generative AI model" is a type of algorithm created using machine learning and deep learning techniques to analyze data and predict future behavior or states.

[0703] An "emotion engine" refers to a software or hardware system that recognizes and analyzes a user's emotional state from facial expressions, voice, etc.

[0704] "Emotion data" refers to information that expresses the user's emotional state as numerical values ​​or categories.

[0705] "Prediction results" refers to information that estimates future shipment volumes, sales trends, etc. based on the generated AI model.

[0706] "Sales tactics" refers to specific strategies and action plans for achieving sales and marketing goals.

[0707] "Simulation" refers to a method for predicting the outcomes of specific actions or events under hypothetical environments or conditions.

[0708] "Retraining" refers to the process of retraining a generative AI model with new data to improve its performance and accuracy.

[0709] The system of the present invention includes a means for inputting past shipping data, inventory data, and sales data, a means for receiving the data and storing it in a database, a means for making predictions using a generative AI model, a means for providing the prediction results to a user, a means for acquiring emotion data using an emotion engine, and a means for analyzing the emotion data and adjusting the display method.

[0710] First, the user uploads past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The terminal inputs this data via the user interface and sends it to the server. The server receives the data, saves it in storage, and then stores it in the database.

[0711] The server then trains a generative AI model based on the data stored in the database. Specific software used includes TensorFlow and PyTorch. Once the model is trained, the server predicts future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables using tools such as Matplotlib and displayed on the user dashboard.

[0712] The system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze the data. The user's emotion data is acquired through the device's camera and microphone, and technologies such as OpenCV and Google Cloud Speech-to-Text are used. The server receives this data, and the emotion engine analyzes it to determine the user's emotional state.

[0713] Once the user's emotional data is acquired, the server adjusts the way predictions are displayed depending on the user's emotional state. For example, if the user is stressed, the server may display simplified information or messages recommending specific actions. If the user is relaxed, the server may display detailed data and complex graphs.

[0714] The server then generates optimal sales strategies based on the prediction results. It uses rule engines such as ACT-R and RETE to consider emotional data and provide strategies suited to the user. The server then simulates these strategies and provides the results to the user in a detailed report.

[0715] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data, and also uses user emotion data recognized by the emotion engine to improve prediction accuracy.

[0716] As a specific example, the prompt text is entered as follows: "Please upload your shipping data, inventory data, and sales data for the past five years. The system will then generate a shipping quantity forecast and display it on a dashboard. It will also adjust the way the information is displayed based on the user's emotional state and suggest optimal sales strategies."

[0717] As described above, the system of the present invention performs a comprehensive process from data input to prediction, emotion recognition, optimal policy proposals, and self-learning, thereby enabling user-friendly and highly accurate shipping forecasts and sales policy proposals, thereby supporting the efficient operation of logistics centers and warehouses.

[0718] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0719] Step 1:

[0720] Users upload past shipping data, inventory data, and sales data to the system.

[0721] The user opens the system's data entry screen from their terminal, clicks the "Data Upload" button, selects the target CSV or Excel file, and clicks "Upload."

[0722] Input: CSV or Excel file of 2022 shipping, inventory, and sales data.

[0723] Output: The data file sent to the server.

[0724] Step 2:

[0725] The server receives the uploaded data files and processes them for storage in a database.

[0726] After receiving the data files, the server classifies each data item into "shipping data," "inventory data," and "sales data," and temporarily stores it in storage. It then organizes and stores the data in a database.

[0727] Input: Data file received from user.

[0728] Output: Organized data stored in a database.

[0729] Step 3:

[0730] The server performs preprocessing to train the generative AI model based on the data stored in the database.

[0731] The server retrieves the necessary data from the database, cleans the data, imputes missing values, and normalizes it.

[0732] Input: Shipping data, inventory data, sales data in the database.

[0733] Output: The preprocessed dataset.

[0734] Step 4:

[0735] The server trains the generative AI model.

[0736] The server uses the preprocessed data to train an AI model using a machine learning framework (e.g., TensorFlow or PyTorch).

[0737] Input: The preprocessed dataset.

[0738] Output: A trained generative AI model.

[0739] Step 5:

[0740] Use a trained generative AI model to predict future shipment quantities.

[0741] Based on the newly acquired data, the server inputs it into a forecasting model to predict future shipment quantities.

[0742] Input: A trained generative AI model and data for the time period you want to predict.

[0743] Output: Forecast results of future shipment quantities.

[0744] Step 6:

[0745] The prediction results are converted into graphs and tables and displayed on the user's dashboard.

[0746] The server visualizes the prediction results using libraries such as Matplotlib and D3.js and displays them on a dashboard in real time.

[0747] Input: Prediction results.

[0748] Output: Graphs and tables on a dashboard.

[0749] Step 7:

[0750] Emotion data is acquired using an emotion engine that recognizes the user's emotions.

[0751] The user's facial expressions and voice are captured through the camera and microphone installed on the device, and emotion data is generated using OpenCV, Google Cloud Speech-to-Text, etc.

[0752] Input: User's facial expression images and voice data.

[0753] Output: Emotion data.

[0754] Step 8:

[0755] The server analyzes the emotion data and adjusts the display method according to the user's state.

[0756] The server analyzes the emotional data received from the emotion engine and dynamically adjusts the way prediction results are displayed based on the user's mental state. For example, if stress is detected, the information displayed will be simplified.

[0757] Input: Emotion data.

[0758] Output: Adjusted dashboard display.

[0759] Step 9:

[0760] The server generates optimal sales strategies based on the prediction results and takes into account emotional data.

[0761] The server generates sales strategies based on the generated predictions and optimizes them using emotional data, using rule engines such as ACT-R and RETE.

[0762] Input: Prediction results, emotion data.

[0763] Output: Optimized sales execution.

[0764] Step 10:

[0765] The server simulates the effects of the sales measures and provides the results to the user.

[0766] The server uses a simulation engine to evaluate the hypothetical effects of the proposed sales measures and provides the results to the user in the form of a detailed report.

[0767] Input: Optimized merchandising.

[0768] Output: Report of simulation results.

[0769] Step 11:

[0770] Users periodically upload new shipping and sales data to the system, which the server receives and updates the database.

[0771] Input: New shipping data, sales data.

[0772] Output: The updated database.

[0773] Step 12:

[0774] The server retrains the predictive model based on new data, including sentiment data.

[0775] Input: The updated database.

[0776] Output: A retrained generative AI model and improved prediction results.

[0777] Through the above steps, the system of the present invention realizes user-friendly and highly accurate shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[0778] (Application example 2)

[0779] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0780] Conventional shipping forecasting systems only make predictions based on past data and are unable to consider the user's emotional state. This can make it difficult for users to understand the prediction results, and can result in insufficient proposals for appropriate sales strategies. Furthermore, it is difficult to provide customized customer service and product proposals in response to customer emotions in physical stores, which can hinder the system's ability to improve customer satisfaction.

[0781] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for analyzing the data using an emotion engine that recognizes the user's emotions, means for generating and providing the prediction results to the user, and means for adjusting the display method of the prediction results based on the user's emotions. This makes it easier to understand the prediction results and makes it possible to propose optimal sales measures based on the user's emotional state. Furthermore, in physical stores, customized customer service and product suggestions based on customer emotions can be provided, improving customer satisfaction.

[0782] "Past shipping data" refers to information about shipments that the system has recorded in the past.

[0783] "Inventory data" is information describing current and past inventory status.

[0784] "Sales data" refers to information relating to sales, such as product sales records and customer information.

[0785] "Means of input" refers to the interface or method by which a user provides data to the system.

[0786] "Means for receiving data and storing it in a database" refers to the method or infrastructure by which the system receives input data and stores it in a database.

[0787] A "generative AI model" is an artificial intelligence model designed to make predictions and judgments based on large amounts of data.

[0788] A "means of forecasting" is a method or process for calculating future shipment quantities, etc. based on input data.

[0789] An "emotion engine" is a technology or algorithm that analyzes a user's facial expressions and voice and recognizes their emotions.

[0790] "Analytical tools" are methods and tools used to analyze data and information and find meaning.

[0791] The "means for generating a prediction result and providing it to a user" refers to a method for creating predicted information and displaying or notifying it to a user.

[0792] The "means for adjusting the display method of the prediction result based on the emotion" is a method for changing the format and content of the information to be displayed depending on the emotional state of the user.

[0793] The "means for generating optimal sales measures" is a method for devising the most effective sales strategy based on prediction results and emotional data.

[0794] A "means for simulating the effectiveness of sales measures" is a method for estimating in advance how successful a proposed sales strategy will be.

[0795] "Means for providing simulation results to users" refers to processes and tools for presenting the results of the simulation to users.

[0796] "Means for retraining a predictive model based on new data" refers to a method for updating an existing predictive model using newly obtained data to improve its accuracy.

[0797] The "means for generating improved prediction results using a retrained prediction model" is a process for using an updated prediction model to derive more accurate prediction results.

[0798] This invention provides a customer service support system that responds to customer emotions in brick-and-mortar stores. The system includes a means for inputting past shipping data, inventory data, and sales data, and a means for receiving this data and storing it in a database. Each of these means and the operation of the system are described in detail below.

[0799] The server receives past shipping data, inventory data, and sales data and stores it in a database. Users provide this data by uploading it in CSV or Excel file format. The server receives the uploaded data and stores it in a database. This provides the basis for the data used in the next steps.

[0800] Next, the server uses a generative AI model to predict future shipment quantities from the data stored in the database. A large amount of past data is used to train the AI ​​model. The prediction results are displayed in graphs and tables on a dashboard and provided to the user. This predictive model is retrained each time new data is input, improving its prediction accuracy. The server manages this entire process.

[0801] The smart glasses are also equipped with an emotion engine that recognizes the user's emotions in real time. This emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses. The captured data is sent to a server and analyzed in real time. The analyzed emotion data is used to adjust the way prediction results are displayed based on the user's emotional state.

[0802] For example, if a salesperson wearing smart glasses analyzes a customer's emotional state and determines that the customer is feeling "stressed," the system can use that information to simplify product explanations or display messages to reassure the customer. If the customer is feeling "happy," a message suggesting an upsell product will be displayed.

[0803] Based on the analysis results of this emotion engine, the server also proposes optimal sales strategies. These proposals are adjusted taking into account the user's emotions, so if the user is feeling anxious, for example, the server will prioritize sales strategies with less risk.

[0804] Consider the following scenario as a concrete example: Customer A is shopping in a store. Salesperson B uses smart glasses to observe Customer A and analyzes his / her emotions from his / her facial expressions and voice. If Customer A is recognized as "happy," a "new product suggestion" will appear on the display of Salesperson B's glasses, and Salesperson B will suggest, "Please take a look at these new products."

[0805] Example prompt sentence:

[0806] "Implement a smart glasses application that analyzes customer emotions in real time and provides personalized product recommendations and customer service based on those emotions. If the customer is recognized as 'happy,' the glasses will display a message suggesting new products to the store clerk, who will then make the recommendation to the customer."

[0807] In this way, the present invention adjusts prediction results and sales strategies based on user emotions, thereby improving customer satisfaction in physical stores.

[0808] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0809] Step 1:

[0810] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format through the system's data input screen. The input data is used to forecast past shipments and improve the accuracy of the results. This data is sent from the user's device.

[0811] Step 2:

[0812] The server receives the data uploaded by the user and stores it in a database. The input data is used for subsequent data analysis and predictive model training. The database stores various data categories (shipment data, inventory data, sales data) appropriately.

