system

Abstract

We provide the system. [Solution] A means of collecting past sales history data and real-time data, Methods for preprocessing and normalizing the collected data, A means of analyzing preprocessed data using a generative AI model to perform demand forecasting, A means of proposing inventory management and supply plans based on predicted demand, A means for displaying and referencing prediction results in conjunction with a supply chain management system, A means to evaluate the accuracy of predictions and improve the model based on feedback, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Inventory management in enterprises has problems such as inefficiencies in business operations and increased costs due to excessive inventory or inventory shortages. Such problems are particularly serious in industries with large fluctuations in demand. In addition, conventional demand forecasting methods rely on past data and often cannot adequately respond to rapid market changes. Furthermore, there is a lack of systems that support quick and effective decision-making according to the predicted demand, making it difficult to optimize the entire supply chain. In response to these problems, there is a need for a method that enables accurate demand forecasting and improves the efficiency of inventory management and the supply chain.

Means for Solving the Problems

[0005] This invention provides a system that collects historical sales data and real-time data and performs demand forecasting using a generative AI model. Specifically, it predicts future demand by preprocessing and normalizing the collected data and analyzing it using a generative AI model. It also proposes inventory management and supply plans based on the forecast results and visualizes them in conjunction with a supply chain management system. Furthermore, by evaluating the accuracy of the forecast and building a feedback loop to improve the generative AI model, it enables rapid response to fluctuations in demand and optimization of the entire supply chain. This provides a system that achieves cost reduction and operational efficiency.

[0006] "Sales history data" refers to data that records information about past sales activities, showing how long a product or service was sold, in which region, and in what quantity.

[0007] "Real-time data" refers to data that reflects the current or most recent situation and is updated instantly to provide the most up-to-date information at all times.

[0008] A "generative AI model" is a collection of algorithms that use artificial intelligence technology to generate and analyze data, enabling data processing and prediction tailored to specific purposes.

[0009] "Inventory management" is the process of maintaining the inventory of goods within a company or organization and adjusting the supply to be in the appropriate quantity and at the right time.

[0010] A "supply chain management system" is a system that manages the entire process from product production to delivery to the consumer, and is a means of achieving an efficient supply process.

[0011] A "feedback loop" is a process that uses the output of a system as input again to continuously improve the performance and accuracy of the system.

[0012] "Demand forecasting" is the process of predicting future demand for products and services in the market, and is used in developing sales and production plans. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

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

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

[0019] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

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

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

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

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

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

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

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

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

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

[0034] The system of this invention operates through the interaction of a server, terminals, and users. First, the server collects sales history data and real-time data from databases and APIs both inside and outside the company. This enables the rapid acquisition of necessary information. The collected data is pre-processed by the server into an appropriate format and shaped for analysis.

[0035] The server analyzes data formatted using a generative AI model to predict future demand. The AI ​​model considers past sales trends and market factors, enabling it to capture demand fluctuations with high accuracy. The predicted demand data is transmitted from the server to the supply chain management system and displayed in real time on a dashboard on the terminal. This information is used for inventory management and sales strategy development.

[0036] The terminal makes suggestions for ordering and inventory adjustments based on the displayed demand forecast. Users can then develop specific action plans based on these suggestions. For example, if increased demand for a particular product is predicted, users can increase orders or plan store promotions based on the data provided by the server.

[0037] Furthermore, the server continuously monitors the accuracy of predictions, receives feedback based on actual user behavior and market trends, and updates the AI ​​model. This allows for flexible responses to future demand fluctuations while maintaining prediction accuracy. For example, if historical data predicts that demand for a certain product will accelerate during the summer, the server can analyze relevant data in advance and suggest actions such as adjusting inventory for that product.

[0038] This system enables users to prevent inventory shortages and excesses, achieve optimal supply chain management, and improve operational efficiency and reduce costs.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server collects sales history and real-time data from various databases and APIs within the enterprise. This includes information on product sales history, inventory status, and distribution channels. Data collection is performed in a consistent format, forming the basis for subsequent processing.

[0042] Step 2:

[0043] The server preprocesses the collected data. First, it scrutinizes the data to detect and remove incomplete or duplicate data. Next, it normalizes the data and converts it to a unified format. During this process, missing values ​​are imputed and outliers are corrected.

[0044] Step 3:

[0045] The server inputs the pre-processed data into the generating AI model and begins the analysis. This AI model uses machine learning algorithms to forecast demand, learning demand patterns from historical data. The AI ​​model then optimizes its prediction accuracy through iterative learning, with appropriate hyperparameters set.

[0046] Step 4:

[0047] The forecast results are transmitted from the server to the supply chain management system and displayed in real time on the user interface on the terminal. The terminal visualizes the demand forecast data in graphs and charts, helping users make quick decisions based on that information.

[0048] Step 5:

[0049] Users refer to the demand forecast displayed on their terminals to adjust inventory management and ordering plans. For example, if the forecast indicates increased demand for a particular product, users can consider taking specific actions, such as increasing the order quantity, on their terminals.

[0050] Step 6:

[0051] The server collects feedback based on user behavior and actual sales data. This feedback is used to update the AI ​​model, improving the accuracy of future predictions. This allows the system to continuously learn and adapt to changes in the sales environment.

[0052] (Example 1)

[0053] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0054] There is a challenge in improving the accuracy of demand forecasts while simultaneously streamlining inventory management and supply planning. In particular, because it is necessary to respond flexibly to forecast uncertainties and market fluctuations, conventional approaches are insufficient for effective supply network management.

[0055] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0056] In this invention, the server includes means for collecting sales history data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the data using a generative AI model and performing demand forecasting. This makes it possible to improve the accuracy of forecasts while making optimal ordering and inventory adjustment suggestions to the user.

[0057] "Sales history data" refers to data that shows information about the sale of goods and services in past transactions, including sales quantity, unit price, and date.

[0058] "Real-time data" refers to the latest information acquired at the present time, and is dynamic data acquired without any time delay.

[0059] A "generative AI model" is a machine learning model that uses artificial intelligence to train algorithms and perform predictions and classifications from large amounts of data.

[0060] A "supply network management system" is an information system designed to optimize inventory, logistics, and order processing within a supply chain.

[0061] A "user terminal" is a device that a user operates to obtain information, and includes devices such as personal computers, tablets, and smartphones.