[0813] Step 3:

[0814] The server trains the generative AI model using past shipping, inventory, and sales data stored in the database. During this process, the data is processed (for example, missing value completion, data standardization, etc.) for use as training data. Meaningful features are extracted from the input data and used to generate the AI ​​model.

[0815] Step 4:

[0816] Using the generative AI model, the server predicts future shipment quantities. New input data is fed into the model to obtain predictions. These predictions are then converted into graphs and tables.

[0817] Step 5:

[0818] The server provides the prediction results to the user, and displays them in an easy-to-understand dashboard for easy access by the user.

[0819] Step 6:

[0820] The emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses, and transmits this data to the server in real time. This data becomes input data for emotion recognition.

[0821] Step 7:

[0822] The server analyzes the acquired emotional data using an emotion engine. It identifies the user's emotional state using facial expression recognition algorithms and voice analysis algorithms. The analysis results (e.g., stress, joy, etc.) are obtained.

[0823] Step 8:

[0824] The server adjusts the way predictions are displayed based on the emotional data. For example, if the user is feeling stressed, it simplifies the prediction or displays a reassuring message. This information is reflected on the smart glasses display or the device screen.

[0825] Step 9:

[0826] The server generates optimal sales strategies based on the prediction results and emotion data. It then simulates the effectiveness of the generated sales strategies and provides the results to the user. The simulation also includes risk assessment and profit forecasting, providing the user with detailed analysis results.

[0827] Step 10:

[0828] Every time a user periodically uploads new shipping or sales data, the server updates the database with this data and retrains the predictive model. Emotional data is also incorporated into the retraining process to improve the accuracy of the predictive model. The prediction results provided to users are always highly accurate and based on the latest data.

[0829] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0830] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0831] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0832] [Third embodiment]

[0833] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0834] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0835] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0836] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0837] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0838] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0839] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0840] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0841] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0842] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0843] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0844] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0845] The system of the present invention begins when a logistics center or warehouse manager inputs past shipping data, inventory data, and sales data. This data is received by a server and stored in a database. The input data is then analyzed using a generative AI model to predict future shipping quantities. The prediction results are provided to the user.

[0846] Example 1: Data Entry

[0847] Users prepare shipping and inventory data from the past year and upload it to the system's data entry screen. Data can be entered in CSV or Excel format. For example, users can select and upload a file containing monthly shipping and inventory figures from January to December 2022.

[0848] Example 2: Data Receipt and Storage

[0849] The server receives files uploaded by users and stores them in storage. It then stores them in a database and centralizes the data. This allows past data to be efficiently organized and accessible at any time.

[0850] Example 3: Generating a predictive model

[0851] The server trains a generative AI model based on the received data. This process uses machine learning libraries such as TensorFlow and PyTorch. Once the training phase is complete, future shipment quantities are predicted. For example, the forecast shipment quantities for January to December 2023 are obtained.

[0852] Example 4: Providing prediction results

[0853] The server converts the forecast results into graphs and tables and provides them in an easy-to-understand format. Users can view these forecast results through the system's dashboard. This information can be used to make appropriate personnel allocation and inventory management.

[0854] Example 5: Proposal of optimal sales measures

[0855] The server also receives and analyzes past sales data. It uses a generative AI model to generate optimal sales strategies and simulate their effectiveness. For example, it proposes optimal discount rates and marketing strategies for promoting new products. These strategies are simulated and the results are provided to the user.

[0856] Example 6: Self-learning and accuracy improvement

[0857] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, you will get more accurate results than the first time.

[0858] As described above, the present invention is a system that enables efficient management of logistics centers and warehouses, and realizes optimization of shipping forecasts and sales strategies.

[0859] The processing flow will be explained below.

[0860] Generate shipment quantity forecasts

[0861] Step 1: Data entry

[0862] The user prepares past shipping data, inventory data, and sales data.

[0863] The user uploads past data in CSV or Excel file format from the system's data entry screen.

[0864] Step 2: Receiving and storing data

[0865] The server receives the uploaded file from the user.

[0866] The server stores the received data in temporary storage.

[0867] Step 3: Save the data to a database

[0868] The server reads the data stored in the storage and stores it in the database.

[0869] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[0870] Step 4: Generate a predictive model

[0871] The server retrieves the data stored in the database and performs preprocessing.

[0872] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[0873] Step 5: Run a prediction

[0874] The server uses the generated AI model to predict future shipment quantities.

[0875] The server retrieves and organizes the prediction results.

[0876] Step 6: Providing prediction results

[0877] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[0878] Proposing optimal sales strategies

[0879] Step 1: Enter your sales data

[0880] Users upload past sales and campaign data into the system.

[0881] Step 2: Receiving and storing sales data

[0882] A server receives sales data uploaded by users.

[0883] The server stores the received data in a database.

[0884] Step 3: Generate a sales execution model

[0885] The server analyzes the sales data and builds a sales strategy model.

[0886] The server uses the generated AI model to automatically generate optimal sales strategies.

[0887] Step 4: Run the simulation

[0888] The server simulates the effect of the automatically generated sales measures.

[0889] The server organizes the simulation results.

[0890] Step 5: Providing simulation results

[0891] The server displays the simulation results on a dashboard for the user.

[0892] Improved prediction accuracy through self-learning

[0893] Step 1: Enter new data

[0894] Users periodically upload the latest shipping and sales data to the system.

[0895] Step 2: Receive and store the latest data

[0896] The server receives the latest data and stores it in storage.

[0897] The server adds and saves the received data to the database.

[0898] Step 3: Retrain the model

[0899] The server retrains the existing predictive model using the latest data.

[0900] The server verifies the accuracy of the retrained model.

[0901] Step 4: Providing improved prediction results

[0902] The server uses the retrained model to make new predictions and generate improved prediction results.

[0903] The server provides the new prediction results to the user and displays them on a dashboard.

[0904] Through these processing steps, the system achieves highly accurate shipping forecasts and proposes optimal sales strategies, supporting the efficiency and optimization of logistics.

[0905] Example 1

[0906] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0907] Logistics centers and warehouses require highly accurate predictions of future shipment quantities and sales strategies based on past shipping, inventory, and sales data. However, previous systems did not centralize data management or improve prediction accuracy sufficiently, making it difficult to efficiently manage inventory and optimize sales strategies. Another challenge was continually improving the accuracy of prediction models by utilizing new data.

[0908] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0909] In this invention, the server includes a means for a user to input past data, a means for receiving the data, storing the data in a database, and centrally managing the data, a means for predicting future shipment quantities from the input data using a generative AI model, and a means for visualizing the prediction results and providing them to the user. This enables efficient data management and highly accurate shipment quantity predictions. The system also includes a means for generating optimal measures based on predictions made using the generative AI model and simulating their effects, thereby optimizing sales measures. Furthermore, the accuracy of predictions can be continuously improved by periodically inputting new data to update the database and retraining the prediction model.

[0910] "Historical data" refers to previous shipping data, inventory data, and sales data collected at distribution centers and warehouses.

[0911] "Users" refer to managers of logistics centers and warehouses who operate the system, input data, and utilize the prediction results.

[0912] "Database" refers to an information storage system for organizing and centrally managing received data.

[0913] A "generative AI model" refers to an artificial intelligence model that uses past data to predict future shipment volumes and optimal sales strategies.

[0914] "Visualization" refers to the process of converting prediction results into graphs, tables, or other formats and presenting them in a way that is easy for users to understand.

[0915] "Measures" refer to specific strategies and measures for formulating optimal action plans based on the prediction results.

[0916] "Simulation" refers to the process of estimating the effects of new measures in advance and verifying them on a trial basis.

[0917] "Retraining" refers to the training process of updating a generative AI model with new data to improve its predictive accuracy.

[0918] "Efficient data management" means quickly organizing and storing incoming data so that it remains easily accessible when needed.

[0919] "Prediction accuracy" refers to an indicator of how accurately a generative AI model can predict future shipment volumes and the effectiveness of sales strategies.

[0920] The system of the present invention is designed to enable managers of logistics centers and warehouses to efficiently forecast and optimize shipping quantities and sales strategies. This system is implemented in the following manner.

[0921] First, the user prepares shipping and inventory data for the past year and uploads it from the system's data input screen. This data is entered in CSV or Excel format. For example, an Excel file containing monthly shipping and inventory quantities from January to December 2022 can be selected and uploaded. An example of a specific prompt is, "Please upload shipping data for the past year (e.g., Excel file from January to December 2022)."

[0922] Next, the terminal sends the file selected by the user to the system. The server receives the file and saves it in storage. It then stores it in a database for centralized data management. For example, validation processing is performed to detect missing values ​​and outliers.

[0923] The server trains a generative AI model based on the received shipping and inventory data. This process uses machine learning libraries such as TensorFlow and PyTorch. The server performs feature engineering based on past data and converts the data into a form that can be input to the model. Once the training phase is complete, future shipping quantities are predicted. For example, shipping quantities from January to December 2023 are predicted.

[0924] Furthermore, the server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). Users can view these prediction results by opening the system's dashboard. The server also provides a function to update the dashboard in real time. An example of a specific prompt is "Please open the dashboard to check the prediction results."

[0925] In addition, the server analyzes past sales data and generates optimal sales measures using a generative AI model. A function to simulate the effects of these measures is also provided, and the optimal discount rate and marketing strategy for promoting new products are proposed. These proposals are provided to users via the dashboard. An example of a specific prompt is, "Please propose the optimal discount rate for promoting new products."

[0926] Finally, users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, the accuracy will be better than the first forecast.

[0927] Through the above steps, this system enables efficient management of logistics centers and warehouses, and realizes the optimization of shipping forecasts and sales strategies.

[0928] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0929] Step 1: The user uploads shipping and inventory data from the past year to the system's data input screen. The input is in CSV or Excel format, and includes files recording monthly shipping and inventory quantities from January to December 2022. The terminal sends these files to the system, where they are received by the server.

[0930] Step 2: The server saves the file received from the user in storage. The contents of this file are then stored in a database for centralized management. When the data is stored in the database, a validation process is performed to detect missing values ​​and outliers. The output of this stage is the data correctly stored and organized in the database.

[0931] Step 3: The server retrieves past shipping and inventory data from the database and uses this data to train a generative AI model. Specifically, training is performed using machine learning libraries such as TensorFlow and PyTorch. Feature engineering is performed based on the past data, and the data is converted into a form that can be input into the model. Future shipping quantities are predicted using the input past data and the AI ​​model. The output of this stage is predicted future shipping data.

[0932] Step 4: The server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). The user can then open the system's dashboard to view the prediction results. The dashboard displays the prediction results updated in real time. As an output, the prediction results are provided to the user in a visually easy-to-understand format.

[0933] Step 5: The server analyzes past sales data and generates optimal sales measures using a generative AI model. Specifically, the model proposes optimal discount rates and marketing strategies for promoting new products. The server then simulates the effects of these measures and provides them to the user. The user can use this as a reference to actually implement the measures. The output includes the simulation results and the proposed measures.

[0934] Step 6: Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data. The retrained predictive model can generate more accurate predictions. Finally, the predictions made by the retrained model are provided to the user. The output includes the improved predictions based on the retrained model.

[0935] (Application example 1)

[0936] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0937] To improve the accuracy of shipping forecasts and inventory management at logistics centers and warehouses, it is important not only to make forecasts based on past data, but also to quickly input data on-site and obtain real-time information. However, with conventional systems, data input was time-consuming and manual, and there were limited ways to check forecast results and sales measures in real time. This made it difficult to operate efficiently and plan optimal sales measures.