[0062] "Feedback" refers to the information returned from a system that is used to evaluate its output or results and to improve or adjust them.

[0063] An "inventory adjustment proposal" is a suggestion that includes advice recommending increases, decreases, or replenishments of inventory based on projected demand.

[0064] This invention relates to an information processing system that optimizes inventory management and supply planning based on demand forecasting. This system efficiently forecasts demand and manages inventory through the collaboration of a server, terminals, and users.

[0065] First, the server collects historical sales data and real-time data from databases and APIs both inside and outside the company. In this process, the server uses scraping tools and database connection drivers to efficiently collect data. For example, servers are often built using Python libraries.

[0066] Next, the data collected by the server is preprocessed. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. This formats the data in a way that is suitable for analysis. Specifically, data processing libraries such as Pandas and NumPy are used.

[0067] Subsequently, the server analyzes the pre-processed data using a generative AI model to predict future demand. The AI ​​model is designed using frameworks such as TENSORFLOW® and PyTorch and includes advanced machine learning algorithms. The model takes into account monthly sales data and market trends to accurately predict future demand.

[0068] Demand forecast data is linked to a supply network management system via a server and displayed on the terminal in real time. The terminal visualizes this data as a dashboard, presenting it in the form of graphs and tables in an easy-to-understand format for the user. It is often built as a browser-based application.

[0069] Based on the forecasts displayed on the terminal, users can formulate specific action plans based on the ordering and inventory adjustment suggestions provided by the server. In particular, by accepting the inventory recommendations suggested by the server, users can prevent inventory shortages and excesses.

[0070] Furthermore, the results of user actions are sent to the server as feedback and used as data to improve the AI ​​model. This process allows the model to continuously learn and improve its accuracy.

[0071] As a concrete example, here is an example of a prompt message: "Consider sales data and market trends from the past three years, forecast demand for a specific product during the summer, and propose inventory management and promotional strategies." This prompt message allows the user to fully utilize the system's capabilities.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The server collects sales history data and real-time data from databases and APIs both inside and outside the company. Database connection information and API keys are required as input. The server uses this information and Python libraries to extract the data. The retrieved data is stored in the server's temporary storage as output. Specifically, the server is scheduled to perform data collection tasks daily.

[0075] Step 2:

[0076] The server preprocesses the collected data. It uses the raw data collected in step 1 as input. It performs data cleansing using the Pandas library to impute missing values ​​and remove outliers. The output is a clean dataset in a format suitable for analysis. Specifically, the server applies outlier detection criteria and filters out unnecessary data.

[0077] Step 3:

[0078] The server inputs pre-processed data into a generating AI model to predict demand. A formatted dataset is required as input. The AI ​​model is trained using TensorFlow and predicts future demand by analyzing historical data and market trend patterns. The output is predicted demand data. Specifically, the server processes multiple datasets in batches, running them through the AI ​​model in parallel.

[0079] Step 4:

[0080] The server prepares to transmit the predicted demand data to the supply network management system and display it on the terminal. The demand forecast data obtained in step 3 is used as input. The server sends this data to the supply management system via API, updating the database in real time. The output is updated supply plan data. Specifically, the server converts the data into a specific format and synchronizes it with the system over the network.

[0081] Step 5:

[0082] The terminal displays supply plan data sent from the server on a dashboard. It receives demand forecast data from the server as input. The terminal launches a browser-based application, presenting information to the user visually through graphs and tables. The output provides user-understandable, visualized information. Specifically, the terminal has an automatic update function, reflecting the latest data in a timely manner.

[0083] Step 6:

[0084] The user reviews proposals based on demand forecasts and develops a concrete action plan. The input is demand forecast information displayed on the terminal. Based on this information, the user adjusts negotiations with suppliers and sales promotion activities. The output is an optimized ordering plan and inventory strategy. In terms of specific actions, the user approves proposals on the system via the terminal and takes specific actions.

[0085] Step 7:

[0086] The server receives user execution results as feedback and uses them to improve the accuracy of the AI ​​model. As input, it collects user behavior results and market response data. The server adds this data to the AI ​​model's training data to improve the model. As output, a more accurate AI model is generated. Specifically, the server periodically retrains the AI ​​model to optimize its performance.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Modern logistics management requires a rapid and appropriate response to fluctuations in demand. However, conventional systems suffer from insufficient accuracy in demand forecasting and inability to efficiently propose inventory adjustments based on that forecasting. This results in excess or shortages of inventory, ultimately leading to decreased operational efficiency of logistics centers and increased costs.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for collecting historical sales data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the preprocessed data using a generative AI model to forecast demand. This enables highly accurate forecasting of demand fluctuations and rapid product adjustments in accordance with inventory levels.

[0092] "Sales history data" refers to records of sales activities conducted in the past.

[0093] "Real-time data" refers to immediate information that reflects the current situation.

[0094] "Preprocessing" refers to the preparatory work required to convert data into a format suitable for analysis.

[0095] "Normalization" is the process of standardizing data that exists on different scales to a common scale.

[0096] A "generative AI model" is an algorithmic model based on artificial intelligence technology that analyzes data and generates results according to a specific purpose.

[0097] "Demand forecasting" is the process of estimating the future demand for a product or service.

[0098] "Inventory management" is a general term for planning and controlling measures to maintain appropriate inventory levels.

[0099] A "supply plan" is the process of formulating the necessary supply quantity and timing based on demand forecasts.

[0100] "Product adjustment" refers to modifying the supply volume of a product in response to fluctuations in market demand.

[0101] An "information processing device" is a device used for calculating, storing, and transferring data.

[0102] "Supply chain management" is the process of effectively managing the entire flow of goods, from production to consumption.

[0103] "Feedback" refers to information that is re-entered based on the system's output results and used to improve the system.

[0104] The server effectively collects historical sales data and real-time data from multiple databases and APIs both inside and outside the company. This process requires infrastructure that leverages cloud computing technology to rapidly process large volumes of data.

[0105] The collected data is preprocessed by the server and converted into a standardized format. This preprocessing is performed using data processing software such as pandas and NumPy, which prepares the data in a format suitable for AI analysis.

[0106] Next, the server analyzes the pre-processed data using a generative AI model to forecast demand. This generative AI model uses machine learning libraries such as scikit-learn and TensorFlow to make predictions that take into account past sales trends and market factors. The forecasted demand data is sent from the server to an information processing device and visualized on the user's terminal. For example, a logistics center manager can use this information to make decisions regarding product adjustments.