[0938] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0939] In this invention, the server includes: a means for inputting past shipping data, inventory data, and sales data; a means for receiving the data and storing it in a database; a means for predicting future shipping quantities from the input data using a generative AI model; a means for generating the prediction results and providing them to the user; a means for checking shipping prediction data in real time using a smart device; and a means for photographing past shipping and inventory data and inputting the data using OCR technology. This allows for quick and efficient data entry and confirmation of prediction results, enabling more efficient operation of logistics centers and warehouses and optimized inventory management. It also enables the planning and simulation of sales strategies based on the improved prediction results produced by the generative AI model.

[0940] "Past shipping data" refers to data that includes specific quantities, dates and times, and product information regarding shipments that have been made in advance.

[0941] "Inventory data" refers to data that indicates the quantity, type, and contents of products stored in warehouses and logistics centers.

[0942] "Sales data" refers to data that includes specific information regarding the sales quantity, sales destination, sales period, and sales amount of a product.

[0943] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze past data and generate future trends and predictions.

[0944] A "smart device" is a portable electronic device that can connect to the Internet, such as a smartphone or smart glasses.

[0945] "OCR technology" refers to optical character recognition technology, which extracts and digitizes character information from image data.

[0946] A "prompt" is a written instruction or question that is input to a generative AI model, and the AI ​​responds or analyzes based on this.

[0947] The system for realizing this invention is designed for efficient management in logistics centers and warehouses. A specific embodiment of this system is described below.

[0948] System Configuration

[0949] Hardware

[0950] Server: Receives, stores, analyzes data, and performs training and prediction processing for generated AI models. Examples include database servers and GPU servers for machine learning.

[0951] Smart devices: Smartphones and smart glasses are used to assist users in inputting and verifying data.

[0952] Camera: Cameras built into smartphones and smart glasses are used to capture inventory and shipping data.

[0953] software

[0954] Database: Used to centrally manage received data. Examples include MySQL and PostgreSQL.

[0955] Generative AI model: An AI model generated using TensorFlow and PyTorch that predicts future shipment quantities based on past data.

[0956] OCR technology: Optical character recognition technology is used to extract text information from image data. For example, Google Cloud Vision API is used.

[0957] Web application: Using frameworks such as Streamlit, we provide users with an interface that visualizes prediction results and sales strategies.

[0958] Detailed System Operation

[0959] The server provides a means to input past shipping data, inventory data, and sales data. Users can upload this data in the form of CSV files or photographed images and enter it into the system. Data can be easily entered from the field using a smart device.

[0960] The server then receives the uploaded data and stores it in a database, where it uses OCR technology to extract text information from the image data and store it as structured data.

[0961] The server uses a generative AI model based on the received data to predict future shipping quantities, which will improve the efficiency of future shipping and inventory management. The prediction results can be viewed in real time via smart devices and are provided to users in graph and table format.

[0962] Furthermore, the server generates optimal sales strategies based on the prediction results and simulates their effectiveness. Users can obtain these strategies in real time through the voice assistant of their smart device and check important information.

[0963] Specific examples

[0964] When a user says to the smart glasses, "I would like to check the shipment forecast data for March 2023," the voice assistant will provide a real-time shipment forecast.

[0965] Simply tap the "Upload inventory data" button on your smartphone and use the camera to take a photo of your inventory list. OCR technology will automatically convert the data into text and upload it to the system.

[0966] Prompt Sentence Examples

[0967] "Please upload shipping data for the past year."

[0968] "Generate a shipping forecast for the next month."

[0969] "Please show me the results of the sales strategy simulation."

[0970] This system will significantly improve the efficiency of shipping forecasts and inventory management at logistics centers and warehouses, enabling real-time information acquisition and policy planning.

[0971] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0972] Step 1:

[0973] The server provides a means for users to input past shipping data, inventory data, and sales data. Users can input data using their smart devices and upload data in CSV files or image format. The input data is converted into a format that can be saved in the database.

[0974] Input: CSV file, image data

[0975] Output: Converted data that can be saved in a database

[0976] Specific operation: The user takes a photo of the inventory list using their smartphone and uploads it to the system.

[0977] Step 2:

[0978] The server receives the uploaded data and stores it in a database. Using OCR technology, text information is extracted from the image data and stored as structured data. The data is then centrally managed with correlation.

[0979] Input: Converted data in input format

[0980] Output: Data converted to text, stored in a database

[0981] Specific operation: The server uses Google Cloud Vision API or similar to extract and save text information from image data.

[0982] Step 3:

[0983] The server trains a generative AI model based on the received data. The trained model is used to predict future shipment quantities. The generative AI model is built using TensorFlow and PyTorch to analyze the data.

[0984] Input: Structured data

[0985] Output: A trained generative AI model

[0986] Specific operation: The server launches TensorFlow and trains an AI model using the received data.

[0987] Step 4:

[0988] The server uses the trained generative AI model to predict future shipment quantities, and the results are converted into a format that users can view and provided via their smart devices, displayed in graphs and tables.

[0989] Input: Trained generative AI model, data needed to predict future shipments

[0990] Output: Shipping quantity forecast result

[0991] Specific operation: The prediction results are converted into graphs and tables and displayed on the user's smart device.

[0992] Step 5:

[0993] The server generates optimal sales strategies based on the prediction results and simulates their effectiveness. The simulation results are provided to the user in real time via the voice assistant.

[0994] Input: Forecast results, past sales data

[0995] Output: Sales strategies, simulation results

[0996] What it does: The voice assistant responds to user prompts and presents simulation results.

[0997] Step 6:

[0998] Users periodically input new shipping and sales data, which the server receives and updates the database, retraining the generative AI model and providing improved prediction results.

[0999] Input: New shipping data, sales data

[1000] Output: Updated database, improved prediction results

[1001] How it works: Users periodically upload data, and the server automatically updates and retrains the database.

[1002] Step 7:

[1003] The server responds in real time by providing the necessary data in response to prompts from the user. Examples of prompts include "Generate a shipping forecast for the next month" and "Display the results of a sales strategy simulation."

[1004] Input: prompt statement

[1005] Output: Real-time data, forecast data, simulation results

[1006] Specific behavior: The server parses the prompt, performs the necessary processing, and provides the answer to the user.

[1007] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1008] The system of the present invention incorporates a means for inputting past shipping data, inventory data, and sales data, as well as an emotion engine that recognizes the user's emotions, making it possible to provide information and propose sales measures that are more optimized for the user.

[1009] Example 1: Data entry and reception

[1010] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The server receives this data, saves it in storage, and then stores it in the database.

[1011] Example 2: Predictive model generation and prediction

[1012] The server trains a generative AI model based on the data stored in the database. Once trained, the model is used to predict future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables and displayed on a dashboard.

[1013] Example 3: Incorporating an Emotion Engine

[1014] The system is equipped with an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze that data. For example, it can obtain user emotion data through a camera or microphone.

[1015] Example 4: Adjusting display methods based on emotions

[1016] The server receives emotion data from the emotion engine and adjusts the display of prediction results depending on the user's state. For example, if the user is feeling stressed, the server may simplify the prediction results or display a message recommending a specific action.

[1017] Example 5: Proposal of optimal sales measures

[1018] The server generates optimal sales strategies based on the prediction results, taking into account emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will prioritize suggesting sales strategies with low risk. It also simulates the effects of the proposed sales strategies and provides the results to the user.

[1019] Example 6: Self-learning and accuracy improvement

[1020] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. By retraining the predictive model based on the new data, prediction accuracy is continuously improved. User emotion data recognized by the emotion engine is also used for retraining.

[1021] Specific examples

[1022] 1. Data Entry:

[1023] Users upload shipping, inventory, and sales data for 2022 into the system.

[1024] 2. Receiving and storing data:

[1025] The server receives the data and stores it in a database.

[1026] 3. Generate predictive models:

[1027] The server trains a generative AI model to predict shipment volumes for 2023.

[1028] 4. Use of Emotion Engine:

[1029] When a user operates the system, the emotion engine analyzes the user's facial expressions and voice to recognize emotions such as stress or joy.

[1030] 5. Adjust the display:

[1031] The server detects from the emotion data that the user is feeling stressed and simplifies the display content to make it easier to understand.

[1032] 6. Sales strategy proposal:

[1033] The server takes into account emotional data and prioritizes safe sales strategies.

[1034] 7. Self-learning and accuracy improvement:

[1035] Users upload their latest data, and the server uses that data to retrain the predictive model, also leveraging feedback from the emotion engine.

[1036] As described above, the system of the present invention realizes more accurate and user-friendly shipping forecasts and sales strategy proposals, and supports the efficient operation of logistics centers and warehouses.

[1037] The processing flow will be explained below.

[1038] Generate shipment volume forecasts and incorporate sentiment engines

[1039] Step 1: Data entry

[1040] The user prepares past shipping data, inventory data, and sales data.

[1041] Users upload this data in CSV or Excel file format through the system's data entry screen.

[1042] Step 2: Receiving and storing data

[1043] The server receives the uploaded file from the user.

[1044] The server stores the received data in temporary storage.

[1045] Step 3: Save the data to a database

[1046] The server reads the data stored in the storage and stores it in the database.

[1047] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[1048] Step 4: Generate a predictive model

[1049] The server retrieves the data stored in the database and performs preprocessing.

[1050] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[1051] Step 5: Run a prediction

[1052] The server uses the generated AI model to predict future shipment quantities.

[1053] The server retrieves and organizes the prediction results.

[1054] Step 6: Providing prediction results

[1055] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[1056] Proposing optimal sales strategies

[1057] Step 7: Enter sales data

[1058] Users upload past sales and campaign data into the system.

[1059] Step 8: Receiving and storing sales data

[1060] A server receives sales data uploaded by users.

[1061] The server stores the received data in a database.

[1062] Step 9: Generate execution models

[1063] The server analyzes the sales data and builds a sales strategy model.

[1064] The server uses the generated AI model to automatically generate optimal sales strategies.

[1065] Step 10: Run the simulation

[1066] The server simulates the effect of the automatically generated sales measures.

[1067] The server organizes the simulation results.

[1068] Step 11: Providing simulation results

[1069] The server displays the simulation results on a dashboard for the user.

[1070] Improved prediction accuracy through self-learning

[1071] Step 12: Enter new data

[1072] Users periodically upload the latest shipping and sales data to the system.

[1073] Step 13: Receive and store the latest data

[1074] The server receives the latest data and stores it in storage.

[1075] The server adds and saves the received data to the database.

[1076] Step 14: Retrain the model

[1077] The server retrains the existing predictive model using the latest data.

[1078] The server verifies the accuracy of the retrained model.

[1079] Step 15: Providing improved prediction results

[1080] The server uses the retrained model to make new predictions and generate improved prediction results.

[1081] The server provides the new prediction results to the user and displays them on a dashboard.

[1082] Incorporating an emotion engine

[1083] Step 16: Obtaining Emotion Data

[1084] The device (e.g., camera or microphone) captures the user's facial expression and voice data.

[1085] The emotion data acquired by the device is sent to the server in real time.

[1086] Step 17: Analyze the emotion data

[1087] The server uses an emotion engine to analyze the transmitted emotion data and recognize the user's emotional state.

[1088] Step 18: Adjust the display

[1089] The server adjusts how the prediction results are displayed based on the recognized user emotion.

[1090] The server makes adjustments such as simplifying and displaying prediction results when the user is feeling stressed.

[1091] Step 19: Adjust your sales strategy

[1092] The server adjusts the optimal sales strategy proposals based on the emotional data.

[1093] The server makes adjustments, such as prioritizing sales strategies with low risk.

[1094] Step 20: Feedback to the predictive model

[1095] The server uses the user's emotion data recognized by the emotion engine to retrain the prediction model.