[0107] The terminal application used by users provides relevant suggestions based on predicted demand, contributing to inventory adjustments and supply planning. This information is displayed in real time, supporting rapid decision-making. On the information processing device, users can intuitively analyze data using a visual dashboard.

[0108] Furthermore, the server receives feedback from actual user actions and market trends to continuously update the AI ​​model, thereby improving prediction accuracy. This increases the reliability of the predictions and enables it to respond to future demand fluctuations.

[0109] An example of a prompt for a generative AI model is: "Consider historical sales data and current market trends to generate a demand forecast for the next month and output suggestions to help manage inventory at the logistics center." Based on this prompt, the model performs highly accurate data analysis and provides useful information to the user.

[0110] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0111] Step 1:

[0112] The server collects historical sales data and real-time data from internal and external databases and APIs. Inputs are database queries and API requests, and outputs are raw sales and market data. This operation involves using database connection libraries to retrieve data quickly and in a structured format.

[0113] Step 2:

[0114] The server preprocesses and normalizes the collected data. The input is the raw data collected in step 1, and the output is data formatted for use with the AI ​​model. The data undergoes data transformations such as imputation of missing values, handling of outliers, and scaling using pandas or NumPy.

[0115] Step 3:

[0116] The server analyzes preprocessed data using a generative AI model and performs demand forecasting. The input is the data processed in step 2, and the output is the resulting demand forecast data. Using libraries such as scikit-learn and TensorFlow, the model learns past data patterns and performs calculations to predict future demand.

[0117] Step 4:

[0118] The server transmits the demand forecast results to the information processing device, where they are visualized on the user's terminal. The input is the demand forecast data obtained in step 3, and the output is visualized data displayed on a graphical user interface. This allows the user to intuitively analyze the data through the dashboard and supports their decision-making.

[0119] Step 5:

[0120] The user's device generates inventory adjustment and supply plan suggestions based on predicted demand. The input is the visualization data displayed in step 4, and the output is specific product adjustment and supply strategy suggestions. Automated alerts and recommended actions are provided, allowing the user to take immediate, concrete action.

[0121] Step 6:

[0122] The server analyzes user behavior and market changes to generate feedback and improve the accuracy of the generated AI model. The input is actual sales data and user feedback, and the output is the updated AI model. Here, the AI ​​model adapts to the real world through a continuous learning process.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention is a system that combines a demand forecasting system with an emotion engine that recognizes user emotions. First, the server collects sales history data and real-time data from databases both inside and outside the company. This prepares the basic data necessary for demand forecasting. The collected data is preprocessed, such as through normalization, and formatted to be suitable for analysis.

[0125] Using a generative AI model, the server analyzes pre-processed data and predicts future demand. The AI ​​model learns patterns from historical data and optimizes prediction accuracy. This predicted data is used by the server to propose inventory management and supply chain planning.

[0126] Furthermore, the user's device has an emotion engine built in. This emotion engine can recognize emotions from the user's input and actions and analyze the user's response. For example, if the emotion engine recognizes that the user is dissatisfied with the prediction results, it can provide an interface that takes the user's emotions into consideration and offer different suggestions.

[0127] The analysis results from the emotion engine are sent to the server as feedback, and the generated AI model is improved based on this feedback. This allows the model to reflect user opinions and enable more appropriate predictions and suggestions. For example, the emotion engine can detect user anxiety and readjust the supply plan to be more cautious.

[0128] Thus, by integrating emotion understanding and demand forecasting, this invention enables more rational and reliable supply chain management for users, thereby improving corporate operational efficiency and customer satisfaction.

[0129] The following describes the processing flow.

[0130] Step 1:

[0131] The server collects historical and real-time sales data from the company's databases and APIs. This provides a wide range of information about sales trends and current market conditions. The data is collected in a consistent format and prepared for subsequent analysis.

[0132] Step 2:

[0133] The server preprocesses the collected data. It performs data cleaning, supplements missing data, and removes duplicate data. Next, it normalizes the data and converts it into a unified format for analysis, ensuring processing accuracy and speed.

[0134] Step 3:

[0135] The server inputs the pre-processed data into a generating AI model and begins the analysis. This model is tuned using machine learning algorithms to maximize prediction accuracy and has the ability to forecast future demand based on sales history and market factors.

[0136] Step 4:

[0137] Based on predicted demand, the server generates inventory management and supply plan suggestions. These suggestions guide the implementation of an efficient supply chain and optimize the company's resource management.

[0138] Step 5:

[0139] The terminal displays prediction results and inventory management suggestions in the user interface. Here, the emotion engine monitors the user's reactions and acquires emotion data. The terminal analyzes emotions based on user input and facial recognition data, etc., and determines how the user is reacting to the displayed content.

[0140] Step 6:

[0141] The user's reactions, recognized by the emotion engine, are sent to the server, where this information is fed back to the generating AI model. The server uses this feedback to readjust the AI ​​model, enabling it to reflect user expectations and frustrations in future predictions.

[0142] Step 7:

[0143] Users can evaluate the emotionally sensitive supply plan displayed on the device and manually adjust it as needed. For example, if the emotion engine detects that the user is feeling anxious, the device will provide more detailed explanations and additional information to enhance the user's sense of security.

[0144] Through the above process, the system takes user sentiment into consideration, responds promptly to demand fluctuations, and supports the efficient management of a company's supply chain.

[0145] (Example 2)

[0146] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0147] Traditional demand forecasting systems were unable to adjust their forecasts to reflect consumer sentiment, making it difficult to respond quickly to changes in consumer trends. Furthermore, there was a lack of efficient methods for improving AI algorithms using feedback. This left challenges in both usability and forecasting accuracy.

[0148] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0149] In this invention, the server includes means for collecting historical time-series data and real-time information, means for preprocessing and normalizing the collected information, means for analyzing the preprocessed information using a generative AI algorithm and making consumption predictions, means for recognizing the user's psychology using an emotion analysis mechanism and sending it to the server as feedback, and means for adjusting the interface based on the user's emotions and presenting different suggestions. This enables demand forecasting that takes user emotions into account and improvement of the AI ​​algorithm using feedback.

[0150] "Time-series data" refers to information recorded in chronological order of specific phenomena or actions, and is used for analyzing past sales history and trends.

[0151] "Real-time information" refers to timely data obtained based on the current situation and recent events.

[0152] "Preprocessing" refers to a series of processes that format raw data into a form suitable for analysis, including imputation of missing values ​​and data normalization.

[0153] "Normalization" is a data processing technique that unifies the scale of data to improve the accuracy and efficiency of analysis.

[0154] A "generative AI algorithm" is a statistical model or computer program that uses machine learning techniques to learn patterns and predict future demand.

[0155] "Consumption forecasting" is the process of estimating future demand for goods based on past data and trends, and it forms the basis for resource management and supply planning.

[0156] An "emotion analysis mechanism" is a technology that recognizes and understands a user's psychological state based on their input and actions, and is an element that adjusts the responsiveness of the system.

[0157] "Interface adjustment" refers to the act of customizing the display and operating environment of a system or application in response to user emotions and feedback.

[0158] This system is designed to improve user-involved demand forecasting. First, the server accesses internal and external information sources to collect time-series and real-time data. This information is obtained through database queries and APIs. The collected data is preprocessed and normalized using data processing tools such as the "Pandas" library. This process includes imputing missing values, scaling, and formatting.

[0159] Next, the server uses generative AI algorithms such as TensorFlow and PyTorch to perform demand forecasting using the pre-processed data. By modeling consumption patterns from past sales data and related information, it is possible to predict future demand with high accuracy. The forecast results are immediately reflected in the supply chain plan and inventory management, which are updated instantly.

[0160] Meanwhile, the user's device incorporates an emotion analysis mechanism that utilizes natural language processing. This mechanism analyzes the user's input and operations, and understands the user's psychological state from reactions such as "This prediction result is unacceptable." Models such as "OpenAI®" are used for emotion analysis, and the interface is adjusted to be more responsive to the user's emotions.

[0161] As a concrete example, when the program is executed, the server inputs a prompt message to the generated AI model such as, "Based on this month's sales trends, predict next month's demand," and the actual demand forecast is performed. Such prompts allow the server to obtain accurate forecast output.

[0162] Finally, the server records user feedback and continuously improves the generating AI algorithm. This ensures that the entire system maintains high predictive accuracy and a high quality user experience.

[0163] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0164] Step 1:

[0165] The server collects historical time-series data and real-time information from internal and external sources within the company. It connects to databases and retrieves new data through queries to gather the necessary information. The input is the query conditions, and the output is the collected raw data. This data includes sales history and trend information.

[0166] Step 2:

[0167] The server preprocesses and normalizes the collected data. It uses the "Pandas" library to impute missing values, convert data types, and scale the data. The input is the raw data obtained in step 1, and the output is formatted data suitable for analysis. This ensures data consistency.

[0168] Step 3:

[0169] The server uses a generative AI model to analyze preprocessed data and forecast demand. It uses TensorFlow and PyTorch to learn past patterns and predict future demand. The input is the formatted data from step 2, and the output is the demand forecast result. This result is used in supply planning.

[0170] Step 4:

[0171] The device monitors user input and actions, and recognizes the user's emotions through an emotion analysis mechanism. Using OpenAI's natural language processing technology, it extracts user feedback as emotional information. Input is user text input and action information, and output is the analyzed emotional information. The interface is adjusted based on this information.

[0172] Step 5:

[0173] The server receives the results of the emotion analysis mechanism as feedback. Based on this, it improves the generative AI model. The model is retrained and the prediction algorithm is updated. The input is the emotion information from step 4, and the output is the improved AI model. This improves the accuracy of the predictions.

[0174] Step 6:

[0175] The server ultimately integrates demand forecast results and user feedback to update the supply chain plan and present it to the user. The plan includes inventory management and resource allocation, forming the foundation for improving operational efficiency. Inputs are forecast results and sentiment feedback, and output is the adjusted supply chain plan.

[0176] (Application Example 2)

[0177] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0178] Conventional demand forecasting systems could predict product demand and manage supply chains based on historical and real-time data, but they lacked suggestions that reflected user emotions. As a result, it was difficult to maximize user satisfaction and purchasing intent. This invention aims to improve the user experience by realizing demand forecasting and purchasing suggestions that take user emotions into account.

[0179] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0180] In this invention, the server includes means for collecting historical sales data and real-time data; means for preprocessing and normalizing the collected data; means for analyzing the preprocessed data using a generative AI model and making demand forecasts; means for proposing inventory management and supply plans based on the forecasted demand; means for displaying and referencing the forecast results in cooperation with a supply chain management system; means for evaluating the accuracy of the forecast and improving the model based on feedback; means for recognizing the user's emotional state using an emotion analysis engine; and means for adapting purchase suggestions based on the user's emotional state. This enables appropriate product suggestions that take into account the user's emotions, thereby improving the user experience and increasing purchasing intent.

[0181] "Sales history data" refers to data that shows records of past sales, quantities, and consumer purchasing activities for a product.

[0182] "Real-time data" refers to data that shows the latest information and records based on the current situation.

[0183] "Preprocessing" refers to the process of normalizing data for analysis and converting it into a format suitable for analysis.

[0184] A "generative AI model" is an artificial intelligence framework that uses data-based algorithms to analyze new data, learn patterns, and make predictions.

[0185] "Demand forecasting" is the process of predicting future demand for a product, and it is important for optimizing the efficiency of the supply chain.

[0186] "Inventory management" refers to management activities aimed at maintaining a balance between the supply and consumption of goods, and preventing situations of surplus or shortage.

[0187] A "supply plan" is a plan to ensure an efficient supply of goods in accordance with demand.

[0188] A "supply chain management system" is a system that optimizes the flow of goods and services and manages an organization's supply activities.

[0189] "Feedback" refers to a feedback loop that evaluates the accuracy of predictions in order to improve the model.

[0190] An "emotion analysis engine" is an engine that analyzes and understands a user's emotions based on their voice, behavior, facial expressions, etc.

[0191] A "purchase suggestion" is an activity that presents users with the most suitable purchase options, and these suggestions are based on predictive and sentiment data.

[0192] In this invention, a server, terminal, and user collaborate to build a system. The server collects sales history data and real-time data from numerous databases, and preprocesses and normalizes this data. The preprocessed data is sent to a generative AI model, where it learns patterns and performs demand forecasting. This AI model incorporates a machine learning algorithm using TensorFlow.