[1096] The server makes new predictions with the retrained model, continually improving its accuracy.

[1097] This enables the system to take user emotions into account to provide more accurate and user-friendly shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[1098] Example 2

[1099] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1100] While conventional logistics and sales forecasting systems can perform predictions based on shipping and sales data, they are often not optimized to take user emotions into account. This can lead to users feeling stressed or being unable to properly understand the information, potentially resulting in reduced work efficiency and incorrect decision-making. Furthermore, incorporating emotion engine functionality is expected to improve user-friendliness in information provision and the accuracy of policy proposals, but implementation is not easy.

[1101] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for converting the prediction results into graphs or tables and providing them to the user, means for acquiring emotion data using an emotion engine that recognizes the user's emotions, and means for analyzing the emotion data and adjusting the display method of the prediction results depending on the user's state. This makes it possible to provide optimal information and propose sales measures that take the user's emotions into consideration.

[1102] "Historical Shipping Data" refers to information relating to the actual delivery or transportation of goods or materials within a specified period of time.

[1103] "Inventory data" refers to information about the quantity and types of products and goods currently stored in warehouses and stores.

[1104] "Sales Data" means information regarding the quantity and value of goods or services actually sold within a particular period of time.

[1105] "Database" refers to a collection of digital information that is organized, managed, and stored in a searchable and accessible format.

[1106] A "generative AI model" is a type of algorithm created using machine learning and deep learning techniques to analyze data and predict future behavior or states.

[1107] An "emotion engine" refers to a software or hardware system that recognizes and analyzes a user's emotional state from facial expressions, voice, etc.

[1108] "Emotion data" refers to information that expresses the user's emotional state as numerical values ​​or categories.

[1109] "Prediction results" refers to information that estimates future shipment volumes, sales trends, etc. based on the generated AI model.

[1110] "Sales tactics" refers to specific strategies and action plans for achieving sales and marketing goals.

[1111] "Simulation" refers to a method for predicting the outcomes of specific actions or events under hypothetical environments or conditions.

[1112] "Retraining" refers to the process of retraining a generative AI model with new data to improve its performance and accuracy.

[1113] The system of the present invention includes a means for inputting past shipping data, inventory data, and sales data, a means for receiving the data and storing it in a database, a means for making predictions using a generative AI model, a means for providing the prediction results to a user, a means for acquiring emotion data using an emotion engine, and a means for analyzing the emotion data and adjusting the display method.

[1114] First, the user uploads past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The terminal inputs this data via the user interface and sends it to the server. The server receives the data, saves it in storage, and then stores it in the database.

[1115] The server then trains a generative AI model based on the data stored in the database. Specific software used includes TensorFlow and PyTorch. Once the model is trained, the server predicts future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables using tools such as Matplotlib and displayed on the user dashboard.

[1116] The system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze the data. The user's emotion data is acquired through the device's camera and microphone, and technologies such as OpenCV and Google Cloud Speech-to-Text are used. The server receives this data, and the emotion engine analyzes it to determine the user's emotional state.

[1117] Once the user's emotional data is acquired, the server adjusts the way predictions are displayed depending on the user's emotional state. For example, if the user is stressed, the server may display simplified information or messages recommending specific actions. If the user is relaxed, the server may display detailed data and complex graphs.

[1118] The server then generates optimal sales strategies based on the prediction results. It uses rule engines such as ACT-R and RETE to consider emotional data and provide strategies suited to the user. The server then simulates these strategies and provides the results to the user in a detailed report.

[1119] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data, and also uses user emotion data recognized by the emotion engine to improve prediction accuracy.

[1120] As a specific example, the prompt text is entered as follows: "Please upload your shipping data, inventory data, and sales data for the past five years. The system will then generate a shipping quantity forecast and display it on a dashboard. It will also adjust the way the information is displayed based on the user's emotional state and suggest optimal sales strategies."

[1121] As described above, the system of the present invention performs a comprehensive process from data input to prediction, emotion recognition, optimal policy proposals, and self-learning, thereby enabling user-friendly and highly accurate shipping forecasts and sales policy proposals, thereby supporting the efficient operation of logistics centers and warehouses.

[1122] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1123] Step 1:

[1124] Users upload past shipping data, inventory data, and sales data to the system.

[1125] The user opens the system's data entry screen from their terminal, clicks the "Data Upload" button, selects the target CSV or Excel file, and clicks "Upload."

[1126] Input: CSV or Excel file of 2022 shipping, inventory, and sales data.

[1127] Output: The data file sent to the server.

[1128] Step 2:

[1129] The server receives the uploaded data files and processes them for storage in a database.

[1130] After receiving the data files, the server classifies each data item into "shipping data," "inventory data," and "sales data," and temporarily stores it in storage. It then organizes and stores the data in a database.

[1131] Input: Data file received from user.

[1132] Output: Organized data stored in a database.

[1133] Step 3:

[1134] The server performs preprocessing to train the generative AI model based on the data stored in the database.

[1135] The server retrieves the necessary data from the database, cleans the data, imputes missing values, and normalizes it.

[1136] Input: Shipping data, inventory data, sales data in the database.

[1137] Output: The preprocessed dataset.

[1138] Step 4:

[1139] The server trains the generative AI model.

[1140] The server uses the preprocessed data to train an AI model using a machine learning framework (e.g., TensorFlow or PyTorch).

[1141] Input: The preprocessed dataset.

[1142] Output: A trained generative AI model.

[1143] Step 5:

[1144] Use a trained generative AI model to predict future shipment quantities.

[1145] Based on the newly acquired data, the server inputs it into a forecasting model to predict future shipment quantities.

[1146] Input: A trained generative AI model and data for the time period you want to predict.

[1147] Output: Forecast results of future shipment quantities.

[1148] Step 6:

[1149] The prediction results are converted into graphs and tables and displayed on the user's dashboard.

[1150] The server visualizes the prediction results using libraries such as Matplotlib and D3.js and displays them on a dashboard in real time.

[1151] Input: Prediction results.

[1152] Output: Graphs and tables on a dashboard.

[1153] Step 7:

[1154] Emotion data is acquired using an emotion engine that recognizes the user's emotions.

[1155] The user's facial expressions and voice are captured through the camera and microphone installed on the device, and emotion data is generated using OpenCV, Google Cloud Speech-to-Text, etc.

[1156] Input: User's facial expression images and voice data.

[1157] Output: Emotion data.

[1158] Step 8:

[1159] The server analyzes the emotion data and adjusts the display method according to the user's state.

[1160] The server analyzes the emotional data received from the emotion engine and dynamically adjusts the way prediction results are displayed based on the user's mental state. For example, if stress is detected, the information displayed will be simplified.

[1161] Input: Emotion data.

[1162] Output: Adjusted dashboard display.

[1163] Step 9:

[1164] The server generates optimal sales strategies based on the prediction results and takes into account emotional data.

[1165] The server generates sales strategies based on the generated predictions and optimizes them using emotional data, using rule engines such as ACT-R and RETE.

[1166] Input: Prediction results, emotion data.

[1167] Output: Optimized sales execution.

[1168] Step 10:

[1169] The server simulates the effects of the sales measures and provides the results to the user.

[1170] The server uses a simulation engine to evaluate the hypothetical effects of the proposed sales measures and provides the results to the user in the form of a detailed report.

[1171] Input: Optimized merchandising.

[1172] Output: Report of simulation results.

[1173] Step 11:

[1174] Users periodically upload new shipping and sales data to the system, which the server receives and updates the database.

[1175] Input: New shipping data, sales data.

[1176] Output: The updated database.

[1177] Step 12:

[1178] The server retrains the predictive model based on new data, including sentiment data.

[1179] Input: The updated database.

[1180] Output: A retrained generative AI model and improved prediction results.

[1181] Through the above steps, the system of the present invention realizes user-friendly and highly accurate shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[1182] (Application example 2)

[1183] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1184] Conventional shipping forecasting systems only make predictions based on past data and are unable to consider the user's emotional state. This can make it difficult for users to understand the prediction results, and can result in insufficient proposals for appropriate sales strategies. Furthermore, it is difficult to provide customized customer service and product proposals in response to customer emotions in physical stores, which can hinder the system's ability to improve customer satisfaction.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for analyzing the data using an emotion engine that recognizes the user's emotions, means for generating and providing the prediction results to the user, and means for adjusting the display method of the prediction results based on the user's emotions. This makes it easier to understand the prediction results and makes it possible to propose optimal sales measures based on the user's emotional state. Furthermore, in physical stores, customized customer service and product suggestions based on customer emotions can be provided, improving customer satisfaction.

[1186] "Past shipping data" refers to information about shipments that the system has recorded in the past.

[1187] "Inventory data" is information describing current and past inventory status.

[1188] "Sales data" refers to information relating to sales, such as product sales records and customer information.

[1189] "Means of input" refers to the interface or method by which a user provides data to the system.

[1190] "Means for receiving data and storing it in a database" refers to the method or infrastructure by which the system receives input data and stores it in a database.

[1191] A "generative AI model" is an artificial intelligence model designed to make predictions and judgments based on large amounts of data.

[1192] A "means of forecasting" is a method or process for calculating future shipment quantities, etc. based on input data.

[1193] An "emotion engine" is a technology or algorithm that analyzes a user's facial expressions and voice and recognizes their emotions.

[1194] "Analytical tools" are methods and tools used to analyze data and information and find meaning.

[1195] The "means for generating a prediction result and providing it to a user" refers to a method for creating predicted information and displaying or notifying it to a user.

[1196] The "means for adjusting the display method of the prediction result based on the emotion" is a method for changing the format and content of the information to be displayed depending on the emotional state of the user.

[1197] The "means for generating optimal sales measures" is a method for devising the most effective sales strategy based on prediction results and emotional data.

[1198] A "means for simulating the effectiveness of sales measures" is a method for estimating in advance how successful a proposed sales strategy will be.

[1199] "Means for providing simulation results to users" refers to processes and tools for presenting the results of the simulation to users.

[1200] "Means for retraining a predictive model based on new data" refers to a method for updating an existing predictive model using newly obtained data to improve its accuracy.

[1201] The "means for generating improved prediction results using a retrained prediction model" is a process for using an updated prediction model to derive more accurate prediction results.

[1202] This invention provides a customer service support system that responds to customer emotions in brick-and-mortar stores. The system includes a means for inputting past shipping data, inventory data, and sales data, and a means for receiving this data and storing it in a database. Each of these means and the operation of the system are described in detail below.

[1203] The server receives past shipping data, inventory data, and sales data and stores it in a database. Users provide this data by uploading it in CSV or Excel file format. The server receives the uploaded data and stores it in a database. This provides the basis for the data used in the next steps.

[1204] Next, the server uses a generative AI model to predict future shipment quantities from the data stored in the database. A large amount of past data is used to train the AI ​​model. The prediction results are displayed in graphs and tables on a dashboard and provided to the user. This predictive model is retrained each time new data is input, improving its prediction accuracy. The server manages this entire process.

[1205] The smart glasses are also equipped with an emotion engine that recognizes the user's emotions in real time. This emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses. The captured data is sent to a server and analyzed in real time. The analyzed emotion data is used to adjust the way prediction results are displayed based on the user's emotional state.

[1206] For example, if a salesperson wearing smart glasses analyzes a customer's emotional state and determines that the customer is feeling "stressed," the system can use that information to simplify product explanations or display messages to reassure the customer. If the customer is feeling "happy," a message suggesting an upsell product will be displayed.

[1207] Based on the analysis results of this emotion engine, the server also proposes optimal sales strategies. These proposals are adjusted taking into account the user's emotions, so if the user is feeling anxious, for example, the server will prioritize sales strategies with less risk.