[0193] The server proposes inventory management and supply plans based on predicted demand. Furthermore, it integrates with supply chain management systems to display forecast results, making them accessible to stakeholders. The model's prediction accuracy is regularly evaluated, and feedback is used to improve the model.

[0194] The user's device has an emotion analysis engine installed. This engine uses the smartphone's or device's built-in camera and microphone to analyze the user's emotions from their facial expressions and voice tone. By using the OpenCV library and Google Cloud's emotion analysis API, it analyzes facial expressions and voice in real time to identify the user's emotional state.

[0195] This emotional state is sent to the server, which uses this information to modify the predictions of the generating AI model and provide the device with more optimized purchase suggestions. This information is used while the user is shopping in a store, allowing them to receive more personalized product suggestions.

[0196] As a concrete example, if a user shows dissatisfaction or lack of interest after listening to a product description in a store, the system analyzes that facial expression data and suggests a more appealing alternative product. Another example of a prompt message is, "If a customer shows dissatisfaction after listening to the product description, please suggest an alternative product." Such an implementation can improve the quality of the customer experience and stimulate purchasing intent.

[0197] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0198] Step 1:

[0199] The server collects sales history data and real-time data from multiple databases. Inputs are internal and external databases, and output is a raw dataset. The server accesses the databases using API calls and extracts the necessary data.

[0200] Step 2:

[0201] The server preprocesses and normalizes the collected data. The input is the raw dataset, and the output is the normalized dataset. The Python Pandas library is used to impute missing values ​​in the data and scale it to a consistent format.

[0202] Step 3:

[0203] The server generates a normalized dataset, inputs it into an AI model, and performs demand forecasting. The input is a normalized dataset, and the output is a forecast of future demand. A machine learning model built using TensorFlow learns patterns from the data and generates predictions.

[0204] Step 4:

[0205] The server generates inventory management and supply plan suggestions based on predicted demand. The input is the demand forecast, and the output is the inventory management and supply plan suggestions. An algorithm is used to calculate the optimal inventory levels and supply plan based on demand.

[0206] Step 5:

[0207] The server integrates with the supply chain management system, making forecast results visible and accessible to stakeholders. Inputs include demand forecast results and suggestions, while outputs include web dashboards and notification messages. The server provides visualizations using a web framework.

[0208] Step 6:

[0209] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone to recognize their emotional state. Input is real-time data from the camera and microphone, and output is the recognized emotional state. OpenCV and an emotion analysis API are combined to analyze both audio and video.

[0210] Step 7:

[0211] The device sends the recognized emotional state to the server. The input is emotional state data, and the output is the prediction result of the modified generative AI model. The server provides this data as feedback to the AI ​​model to improve its accuracy.

[0212] Step 8:

[0213] The server provides the terminal with purchase suggestions that take the customer's emotional state into account. The input is the modified prediction results and emotional state, and the output is a personalized purchase suggestion for the user. The server sends a notification to the user using the prompt message, "If the customer expresses dissatisfaction after hearing the product description, please suggest an alternative product."

[0214] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0215] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0216] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0217] [Second Embodiment]

[0218] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0219] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0220] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0221] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0222] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0223] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0224] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0225] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0226] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0227] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0228] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0229] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0230] The system of this invention operates through the interaction of a server, terminals, and users. First, the server collects sales history data and real-time data from databases and APIs both inside and outside the company. This enables the rapid acquisition of necessary information. The collected data is pre-processed by the server into an appropriate format and shaped for analysis.

[0231] The server analyzes data formatted using a generative AI model to predict future demand. The AI ​​model considers past sales trends and market factors, enabling it to capture demand fluctuations with high accuracy. The predicted demand data is transmitted from the server to the supply chain management system and displayed in real time on a dashboard on the terminal. This information is used for inventory management and sales strategy development.

[0232] The terminal makes suggestions for ordering and inventory adjustments based on the displayed demand forecast. Users can then develop specific action plans based on these suggestions. For example, if increased demand for a particular product is predicted, users can increase orders or plan store promotions based on the data provided by the server.

[0233] Furthermore, the server continuously monitors the accuracy of predictions, receives feedback based on actual user behavior and market trends, and updates the AI ​​model. This allows for flexible responses to future demand fluctuations while maintaining prediction accuracy. For example, if historical data predicts that demand for a certain product will accelerate during the summer, the server can analyze relevant data in advance and suggest actions such as adjusting inventory for that product.

[0234] This system enables users to prevent inventory shortages and excesses, achieve optimal supply chain management, and improve operational efficiency and reduce costs.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server collects sales history and real-time data from various databases and APIs within the enterprise. This includes information on product sales history, inventory status, and distribution channels. Data collection is performed in a consistent format, forming the basis for subsequent processing.

[0238] Step 2:

[0239] The server preprocesses the collected data. First, it scrutinizes the data to detect and remove incomplete or duplicate data. Next, it normalizes the data and converts it to a unified format. During this process, missing values ​​are imputed and outliers are corrected.

[0240] Step 3:

[0241] The server inputs the pre-processed data into the generating AI model and begins the analysis. This AI model uses machine learning algorithms to forecast demand, learning demand patterns from historical data. The AI ​​model then optimizes its prediction accuracy through iterative learning, with appropriate hyperparameters set.

[0242] Step 4:

[0243] The forecast results are transmitted from the server to the supply chain management system and displayed in real time on the user interface on the terminal. The terminal visualizes the demand forecast data in graphs and charts, helping users make quick decisions based on that information.

[0244] Step 5:

[0245] Users refer to the demand forecast displayed on their terminals to adjust inventory management and ordering plans. For example, if the forecast indicates increased demand for a particular product, users can consider taking specific actions, such as increasing the order quantity, on their terminals.

[0246] Step 6:

[0247] The server collects feedback based on user behavior and actual sales data. This feedback is used to update the AI ​​model, improving the accuracy of future predictions. This allows the system to continuously learn and adapt to changes in the sales environment.

[0248] (Example 1)

[0249] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0250] There is a challenge in improving the accuracy of demand forecasts while simultaneously streamlining inventory management and supply planning. In particular, because it is necessary to respond flexibly to forecast uncertainties and market fluctuations, conventional approaches are insufficient for effective supply network management.

[0251] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0252] In this invention, the server includes means for collecting sales history data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the data using a generative AI model and performing demand forecasting. This makes it possible to improve the accuracy of forecasts while making optimal ordering and inventory adjustment suggestions to the user.

[0253] "Sales history data" refers to data that shows information about the sale of goods and services in past transactions, including sales quantity, unit price, and date.

[0254] "Real-time data" refers to the latest information acquired at the present time, and is dynamic data acquired without any time delay.

[0255] A "generative AI model" is a machine learning model that uses artificial intelligence to train algorithms and perform predictions and classifications from large amounts of data.

[0256] A "supply network management system" is an information system designed to optimize inventory, logistics, and order processing within a supply chain.

[0257] A "user terminal" is a device that a user operates to obtain information, and includes devices such as personal computers, tablets, and smartphones.

[0258] "Feedback" refers to the information returned from a system that is used to evaluate its output or results and to improve or adjust them.

[0259] An "inventory adjustment proposal" is a suggestion that includes advice recommending increases, decreases, or replenishments of inventory based on projected demand.

[0260] This invention relates to an information processing system that optimizes inventory management and supply planning based on demand forecasting. This system efficiently forecasts demand and manages inventory through the collaboration of a server, terminals, and users.

[0261] First, the server collects historical sales data and real-time data from databases and APIs both inside and outside the company. In this process, the server uses scraping tools and database connection drivers to efficiently collect data. For example, servers are often built using Python libraries.

[0262] Next, the data collected by the server is preprocessed. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. This formats the data in a way that is suitable for analysis. Specifically, data processing libraries such as Pandas and NumPy are used.

[0263] Subsequently, the server analyzes the pre-processed data using a generative AI model to predict future demand. The AI ​​model is designed using frameworks such as TensorFlow and PyTorch and includes advanced machine learning algorithms. The model takes into account monthly sales data and market trends to accurately predict future demand.

[0264] Demand forecast data is linked to a supply network management system via a server and displayed on the terminal in real time. The terminal visualizes this data as a dashboard, presenting it in the form of graphs and tables in an easy-to-understand format for the user. It is often built as a browser-based application.

[0265] Based on the forecasts displayed on the terminal, users can formulate specific action plans based on the ordering and inventory adjustment suggestions provided by the server. In particular, by accepting the inventory recommendations suggested by the server, users can prevent inventory shortages and excesses.

[0266] Furthermore, the results of user actions are sent to the server as feedback and used as data to improve the AI ​​model. This process allows the model to continuously learn and improve its accuracy.

[0267] As a concrete example, here is an example of a prompt message: "Consider sales data and market trends from the past three years, forecast demand for a specific product during the summer, and propose inventory management and promotional strategies." This prompt message allows the user to fully utilize the system's capabilities.

[0268] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0269] Step 1:

[0270] The server collects sales history data and real-time data from databases and APIs both inside and outside the company. Database connection information and API keys are required as input. The server uses this information and Python libraries to extract the data. The retrieved data is stored in the server's temporary storage as output. Specifically, the server is scheduled to perform data collection tasks daily.

[0271] Step 2:

[0272] The server preprocesses the collected data. It uses the raw data collected in step 1 as input. It performs data cleansing using the Pandas library to impute missing values ​​and remove outliers. The output is a clean dataset in a format suitable for analysis. Specifically, the server applies outlier detection criteria and filters out unnecessary data.

[0273] Step 3:

[0274] The server inputs pre-processed data into a generating AI model to predict demand. A formatted dataset is required as input. The AI ​​model is trained using TensorFlow and predicts future demand by analyzing historical data and market trend patterns. The output is predicted demand data. Specifically, the server processes multiple datasets in batches, running them through the AI ​​model in parallel.

[0275] Step 4:

[0276] The server prepares to transmit the predicted demand data to the supply network management system and display it on the terminal. The demand forecast data obtained in step 3 is used as input. The server sends this data to the supply management system via API, updating the database in real time. The output is updated supply plan data. Specifically, the server converts the data into a specific format and synchronizes it with the system over the network.

[0277] Step 5:

[0278] The terminal displays the supply plan data sent from the server on the dashboard. As input, it receives demand prediction data from the server. The terminal launches a browser-based application and visually presents information to the user in the form of graphs and tables. As output, it provides visualized information that can be understood by the user. As a specific operation, the terminal has an automatic update function and timely reflects the latest data.

[0279] Step 6:

[0280] The user examines the proposal based on the demand prediction and formulates a specific action plan. As input, the user uses the demand prediction information displayed on the terminal. Based on this information, the user adjusts negotiations with suppliers and sales promotion activities. As output, an optimized order plan and inventory strategy are formed. As a specific operation, the user approves the proposal on the system through the terminal and initiates specific actions.

[0281] Step 7:

[0282] The server receives the user's execution results as feedback and utilizes them to improve the accuracy of the AI model. As input, it collects the user's action results and market reaction data. The server adds these data to the training data of the AI model and improves the model. As output, a more accurate AI model is generated. As a specific operation, the server retrains the AI model regularly to optimize its performance.

[0283] (Application Example 1)

[0284] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0285] In modern logistics management, it is required to respond quickly and appropriately to fluctuations in demand. However, in conventional systems, there are problems such as insufficient accuracy of demand forecasting and inefficient proposal of inventory adjustment based on it. As a result, overstocking and stock shortages occur, leading to a decline in the operating efficiency of the logistics center and an increase in costs.

[0286] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 1 is realized by the following respective means.

[0287] In this invention, the server includes means for collecting past sales history data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the preprocessed data using a generative AI model to perform demand forecasting. As a result, fluctuations in demand can be predicted with high accuracy, and rapid product adjustment according to the inventory situation becomes possible.

[0288] "Sales history data" is record information regarding past sales activities.

[0289] "Real-time data" is immediate information reflecting the current ongoing situation.

[0290] "Preprocessing" is preparatory work for converting data into a format suitable for data analysis.

[0291] "Normalization" is a process of arranging data on a common scale when the data exists on different scales.

[0292] "Generative AI model" is an algorithm model for analyzing data and generating results according to a specific purpose based on artificial intelligence technology.

[0293] "Demand forecasting" is to estimate the future demand volume of products and services.