[1208] Consider the following scenario as a concrete example: Customer A is shopping in a store. Salesperson B uses smart glasses to observe Customer A and analyzes his / her emotions from his / her facial expressions and voice. If Customer A is recognized as "happy," a "new product suggestion" will appear on the display of Salesperson B's glasses, and Salesperson B will suggest, "Please take a look at these new products."

[1209] Example prompt sentence:

[1210] "Implement a smart glasses application that analyzes customer emotions in real time and provides personalized product recommendations and customer service based on those emotions. If the customer is recognized as 'happy,' the glasses will display a message suggesting new products to the store clerk, who will then make the recommendation to the customer."

[1211] In this way, the present invention adjusts prediction results and sales strategies based on user emotions, thereby improving customer satisfaction in physical stores.

[1212] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1213] Step 1:

[1214] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format through the system's data input screen. The input data is used to forecast past shipments and improve the accuracy of the results. This data is sent from the user's device.

[1215] Step 2:

[1216] The server receives the data uploaded by the user and stores it in a database. The input data is used for subsequent data analysis and predictive model training. The database stores various data categories (shipment data, inventory data, sales data) appropriately.

[1217] Step 3:

[1218] The server trains the generative AI model using past shipping, inventory, and sales data stored in the database. During this process, the data is processed (for example, missing value completion, data standardization, etc.) for use as training data. Meaningful features are extracted from the input data and used to generate the AI ​​model.

[1219] Step 4:

[1220] Using the generative AI model, the server predicts future shipment quantities. New input data is fed into the model to obtain predictions. These predictions are then converted into graphs and tables.

[1221] Step 5:

[1222] The server provides the prediction results to the user, and displays them in an easy-to-understand dashboard for easy access by the user.

[1223] Step 6:

[1224] The emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses, and transmits this data to the server in real time. This data becomes input data for emotion recognition.

[1225] Step 7:

[1226] The server analyzes the acquired emotional data using an emotion engine. It identifies the user's emotional state using facial expression recognition algorithms and voice analysis algorithms. The analysis results (e.g., stress, joy, etc.) are obtained.

[1227] Step 8:

[1228] The server adjusts the way predictions are displayed based on the emotional data. For example, if the user is feeling stressed, it simplifies the prediction or displays a reassuring message. This information is reflected on the smart glasses display or the device screen.

[1229] Step 9:

[1230] The server generates optimal sales strategies based on the prediction results and emotion data. It then simulates the effectiveness of the generated sales strategies and provides the results to the user. The simulation also includes risk assessment and profit forecasting, providing the user with detailed analysis results.

[1231] Step 10:

[1232] Every time a user periodically uploads new shipping or sales data, the server updates the database with this data and retrains the predictive model. Emotional data is also incorporated into the retraining process to improve the accuracy of the predictive model. The prediction results provided to users are always highly accurate and based on the latest data.

[1233] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1234] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1235] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1236] [Fourth embodiment]

[1237] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1238] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1239] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1240] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1241] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1242] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1243] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1244] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1245] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1246] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1247] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1248] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1249] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1250] The system of the present invention begins when a logistics center or warehouse manager inputs past shipping data, inventory data, and sales data. This data is received by a server and stored in a database. The input data is then analyzed using a generative AI model to predict future shipping quantities. The prediction results are provided to the user.

[1251] Example 1: Data Entry

[1252] Users prepare shipping and inventory data from the past year and upload it to the system's data entry screen. Data can be entered in CSV or Excel format. For example, users can select and upload a file containing monthly shipping and inventory figures from January to December 2022.

[1253] Example 2: Data Receipt and Storage

[1254] The server receives files uploaded by users and stores them in storage. It then stores them in a database and centralizes the data. This allows past data to be efficiently organized and accessible at any time.

[1255] Example 3: Generating a predictive model

[1256] The server trains a generative AI model based on the received data. This process uses machine learning libraries such as TensorFlow and PyTorch. Once the training phase is complete, future shipment quantities are predicted. For example, the forecast shipment quantities for January to December 2023 are obtained.

[1257] Example 4: Providing prediction results

[1258] The server converts the forecast results into graphs and tables and provides them in an easy-to-understand format. Users can view these forecast results through the system's dashboard. This information can be used to make appropriate personnel allocation and inventory management.

[1259] Example 5: Proposal of optimal sales measures

[1260] The server also receives and analyzes past sales data. It uses a generative AI model to generate optimal sales strategies and simulate their effectiveness. For example, it proposes optimal discount rates and marketing strategies for promoting new products. These strategies are simulated and the results are provided to the user.

[1261] Example 6: Self-learning and accuracy improvement

[1262] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, you will get more accurate results than the first time.

[1263] As described above, the present invention is a system that enables efficient management of logistics centers and warehouses, and realizes optimization of shipping forecasts and sales strategies.

[1264] The processing flow will be explained below.

[1265] Generate shipment quantity forecasts

[1266] Step 1: Data entry

[1267] The user prepares past shipping data, inventory data, and sales data.

[1268] The user uploads past data in CSV or Excel file format from the system's data entry screen.

[1269] Step 2: Receiving and storing data

[1270] The server receives the uploaded file from the user.

[1271] The server stores the received data in temporary storage.

[1272] Step 3: Save the data to a database

[1273] The server reads the data stored in the storage and stores it in the database.

[1274] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[1275] Step 4: Generate a predictive model

[1276] The server retrieves the data stored in the database and performs preprocessing.

[1277] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[1278] Step 5: Run a prediction

[1279] The server uses the generated AI model to predict future shipment quantities.

[1280] The server retrieves and organizes the prediction results.

[1281] Step 6: Providing prediction results

[1282] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[1283] Proposing optimal sales strategies

[1284] Step 1: Enter your sales data

[1285] Users upload past sales and campaign data into the system.

[1286] Step 2: Receiving and storing sales data

[1287] A server receives sales data uploaded by users.

[1288] The server stores the received data in a database.

[1289] Step 3: Generate a sales execution model

[1290] The server analyzes the sales data and builds a sales strategy model.

[1291] The server uses the generated AI model to automatically generate optimal sales strategies.

[1292] Step 4: Run the simulation

[1293] The server simulates the effect of the automatically generated sales measures.

[1294] The server organizes the simulation results.

[1295] Step 5: Providing simulation results

[1296] The server displays the simulation results on a dashboard for the user.

[1297] Improved prediction accuracy through self-learning

[1298] Step 1: Enter new data

[1299] Users periodically upload the latest shipping and sales data to the system.

[1300] Step 2: Receive and store the latest data

[1301] The server receives the latest data and stores it in storage.

[1302] The server adds and saves the received data to the database.

[1303] Step 3: Retrain the model

[1304] The server retrains the existing predictive model using the latest data.

[1305] The server verifies the accuracy of the retrained model.

[1306] Step 4: Providing improved prediction results

[1307] The server uses the retrained model to make new predictions and generate improved prediction results.

[1308] The server provides the new prediction results to the user and displays them on a dashboard.

[1309] Through these processing steps, the system achieves highly accurate shipping forecasts and proposes optimal sales strategies, supporting the efficiency and optimization of logistics.

[1310] Example 1

[1311] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1312] Logistics centers and warehouses require highly accurate predictions of future shipment quantities and sales strategies based on past shipping, inventory, and sales data. However, previous systems did not centralize data management or improve prediction accuracy sufficiently, making it difficult to efficiently manage inventory and optimize sales strategies. Another challenge was continually improving the accuracy of prediction models by utilizing new data.

[1313] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1314] In this invention, the server includes a means for a user to input past data, a means for receiving the data, storing the data in a database, and centrally managing the data, a means for predicting future shipment quantities from the input data using a generative AI model, and a means for visualizing the prediction results and providing them to the user. This enables efficient data management and highly accurate shipment quantity predictions. The system also includes a means for generating optimal measures based on predictions made using the generative AI model and simulating their effects, thereby optimizing sales measures. Furthermore, the accuracy of predictions can be continuously improved by periodically inputting new data to update the database and retraining the prediction model.

[1315] "Historical data" refers to previous shipping data, inventory data, and sales data collected at distribution centers and warehouses.

[1316] "Users" refer to managers of logistics centers and warehouses who operate the system, input data, and utilize the prediction results.

[1317] "Database" refers to an information storage system for organizing and centrally managing received data.

[1318] A "generative AI model" refers to an artificial intelligence model that uses past data to predict future shipment volumes and optimal sales strategies.

[1319] "Visualization" refers to the process of converting prediction results into graphs, tables, or other formats and presenting them in a way that is easy for users to understand.

[1320] "Measures" refer to specific strategies and measures for formulating optimal action plans based on the prediction results.

[1321] "Simulation" refers to the process of estimating the effects of new measures in advance and verifying them on a trial basis.

[1322] "Retraining" refers to the training process of updating a generative AI model with new data to improve its predictive accuracy.

[1323] "Efficient data management" means quickly organizing and storing incoming data so that it remains easily accessible when needed.

[1324] "Prediction accuracy" refers to an indicator of how accurately a generative AI model can predict future shipment volumes and the effectiveness of sales strategies.

[1325] The system of the present invention is designed to enable managers of logistics centers and warehouses to efficiently forecast and optimize shipping quantities and sales strategies. This system is implemented in the following manner.

[1326] First, the user prepares shipping and inventory data for the past year and uploads it from the system's data input screen. This data is entered in CSV or Excel format. For example, an Excel file containing monthly shipping and inventory quantities from January to December 2022 can be selected and uploaded. An example of a specific prompt is, "Please upload shipping data for the past year (e.g., Excel file from January to December 2022)."

[1327] Next, the terminal sends the file selected by the user to the system. The server receives the file and saves it in storage. It then stores it in a database for centralized data management. For example, validation processing is performed to detect missing values ​​and outliers.

[1328] The server trains a generative AI model based on the received shipping and inventory data. This process uses machine learning libraries such as TensorFlow and PyTorch. The server performs feature engineering based on past data and converts the data into a form that can be input to the model. Once the training phase is complete, future shipping quantities are predicted. For example, shipping quantities from January to December 2023 are predicted.

[1329] Furthermore, the server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). Users can view these prediction results by opening the system's dashboard. The server also provides a function to update the dashboard in real time. An example of a specific prompt is "Please open the dashboard to check the prediction results."

[1330] In addition, the server analyzes past sales data and generates optimal sales measures using a generative AI model. A function to simulate the effects of these measures is also provided, and the optimal discount rate and marketing strategy for promoting new products are proposed. These proposals are provided to users via the dashboard. An example of a specific prompt is, "Please propose the optimal discount rate for promoting new products."

[1331] Finally, users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The predictive model is then retrained based on the new data. This continuously improves the accuracy of the predictions. For example, if you run a new forecast for 2023 after incorporating the latest data, the accuracy will be better than the first forecast.

[1332] Through the above steps, this system enables efficient management of logistics centers and warehouses, and realizes the optimization of shipping forecasts and sales strategies.

[1333] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1334] Step 1: The user uploads shipping and inventory data from the past year to the system's data input screen. The input is in CSV or Excel format, and includes files recording monthly shipping and inventory quantities from January to December 2022. The terminal sends these files to the system, where they are received by the server.

[1335] Step 2: The server saves the file received from the user in storage. The contents of this file are then stored in a database for centralized management. When the data is stored in the database, a validation process is performed to detect missing values ​​and outliers. The output of this stage is the data correctly stored and organized in the database.

[1336] Step 3: The server retrieves past shipping and inventory data from the database and uses this data to train a generative AI model. Specifically, training is performed using machine learning libraries such as TensorFlow and PyTorch. Feature engineering is performed based on the past data, and the data is converted into a form that can be input into the model. Future shipping quantities are predicted using the input past data and the AI ​​model. The output of this stage is predicted future shipping data.

[1337] Step 4: The server converts the prediction results into graphs or tables using visualization tools (e.g., Matplotlib or D3.js). The user can then open the system's dashboard to view the prediction results. The dashboard displays the prediction results updated in real time. As an output, the prediction results are provided to the user in a visually easy-to-understand format.

[1338] Step 5: The server analyzes past sales data and generates optimal sales measures using a generative AI model. Specifically, the model proposes optimal discount rates and marketing strategies for promoting new products. The server then simulates the effects of these measures and provides them to the user. The user can use this as a reference to actually implement the measures. The output includes the simulation results and the proposed measures.

[1339] Step 6: Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data. The retrained predictive model can generate more accurate predictions. Finally, the predictions made by the retrained model are provided to the user. The output includes the improved predictions based on the retrained model.

[1340] (Application example 1)

[1341] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1342] To improve the accuracy of shipping forecasts and inventory management at logistics centers and warehouses, it is important not only to make forecasts based on past data, but also to quickly input data on-site and obtain real-time information. However, with conventional systems, data input was time-consuming and manual, and there were limited ways to check forecast results and sales measures in real time. This made it difficult to operate efficiently and plan optimal sales measures.

[1343] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1344] In this invention, the server includes: a means for inputting past shipping data, inventory data, and sales data; a means for receiving the data and storing it in a database; a means for predicting future shipping quantities from the input data using a generative AI model; a means for generating the prediction results and providing them to the user; a means for checking shipping prediction data in real time using a smart device; and a means for photographing past shipping and inventory data and inputting the data using OCR technology. This allows for quick and efficient data entry and confirmation of prediction results, enabling more efficient operation of logistics centers and warehouses and optimized inventory management. It also enables the planning and simulation of sales strategies based on the improved prediction results produced by the generative AI model.

[1345] "Past shipping data" refers to data that includes specific quantities, dates and times, and product information regarding shipments that have been made in advance.

[1346] "Inventory data" refers to data that indicates the quantity, type, and contents of products stored in warehouses and logistics centers.

[1347] "Sales data" refers to data that includes specific information regarding the sales quantity, sales destination, sales period, and sales amount of a product.

[1348] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to analyze past data and generate future trends and predictions.

[1349] A "smart device" is a portable electronic device that can connect to the Internet, such as a smartphone or smart glasses.

[1350] "OCR technology" refers to optical character recognition technology, which extracts and digitizes character information from image data.

[1351] A "prompt" is a written instruction or question that is input to a generative AI model, and the AI ​​responds or analyzes based on this.

[1352] The system for realizing this invention is designed for efficient management in logistics centers and warehouses. A specific embodiment of this system is described below.

[1353] System Configuration

[1354] Hardware

[1355] Server: Receives, stores, analyzes data, and performs training and prediction processing for generated AI models. Examples include database servers and GPU servers for machine learning.

[1356] Smart devices: Smartphones and smart glasses are used to assist users in inputting and verifying data.

[1357] Camera: Cameras built into smartphones and smart glasses are used to capture inventory and shipping data.

[1358] software

[1359] Database: Used to centrally manage received data. Examples include MySQL and PostgreSQL.

[1360] Generative AI model: An AI model generated using TensorFlow and PyTorch that predicts future shipment quantities based on past data.

[1361] OCR technology: Optical character recognition technology is used to extract text information from image data. For example, Google Cloud Vision API is used.

[1362] Web application: Using frameworks such as Streamlit, we provide users with an interface that visualizes prediction results and sales strategies.

[1363] Detailed System Operation

[1364] The server provides a means to input past shipping data, inventory data, and sales data. Users can upload this data in the form of CSV files or photographed images and enter it into the system. Data can be easily entered from the field using a smart device.

[1365] The server then receives the uploaded data and stores it in a database, where it uses OCR technology to extract text information from the image data and store it as structured data.

[1366] The server uses a generative AI model based on the received data to predict future shipping quantities, which will improve the efficiency of future shipping and inventory management. The prediction results can be viewed in real time via smart devices and are provided to users in graph and table format.

[1367] Furthermore, the server generates optimal sales strategies based on the prediction results and simulates their effectiveness. Users can obtain these strategies in real time through the voice assistant of their smart device and check important information.

[1368] Specific examples

[1369] When a user says to the smart glasses, "I would like to check the shipment forecast data for March 2023," the voice assistant will provide a real-time shipment forecast.

[1370] Simply tap the "Upload inventory data" button on your smartphone and use the camera to take a photo of your inventory list. OCR technology will automatically convert the data into text and upload it to the system.

[1371] Prompt Sentence Examples

[1372] "Please upload shipping data for the past year."

[1373] "Generate a shipping forecast for the next month."

[1374] "Please show me the results of the sales strategy simulation."

[1375] This system will significantly improve the efficiency of shipping forecasts and inventory management at logistics centers and warehouses, enabling real-time information acquisition and policy planning.

[1376] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1377] Step 1:

[1378] The server provides a means for users to input past shipping data, inventory data, and sales data. Users can input data using their smart devices and upload data in CSV files or image format. The input data is converted into a format that can be saved in the database.

[1379] Input: CSV file, image data

[1380] Output: Converted data that can be saved in a database

[1381] Specific operation: The user takes a photo of the inventory list using their smartphone and uploads it to the system.

[1382] Step 2:

[1383] The server receives the uploaded data and stores it in a database. Using OCR technology, text information is extracted from the image data and stored as structured data. The data is then centrally managed with correlation.

[1384] Input: Converted data in input format

[1385] Output: Data converted to text, stored in a database

[1386] Specific operation: The server uses Google Cloud Vision API or similar to extract and save text information from image data.

[1387] Step 3:

[1388] The server trains a generative AI model based on the received data. The trained model is used to predict future shipment quantities. The generative AI model is built using TensorFlow and PyTorch to analyze the data.

[1389] Input: Structured data

[1390] Output: A trained generative AI model

[1391] Specific operation: The server launches TensorFlow and trains an AI model using the received data.

[1392] Step 4:

[1393] The server uses the trained generative AI model to predict future shipment quantities, and the results are converted into a format that users can view and provided via their smart devices, displayed in graphs and tables.

[1394] Input: Trained generative AI model, data needed to predict future shipments

[1395] Output: Shipping quantity forecast result

[1396] Specific operation: The prediction results are converted into graphs and tables and displayed on the user's smart device.

[1397] Step 5:

[1398] The server generates optimal sales strategies based on the prediction results and simulates their effectiveness. The simulation results are provided to the user in real time via the voice assistant.

[1399] Input: Forecast results, past sales data

[1400] Output: Sales strategies, simulation results

[1401] What it does: The voice assistant responds to user prompts and presents simulation results.

[1402] Step 6:

[1403] Users periodically input new shipping and sales data, which the server receives and updates the database, retraining the generative AI model and providing improved prediction results.

[1404] Input: New shipping data, sales data

[1405] Output: Updated database, improved prediction results

[1406] How it works: Users periodically upload data, and the server automatically updates and retrains the database.

[1407] Step 7:

[1408] The server responds in real time by providing the necessary data in response to prompts from the user. Examples of prompts include "Generate a shipping forecast for the next month" and "Display the results of a sales strategy simulation."

[1409] Input: prompt statement

[1410] Output: Real-time data, forecast data, simulation results

[1411] Specific behavior: The server parses the prompt, performs the necessary processing, and provides the answer to the user.

[1412] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1413] The system of the present invention incorporates a means for inputting past shipping data, inventory data, and sales data, as well as an emotion engine that recognizes the user's emotions, making it possible to provide information and propose sales measures that are more optimized for the user.

[1414] Example 1: Data entry and reception

[1415] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The server receives this data, saves it in storage, and then stores it in the database.

[1416] Example 2: Predictive model generation and prediction

[1417] The server trains a generative AI model based on the data stored in the database. Once trained, the model is used to predict future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables and displayed on a dashboard.

[1418] Example 3: Incorporating an Emotion Engine

[1419] The system is equipped with an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze that data. For example, it can obtain user emotion data through a camera or microphone.

[1420] Example 4: Adjusting display methods based on emotions

[1421] The server receives emotion data from the emotion engine and adjusts the display of prediction results depending on the user's state. For example, if the user is feeling stressed, the server may simplify the prediction results or display a message recommending a specific action.

[1422] Example 5: Proposal of optimal sales measures

[1423] The server generates optimal sales strategies based on the prediction results, taking into account emotional data obtained from the emotion engine. For example, if the user is feeling anxious, it will prioritize suggesting sales strategies with low risk. It also simulates the effects of the proposed sales strategies and provides the results to the user.

[1424] Example 6: Self-learning and accuracy improvement

[1425] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. By retraining the predictive model based on the new data, prediction accuracy is continuously improved. User emotion data recognized by the emotion engine is also used for retraining.

[1426] Specific examples

[1427] 1. Data Entry:

[1428] Users upload shipping, inventory, and sales data for 2022 into the system.

[1429] 2. Receiving and storing data:

[1430] The server receives the data and stores it in a database.

[1431] 3. Generate predictive models:

[1432] The server trains a generative AI model to predict shipment volumes for 2023.

[1433] 4. Use of Emotion Engine:

[1434] When a user operates the system, the emotion engine analyzes the user's facial expressions and voice to recognize emotions such as stress or joy.

[1435] 5. Adjust the display:

[1436] The server detects from the emotion data that the user is feeling stressed and simplifies the display content to make it easier to understand.

[1437] 6. Sales strategy proposal:

[1438] The server takes into account emotional data and prioritizes safe sales strategies.

[1439] 7. Self-learning and accuracy improvement:

[1440] Users upload their latest data, and the server uses that data to retrain the predictive model, also leveraging feedback from the emotion engine.

[1441] As described above, the system of the present invention realizes more accurate and user-friendly shipping forecasts and sales strategy proposals, and supports the efficient operation of logistics centers and warehouses.

[1442] The processing flow will be explained below.

[1443] Generate shipment volume forecasts and incorporate sentiment engines

[1444] Step 1: Data entry

[1445] The user prepares past shipping data, inventory data, and sales data.

[1446] Users upload this data in CSV or Excel file format through the system's data entry screen.

[1447] Step 2: Receiving and storing data

[1448] The server receives the uploaded file from the user.

[1449] The server stores the received data in temporary storage.

[1450] Step 3: Save the data to a database

[1451] The server reads the data stored in the storage and stores it in the database.

[1452] When the server stores the data in a database, it formats the data and fills in any missing or outlier values.

[1453] Step 4: Generate a predictive model

[1454] The server retrieves the data stored in the database and performs preprocessing.

[1455] The server uses the preprocessed data to train a generative AI model (e.g., an LSTM model).

[1456] Step 5: Run a prediction

[1457] The server uses the generated AI model to predict future shipment quantities.

[1458] The server retrieves and organizes the prediction results.

[1459] Step 6: Providing prediction results

[1460] The server converts the prediction results into graphs and tables and displays them on a dashboard that users can access.

[1461] Proposing optimal sales strategies

[1462] Step 7: Enter sales data

[1463] Users upload past sales and campaign data into the system.

[1464] Step 8: Receiving and storing sales data

[1465] A server receives sales data uploaded by users.

[1466] The server stores the received data in a database.

[1467] Step 9: Generate execution models

[1468] The server analyzes the sales data and builds a sales strategy model.