[0294] "Inventory management" is a general term for planning and control to maintain an appropriate inventory level.

[0295] A "supply plan" is the process of formulating the necessary supply quantity and timing based on demand forecasts.

[0296] "Product adjustment" refers to modifying the supply volume of a product in response to fluctuations in market demand.

[0297] An "information processing device" is a device used for calculating, storing, and transferring data.

[0298] "Supply chain management" is the process of effectively managing the entire flow of goods, from production to consumption.

[0299] "Feedback" refers to information that is re-entered based on the system's output results and used to improve the system.

[0300] The server effectively collects historical sales data and real-time data from multiple databases and APIs both inside and outside the company. This process requires infrastructure that leverages cloud computing technology to rapidly process large volumes of data.

[0301] The collected data is preprocessed by the server and converted into a standardized format. This preprocessing is performed using data processing software such as pandas and NumPy, which prepares the data in a format suitable for AI analysis.

[0302] Next, the server analyzes the pre-processed data using a generative AI model to forecast demand. This generative AI model uses machine learning libraries such as scikit-learn and TensorFlow to make predictions that take into account past sales trends and market factors. The forecasted demand data is sent from the server to an information processing device and visualized on the user's terminal. For example, a logistics center manager can use this information to make decisions regarding product adjustments.

[0303] The terminal application used by the user makes relevant proposals based on the predicted demand and contributes to inventory adjustment and supply plan formulation. This information is displayed in real time to support rapid decision-making. On the information processing device, using a visual dashboard, the user can intuitively analyze the data.

[0304] Furthermore, the server receives the user's actual actions and market trends as feedback in order to improve the prediction accuracy and continuously update the AI model. This enhances the reliability of the prediction and enables it to cope with the next demand fluctuations.

[0305] As an example of the prompt sentence for the generative AI model, "Considering past sales data and current market trends, generate a demand prediction for the next month and output proposals useful for inventory management in the logistics center." can be cited. Based on this prompt, the model performs high-precision data analysis and provides useful information for the user.

[0306] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0307] Step 1:

[0308] The server collects past sales history data and real-time data from databases and APIs inside and outside the company. The input is a database query or an API request, and the output is sales and market data as raw data. This operation includes procedures for acquiring data in a rapid and structured format using a database connection library.

[0309] Step 2:

[0310] The server preprocesses the collected data and normalizes it. The input is the raw data collected in Step 1, and the output is data formatted in a form suitable for the AI model. The data undergoes data transformations such as filling in missing values, handling outliers, and scaling using pandas and NumPy.

[0311] Step 3:

[0312] The server analyzes preprocessed data using a generative AI model and performs demand forecasting. The input is the data processed in step 2, and the output is the resulting demand forecast data. Using libraries such as scikit-learn and TensorFlow, the model learns past data patterns and performs calculations to predict future demand.

[0313] Step 4:

[0314] The server transmits the demand forecast results to the information processing device, where they are visualized on the user's terminal. The input is the demand forecast data obtained in step 3, and the output is visualized data displayed on a graphical user interface. This allows the user to intuitively analyze the data through the dashboard and supports their decision-making.

[0315] Step 5:

[0316] The user's device generates inventory adjustment and supply plan suggestions based on predicted demand. The input is the visualization data displayed in step 4, and the output is specific product adjustment and supply strategy suggestions. Automated alerts and recommended actions are provided, allowing the user to take immediate, concrete action.

[0317] Step 6:

[0318] The server analyzes user behavior and market changes to generate feedback and improve the accuracy of the generated AI model. The input is actual sales data and user feedback, and the output is the updated AI model. Here, the AI ​​model adapts to the real world through a continuous learning process.

[0319] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0320] This invention is a system that combines a demand forecasting system with an emotion engine that recognizes user emotions. First, the server collects sales history data and real-time data from databases both inside and outside the company. This prepares the basic data necessary for demand forecasting. The collected data is preprocessed, such as through normalization, and formatted to be suitable for analysis.

[0321] Using a generative AI model, the server analyzes pre-processed data and predicts future demand. The AI ​​model learns patterns from historical data and optimizes prediction accuracy. This predicted data is used by the server to propose inventory management and supply chain planning.

[0322] Furthermore, the user's device has an emotion engine built in. This emotion engine can recognize emotions from the user's input and actions and analyze the user's response. For example, if the emotion engine recognizes that the user is dissatisfied with the prediction results, it can provide an interface that takes the user's emotions into consideration and offer different suggestions.

[0323] The analysis results from the emotion engine are sent to the server as feedback, and the generated AI model is improved based on this feedback. This allows the model to reflect user opinions and enable more appropriate predictions and suggestions. For example, the emotion engine can detect user anxiety and readjust the supply plan to be more cautious.

[0324] Thus, by integrating emotion understanding and demand forecasting, this invention enables more rational and reliable supply chain management for users, thereby improving corporate operational efficiency and customer satisfaction.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The server collects historical and real-time sales data from the company's databases and APIs. This provides a wide range of information about sales trends and current market conditions. The data is collected in a consistent format and prepared for subsequent analysis.

[0328] Step 2:

[0329] The server preprocesses the collected data. It performs data cleaning, supplements missing data, and removes duplicate data. Next, it normalizes the data and converts it into a unified format for analysis, ensuring processing accuracy and speed.

[0330] Step 3:

[0331] The server inputs the pre-processed data into a generating AI model and begins the analysis. This model is tuned using machine learning algorithms to maximize prediction accuracy and has the ability to forecast future demand based on sales history and market factors.

[0332] Step 4:

[0333] Based on predicted demand, the server generates inventory management and supply plan suggestions. These suggestions guide the implementation of an efficient supply chain and optimize the company's resource management.

[0334] Step 5:

[0335] The terminal displays prediction results and inventory management suggestions in the user interface. Here, the emotion engine monitors the user's reactions and acquires emotion data. The terminal analyzes emotions based on user input and facial recognition data, etc., and determines how the user is reacting to the displayed content.

[0336] Step 6:

[0337] The user's reactions, recognized by the emotion engine, are sent to the server, where this information is fed back to the generating AI model. The server uses this feedback to readjust the AI ​​model, enabling it to reflect user expectations and frustrations in future predictions.