[1469] The server uses the generated AI model to automatically generate optimal sales strategies.

[1470] Step 10: Run the simulation

[1471] The server simulates the effect of the automatically generated sales measures.

[1472] The server organizes the simulation results.

[1473] Step 11: Providing simulation results

[1474] The server displays the simulation results on a dashboard for the user.

[1475] Improved prediction accuracy through self-learning

[1476] Step 12: Enter new data

[1477] Users periodically upload the latest shipping and sales data to the system.

[1478] Step 13: Receive and store the latest data

[1479] The server receives the latest data and stores it in storage.

[1480] The server adds and saves the received data to the database.

[1481] Step 14: Retrain the model

[1482] The server retrains the existing predictive model using the latest data.

[1483] The server verifies the accuracy of the retrained model.

[1484] Step 15: Providing improved prediction results

[1485] The server uses the retrained model to make new predictions and generate improved prediction results.

[1486] The server provides the new prediction results to the user and displays them on a dashboard.

[1487] Incorporating an emotion engine

[1488] Step 16: Obtaining Emotion Data

[1489] The device (e.g., camera or microphone) captures the user's facial expression and voice data.

[1490] The emotion data acquired by the device is sent to the server in real time.

[1491] Step 17: Analyze the emotion data

[1492] The server uses an emotion engine to analyze the transmitted emotion data and recognize the user's emotional state.

[1493] Step 18: Adjust the display

[1494] The server adjusts how the prediction results are displayed based on the recognized user emotion.

[1495] The server makes adjustments such as simplifying and displaying prediction results when the user is feeling stressed.

[1496] Step 19: Adjust your sales strategy

[1497] The server adjusts the optimal sales strategy proposals based on the emotional data.

[1498] The server makes adjustments, such as prioritizing sales strategies with low risk.

[1499] Step 20: Feedback to the predictive model

[1500] The server uses the user's emotion data recognized by the emotion engine to retrain the prediction model.

[1501] The server makes new predictions with the retrained model, continually improving its accuracy.

[1502] This enables the system to take user emotions into account to provide more accurate and user-friendly shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[1503] Example 2

[1504] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1505] While conventional logistics and sales forecasting systems can perform predictions based on shipping and sales data, they are often not optimized to take user emotions into account. This can lead to users feeling stressed or being unable to properly understand the information, potentially resulting in reduced work efficiency and incorrect decision-making. Furthermore, incorporating emotion engine functionality is expected to improve user-friendliness in information provision and the accuracy of policy proposals, but implementation is not easy.

[1506] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for converting the prediction results into graphs or tables and providing them to the user, means for acquiring emotion data using an emotion engine that recognizes the user's emotions, and means for analyzing the emotion data and adjusting the display method of the prediction results depending on the user's state. This makes it possible to provide optimal information and propose sales measures that take the user's emotions into consideration.

[1507] "Historical Shipping Data" refers to information relating to the actual delivery or transportation of goods or materials within a specified period of time.

[1508] "Inventory data" refers to information about the quantity and types of products and goods currently stored in warehouses and stores.

[1509] "Sales Data" means information regarding the quantity and value of goods or services actually sold within a particular period of time.

[1510] "Database" refers to a collection of digital information that is organized, managed, and stored in a searchable and accessible format.

[1511] A "generative AI model" is a type of algorithm created using machine learning and deep learning techniques to analyze data and predict future behavior or states.

[1512] An "emotion engine" refers to a software or hardware system that recognizes and analyzes a user's emotional state from facial expressions, voice, etc.

[1513] "Emotion data" refers to information that expresses the user's emotional state as numerical values ​​or categories.

[1514] "Prediction results" refers to information that estimates future shipment volumes, sales trends, etc. based on the generated AI model.

[1515] "Sales tactics" refers to specific strategies and action plans for achieving sales and marketing goals.

[1516] "Simulation" refers to a method for predicting the outcomes of specific actions or events under hypothetical environments or conditions.

[1517] "Retraining" refers to the process of retraining a generative AI model with new data to improve its performance and accuracy.

[1518] The system of the present invention includes a means for inputting past shipping data, inventory data, and sales data, a means for receiving the data and storing it in a database, a means for making predictions using a generative AI model, a means for providing the prediction results to a user, a means for acquiring emotion data using an emotion engine, and a means for analyzing the emotion data and adjusting the display method.

[1519] First, the user uploads past shipping data, inventory data, and sales data in CSV or Excel file format from the system's data input screen. The terminal inputs this data via the user interface and sends it to the server. The server receives the data, saves it in storage, and then stores it in the database.

[1520] The server then trains a generative AI model based on the data stored in the database. Specific software used includes TensorFlow and PyTorch. Once the model is trained, the server predicts future shipment quantities and provides the results to the user. The prediction results are converted into graphs and tables using tools such as Matplotlib and displayed on the user dashboard.

[1521] The system also incorporates an emotion engine that recognizes the user's emotions. The emotion engine has the ability to read emotions from the user's facial expressions and voice, and analyze the data. The user's emotion data is acquired through the device's camera and microphone, and technologies such as OpenCV and Google Cloud Speech-to-Text are used. The server receives this data, and the emotion engine analyzes it to determine the user's emotional state.

[1522] Once the user's emotional data is acquired, the server adjusts the way predictions are displayed depending on the user's emotional state. For example, if the user is stressed, the server may display simplified information or messages recommending specific actions. If the user is relaxed, the server may display detailed data and complex graphs.

[1523] The server then generates optimal sales strategies based on the prediction results. It uses rule engines such as ACT-R and RETE to consider emotional data and provide strategies suited to the user. The server then simulates these strategies and provides the results to the user in a detailed report.

[1524] Users periodically upload new shipping and sales data to the system. The server receives this data and updates the database. The server then retrains the predictive model based on the new data, and also uses user emotion data recognized by the emotion engine to improve prediction accuracy.

[1525] As a specific example, the prompt text is entered as follows: "Please upload your shipping data, inventory data, and sales data for the past five years. The system will then generate a shipping quantity forecast and display it on a dashboard. It will also adjust the way the information is displayed based on the user's emotional state and suggest optimal sales strategies."

[1526] As described above, the system of the present invention performs a comprehensive process from data input to prediction, emotion recognition, optimal policy proposals, and self-learning, thereby enabling user-friendly and highly accurate shipping forecasts and sales policy proposals, thereby supporting the efficient operation of logistics centers and warehouses.

[1527] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1528] Step 1:

[1529] Users upload past shipping data, inventory data, and sales data to the system.

[1530] The user opens the system's data entry screen from their terminal, clicks the "Data Upload" button, selects the target CSV or Excel file, and clicks "Upload."

[1531] Input: CSV or Excel file of 2022 shipping, inventory, and sales data.

[1532] Output: The data file sent to the server.

[1533] Step 2:

[1534] The server receives the uploaded data files and processes them for storage in a database.

[1535] After receiving the data files, the server classifies each data item into "shipping data," "inventory data," and "sales data," and temporarily stores it in storage. It then organizes and stores the data in a database.

[1536] Input: Data file received from user.

[1537] Output: Organized data stored in a database.

[1538] Step 3:

[1539] The server performs preprocessing to train the generative AI model based on the data stored in the database.

[1540] The server retrieves the necessary data from the database, cleans the data, imputes missing values, and normalizes it.

[1541] Input: Shipping data, inventory data, sales data in the database.

[1542] Output: The preprocessed dataset.

[1543] Step 4:

[1544] The server trains the generative AI model.

[1545] The server uses the preprocessed data to train an AI model using a machine learning framework (e.g., TensorFlow or PyTorch).

[1546] Input: The preprocessed dataset.

[1547] Output: A trained generative AI model.

[1548] Step 5:

[1549] Use a trained generative AI model to predict future shipment quantities.

[1550] Based on the newly acquired data, the server inputs it into a forecasting model to predict future shipment quantities.

[1551] Input: A trained generative AI model and data for the time period you want to predict.

[1552] Output: Forecast results of future shipment quantities.

[1553] Step 6:

[1554] The prediction results are converted into graphs and tables and displayed on the user's dashboard.

[1555] The server visualizes the prediction results using libraries such as Matplotlib and D3.js and displays them on a dashboard in real time.

[1556] Input: Prediction results.

[1557] Output: Graphs and tables on a dashboard.

[1558] Step 7:

[1559] Emotion data is acquired using an emotion engine that recognizes the user's emotions.

[1560] The user's facial expressions and voice are captured through the camera and microphone installed on the device, and emotion data is generated using OpenCV, Google Cloud Speech-to-Text, etc.

[1561] Input: User's facial expression images and voice data.

[1562] Output: Emotion data.

[1563] Step 8:

[1564] The server analyzes the emotion data and adjusts the display method according to the user's state.

[1565] The server analyzes the emotional data received from the emotion engine and dynamically adjusts the way prediction results are displayed based on the user's mental state. For example, if stress is detected, the information displayed will be simplified.

[1566] Input: Emotion data.

[1567] Output: Adjusted dashboard display.

[1568] Step 9:

[1569] The server generates optimal sales strategies based on the prediction results and takes into account emotional data.

[1570] The server generates sales strategies based on the generated predictions and optimizes them using emotional data, using rule engines such as ACT-R and RETE.

[1571] Input: Prediction results, emotion data.

[1572] Output: Optimized sales execution.

[1573] Step 10:

[1574] The server simulates the effects of the sales measures and provides the results to the user.

[1575] The server uses a simulation engine to evaluate the hypothetical effects of the proposed sales measures and provides the results to the user in the form of a detailed report.

[1576] Input: Optimized merchandising.

[1577] Output: Report of simulation results.

[1578] Step 11:

[1579] Users periodically upload new shipping and sales data to the system, which the server receives and updates the database.

[1580] Input: New shipping data, sales data.

[1581] Output: The updated database.

[1582] Step 12:

[1583] The server retrains the predictive model based on new data, including sentiment data.

[1584] Input: The updated database.

[1585] Output: A retrained generative AI model and improved prediction results.

[1586] Through the above steps, the system of the present invention realizes user-friendly and highly accurate shipping forecasts and sales strategy proposals, supporting the efficient operation of logistics centers and warehouses.

[1587] (Application example 2)

[1588] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1589] Conventional shipping forecasting systems only make predictions based on past data and are unable to consider the user's emotional state. This can make it difficult for users to understand the prediction results, and can result in insufficient proposals for appropriate sales strategies. Furthermore, it is difficult to provide customized customer service and product proposals in response to customer emotions in physical stores, which can hinder the system's ability to improve customer satisfaction.

[1590] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for inputting past shipping data, inventory data, and sales data, means for receiving the data and storing it in a database, means for predicting future shipping quantities from the input data using a generative AI model, means for analyzing the data using an emotion engine that recognizes the user's emotions, means for generating and providing the prediction results to the user, and means for adjusting the display method of the prediction results based on the user's emotions. This makes it easier to understand the prediction results and makes it possible to propose optimal sales measures based on the user's emotional state. Furthermore, in physical stores, customized customer service and product suggestions based on customer emotions can be provided, improving customer satisfaction.

[1591] "Past shipping data" refers to information about shipments that the system has recorded in the past.

[1592] "Inventory data" is information describing current and past inventory status.

[1593] "Sales data" refers to information relating to sales, such as product sales records and customer information.

[1594] "Means of input" refers to the interface or method by which a user provides data to the system.

[1595] "Means for receiving data and storing it in a database" refers to the method or infrastructure by which the system receives input data and stores it in a database.

[1596] A "generative AI model" is an artificial intelligence model designed to make predictions and judgments based on large amounts of data.

[1597] A "means of forecasting" is a method or process for calculating future shipment quantities, etc. based on input data.

[1598] An "emotion engine" is a technology or algorithm that analyzes a user's facial expressions and voice and recognizes their emotions.

[1599] "Analytical tools" are methods and tools used to analyze data and information and find meaning.

[1600] The "means for generating a prediction result and providing it to a user" refers to a method for creating predicted information and displaying or notifying it to a user.

[1601] The "means for adjusting the display method of the prediction result based on the emotion" is a method for changing the format and content of the information to be displayed depending on the emotional state of the user.

[1602] The "means for generating optimal sales measures" is a method for devising the most effective sales strategy based on prediction results and emotional data.

[1603] A "means for simulating the effectiveness of sales measures" is a method for estimating in advance how successful a proposed sales strategy will be.

[1604] "Means for providing simulation results to users" refers to processes and tools for presenting the results of the simulation to users.

[1605] "Means for retraining a predictive model based on new data" refers to a method for updating an existing predictive model using newly obtained data to improve its accuracy.

[1606] The "means for generating improved prediction results using a retrained prediction model" is a process for using an updated prediction model to derive more accurate prediction results.

[1607] This invention provides a customer service support system that responds to customer emotions in brick-and-mortar stores. The system includes a means for inputting past shipping data, inventory data, and sales data, and a means for receiving this data and storing it in a database. Each of these means and the operation of the system are described in detail below.

[1608] The server receives past shipping data, inventory data, and sales data and stores it in a database. Users provide this data by uploading it in CSV or Excel file format. The server receives the uploaded data and stores it in a database. This provides the basis for the data used in the next steps.

[1609] Next, the server uses a generative AI model to predict future shipment quantities from the data stored in the database. A large amount of past data is used to train the AI ​​model. The prediction results are displayed in graphs and tables on a dashboard and provided to the user. This predictive model is retrained each time new data is input, improving its prediction accuracy. The server manages this entire process.

[1610] The smart glasses are also equipped with an emotion engine that recognizes the user's emotions in real time. This emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses. The captured data is sent to a server and analyzed in real time. The analyzed emotion data is used to adjust the way prediction results are displayed based on the user's emotional state.

[1611] For example, if a salesperson wearing smart glasses analyzes a customer's emotional state and determines that the customer is feeling "stressed," the system can use that information to simplify product explanations or display messages to reassure the customer. If the customer is feeling "happy," a message suggesting an upsell product will be displayed.

[1612] Based on the analysis results of this emotion engine, the server also proposes optimal sales strategies. These proposals are adjusted taking into account the user's emotions, so if the user is feeling anxious, for example, the server will prioritize sales strategies with less risk.

[1613] Consider the following scenario as a concrete example: Customer A is shopping in a store. Salesperson B uses smart glasses to observe Customer A and analyzes his / her emotions from his / her facial expressions and voice. If Customer A is recognized as "happy," a "new product suggestion" will appear on the display of Salesperson B's glasses, and Salesperson B will suggest, "Please take a look at these new products."

[1614] Example prompt sentence:

[1615] "Implement a smart glasses application that analyzes customer emotions in real time and provides personalized product recommendations and customer service based on those emotions. If the customer is recognized as 'happy,' the glasses will display a message suggesting new products to the store clerk, who will then make the recommendation to the customer."

[1616] In this way, the present invention adjusts prediction results and sales strategies based on user emotions, thereby improving customer satisfaction in physical stores.

[1617] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1618] Step 1:

[1619] Users upload past shipping data, inventory data, and sales data in CSV or Excel file format through the system's data input screen. The input data is used to forecast past shipments and improve the accuracy of the results. This data is sent from the user's device.

[1620] Step 2:

[1621] The server receives the data uploaded by the user and stores it in a database. The input data is used for subsequent data analysis and predictive model training. The database stores various data categories (shipment data, inventory data, sales data) appropriately.

[1622] Step 3:

[1623] The server trains the generative AI model using past shipping, inventory, and sales data stored in the database. During this process, the data is processed (for example, missing value completion, data standardization, etc.) for use as training data. Meaningful features are extracted from the input data and used to generate the AI ​​model.

[1624] Step 4:

[1625] Using the generative AI model, the server predicts future shipment quantities. New input data is fed into the model to obtain predictions. These predictions are then converted into graphs and tables.

[1626] Step 5:

[1627] The server provides the prediction results to the user, and displays them in an easy-to-understand dashboard for easy access by the user.

[1628] Step 6:

[1629] The emotion engine captures the user's facial expressions and voice through the camera and microphone built into the smart glasses, and transmits this data to the server in real time. This data becomes input data for emotion recognition.

[1630] Step 7:

[1631] The server analyzes the acquired emotional data using an emotion engine. It identifies the user's emotional state using facial expression recognition algorithms and voice analysis algorithms. The analysis results (e.g., stress, joy, etc.) are obtained.

[1632] Step 8:

[1633] The server adjusts the way predictions are displayed based on the emotional data. For example, if the user is feeling stressed, it simplifies the prediction or displays a reassuring message. This information is reflected on the smart glasses display or the device screen.

[1634] Step 9:

[1635] The server generates optimal sales strategies based on the prediction results and emotion data. It then simulates the effectiveness of the generated sales strategies and provides the results to the user. The simulation also includes risk assessment and profit forecasting, providing the user with detailed analysis results.

[1636] Step 10:

[1637] Every time a user periodically uploads new shipping or sales data, the server updates the database with this data and retrains the predictive model. Emotional data is also incorporated into the retraining process to improve the accuracy of the predictive model. The prediction results provided to users are always highly accurate and based on the latest data.

[1638] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1639] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1640] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1641] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1642] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1643] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1644] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1645] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1646] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1647] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1648] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1649] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1650] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1651] 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.

[1652] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1653] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1654] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1655] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1656] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1657] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1658] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1659] The following is further disclosed regarding the above embodiment.

[1660] (Claim 1)

[1661] A means of inputting past shipping data, inventory data, and sales data;

[1662] means for receiving said data and storing it in a database;

[1663] A means of predicting future shipment quantities from input data using a generative AI model;

[1664] means for generating and providing the prediction result to a user;

[1665] A system including:

[1666] (Claim 2)

[1667] means for generating an optimal sales measure based on the prediction result;

[1668] means for simulating the effect of the sales measures;

[1669] means for providing the simulation results to a user;

[1670] The system of claim 1 further comprising:

[1671] (Claim 3)

[1672] A means of periodically entering new shipping and sales data;

[1673] means for receiving the new data and updating the database;

[1674] means for retraining a predictive model based on the new data;

[1675] a means for generating and providing to a user an improved prediction result using the retrained prediction model;

[1676] The system of claim 1 further comprising:

[1677] "Example 1"

[1678] (Claim 1)

[1679] a means for a user to input historical data;

[1680] a means for receiving the data, storing the data in a database, and managing the data in a unified manner;

[1681] A means of predicting future shipment quantities from input data using a generative AI model;

[1682] a means for visualizing the prediction result and providing it to a user;

[1683] A system including:

[1684] (Claim 2)

[1685] means for generating an optimal measure based on the prediction result;

[1686] A means for simulating the effect of the measures;

[1687] means for providing the simulation results to a user;

[1688] The system of claim 1 further comprising:

[1689] (Claim 3)

[1690] A means of periodically entering new shipping and sales data;

[1691] means for receiving the new data and updating the database;

[1692] means for retraining a predictive model based on the new data;

[1693] a means for generating and providing to a user an improved prediction result using the retrained prediction model;

[1694] The system of claim 1 further comprising:

[1695] "Application Example 1"

[1696] (Claim 1)

[1697] A means of inputting past shipping data, inventory data, and sales data;

[1698] means for receiving said data and storing it in a database;

[1699] A means of predicting future shipment quantities from input data using a generative AI model;

[1700] means for generating and providing the prediction result to a user;

[1701] A way to check shipping forecast data in real time using a smart device,

[1702] A method to take photos of past shipping data and inventory data and input the data using OCR technology.

[1703] A system including:

[1704] (Claim 2)

[1705] means for generating an optimal sales measure based on the prediction result;

[1706] means for simulating the effect of the sales measures;

[1707] means for providing the simulation results to a user;

[1708] A means to obtain information in real time using a voice assistant,

[1709] a means for notifying important inventory fluctuations and measures based on the prediction results;

[1710] The system of claim 1 further comprising:

[1711] (Claim 3)

[1712] A means of periodically entering new shipping and sales data;

[1713] means for receiving the new data and updating the database;

[1714] means for retraining a predictive model based on the new data;

[1715] a means for generating and providing to a user an improved prediction result using the retrained prediction model;

[1716] A means of obtaining forecast data and sales strategies using prompt statements,

[1717] The system of claim 1 further comprising:

[1718] "Example 2: Combining Emotion Engines"

[1719] (Claim 1)

[1720] A means of inputting past shipping data, inventory data, and sales data;

[1721] means for receiving said data and storing it in a database;

[1722] A means of predicting future shipment quantities from input data using a generative AI model;

[1723] A means of converting the prediction results into graphs and tables and providing them to users;

[1724] A means for acquiring emotion data using an emotion engine that recognizes the emotion of a user;

[1725] means for analyzing the emotion data and adjusting the display method of the prediction result according to the state of the user;

[1726] A system including:

[1727] (Claim 2)

[1728] A means for generating optimal sales measures based on the prediction results;

[1729] A means to optimize sales strategies by taking into account emotional data,

[1730] A means for simulating the effects of sales measures and providing the results to users;

[1731] 10. The system of claim 1.

[1732] (Claim 3)

[1733] A means of periodically entering new shipping and sales data;

[1734] a means for receiving new data and updating the database;

[1735] A means to retrain predictive models on new data; and

[1736] A means for generating and providing improved prediction results to users by utilizing emotion data for retraining;

[1737] 10. The system of claim 1.

[1738] "Application example 2 when combining emotion engines"

[1739] (Claim 1)

[1740] A means of inputting past shipping data, inventory data, and sales data;

[1741] means for receiving said data and storing it in a database;

[1742] A means of predicting future shipment quantities from input data using a generative AI model;

[1743] an analyzing means using an emotion engine that recognizes the user's emotion;

[1744] means for generating and providing the prediction result to a user;

[1745] A means for adjusting the display method of the prediction result based on the user's emotion;

[1746] A system including:

[1747] (Claim 2)

[1748] means for generating an optimal sales measure based on the prediction result;

[1749] means for simulating the effect of the sales measures;

[1750] means for providing the simulation results to a user;

[1751] A means for proposing sales measures taking into account user emotional data;

[1752] The system of claim 1 further comprising:

[1753] (Claim 3)

[1754] A means of periodically entering new shipping and sales data;

[1755] means for receiving the new data and updating the database;

[1756] means for retraining a predictive model based on the new data;

[1757] A means to retrain the predictive model using user sentiment data as well;

[1758] a means for generating and providing to a user an improved prediction result using the retrained prediction model;

[1759] The system of claim 1 further comprising: [Explanation of symbols]

[1760] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of inputting past shipping data, inventory data, and sales data; means for receiving said data and storing it in a database; A means of predicting future shipment quantities from input data using a generative AI model; means for generating and providing the prediction result to a user; A system including:

2. means for generating an optimal sales measure based on the prediction result; means for simulating the effect of the sales measures; means for providing the simulation results to a user; The system of claim 1 further comprising:

3. A means of periodically entering new shipping and sales data; means for receiving the new data and updating the database; means for retraining a predictive model based on the new data; a means for generating and providing to a user an improved prediction result using the retrained prediction model; The system of claim 1 further comprising:

Images