[0338] Step 7:

[0339] Users can evaluate the emotionally sensitive supply plan displayed on the device and manually adjust it as needed. For example, if the emotion engine detects that the user is feeling anxious, the device will provide more detailed explanations and additional information to enhance the user's sense of security.

[0340] Through the above process, the system takes user sentiment into consideration, responds promptly to demand fluctuations, and supports the efficient management of a company's supply chain.

[0341] (Example 2)

[0342] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0343] Traditional demand forecasting systems were unable to adjust their forecasts to reflect consumer sentiment, making it difficult to respond quickly to changes in consumer trends. Furthermore, there was a lack of efficient methods for improving AI algorithms using feedback. This left challenges in both usability and forecasting accuracy.

[0344] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0345] In this invention, the server includes means for collecting historical time-series data and real-time information, means for preprocessing and normalizing the collected information, means for analyzing the preprocessed information using a generative AI algorithm and making consumption predictions, means for recognizing the user's psychology using an emotion analysis mechanism and sending it to the server as feedback, and means for adjusting the interface based on the user's emotions and presenting different suggestions. This enables demand forecasting that takes user emotions into account and improvement of the AI ​​algorithm using feedback.

[0346] "Time-series data" refers to information recorded in chronological order of specific phenomena or actions, and is used for analyzing past sales history and trends.

[0347] "Real-time information" refers to timely data obtained based on the current situation and recent events.

[0348] "Preprocessing" refers to a series of processes that format raw data into a form suitable for analysis, including imputation of missing values ​​and data normalization.

[0349] "Normalization" is a data processing technique that unifies the scale of data to improve the accuracy and efficiency of analysis.

[0350] A "generative AI algorithm" is a statistical model or computer program that uses machine learning techniques to learn patterns and predict future demand.

[0351] "Consumption forecasting" is the process of estimating future demand for goods based on past data and trends, and it forms the basis for resource management and supply planning.

[0352] An "emotion analysis mechanism" is a technology that recognizes and understands a user's psychological state based on their input and actions, and is an element that adjusts the responsiveness of the system.

[0353] "Interface adjustment" refers to the act of customizing the display and operating environment of a system or application in response to user emotions and feedback.

[0354] This system is designed to improve user-involved demand forecasting. First, the server accesses internal and external information sources to collect time-series and real-time data. This information is obtained through database queries and APIs. The collected data is preprocessed and normalized using data processing tools such as the "Pandas" library. This process includes imputing missing values, scaling, and formatting.

[0355] Next, the server uses generative AI algorithms such as TensorFlow and PyTorch to perform demand forecasting using the pre-processed data. By modeling consumption patterns from past sales data and related information, it is possible to predict future demand with high accuracy. The forecast results are immediately reflected in the supply chain plan and inventory management, which are updated instantly.

[0356] Meanwhile, the user's device incorporates an emotion analysis mechanism that utilizes natural language processing. This mechanism analyzes the user's input and actions, and understands the user's psychological state from reactions such as "This prediction result is unacceptable." Models like "OpenAI" are used for emotion analysis, and the interface is adjusted to be more responsive to the user's emotions.

[0357] As a concrete example, when the program is executed, the server inputs a prompt message to the generated AI model such as, "Based on this month's sales trends, predict next month's demand," and the actual demand forecast is performed. Such prompts allow the server to obtain accurate forecast output.

[0358] Finally, the server records user feedback and continuously improves the generating AI algorithm. This ensures that the entire system maintains high predictive accuracy and a high quality user experience.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1:

[0361] The server collects historical time-series data and real-time information from internal and external sources within the company. It connects to databases and retrieves new data through queries to gather the necessary information. The input is the query conditions, and the output is the collected raw data. This data includes sales history and trend information.

[0362] Step 2:

[0363] The server preprocesses and normalizes the collected data. It uses the "Pandas" library to impute missing values, convert data types, and scale the data. The input is the raw data obtained in step 1, and the output is formatted data suitable for analysis. This ensures data consistency.

[0364] Step 3:

[0365] The server uses a generative AI model to analyze preprocessed data and forecast demand. It uses TensorFlow and PyTorch to learn past patterns and predict future demand. The input is the formatted data from step 2, and the output is the demand forecast result. This result is used in supply planning.

[0366] Step 4:

[0367] The device monitors user input and actions, and recognizes the user's emotions through an emotion analysis mechanism. Using OpenAI's natural language processing technology, it extracts user feedback as emotional information. Input is user text input and action information, and output is the analyzed emotional information. The interface is adjusted based on this information.

[0368] Step 5:

[0369] The server receives the results of the emotion analysis mechanism as feedback. Based on this, it improves the generative AI model. The model is retrained and the prediction algorithm is updated. The input is the emotion information from step 4, and the output is the improved AI model. This improves the accuracy of the predictions.

[0370] Step 6:

[0371] The server ultimately integrates demand forecast results and user feedback to update the supply chain plan and present it to the user. The plan includes inventory management and resource allocation, forming the foundation for improving operational efficiency. Inputs are forecast results and sentiment feedback, and output is the adjusted supply chain plan.

[0372] (Application Example 2)

[0373] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0374] Conventional demand forecasting systems could predict product demand and manage supply chains based on historical and real-time data, but they lacked suggestions that reflected user emotions. As a result, it was difficult to maximize user satisfaction and purchasing intent. This invention aims to improve the user experience by realizing demand forecasting and purchasing suggestions that take user emotions into account.

[0375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0376] In this invention, the server includes means for collecting historical sales data and real-time data; means for preprocessing and normalizing the collected data; means for analyzing the preprocessed data using a generative AI model and making demand forecasts; means for proposing inventory management and supply plans based on the forecasted demand; means for displaying and referencing the forecast results in cooperation with a supply chain management system; means for evaluating the accuracy of the forecast and improving the model based on feedback; means for recognizing the user's emotional state using an emotion analysis engine; and means for adapting purchase suggestions based on the user's emotional state. This enables appropriate product suggestions that take into account the user's emotions, thereby improving the user experience and increasing purchasing intent.

[0377] "Sales history data" refers to data that shows records of past sales, quantities, and consumer purchasing activities for a product.

[0378] "Real-time data" refers to data that shows the latest information and records based on the current situation.

[0379] "Preprocessing" refers to the process of normalizing data for analysis and converting it into a format suitable for analysis.

[0380] A "generative AI model" is an artificial intelligence framework that uses data-based algorithms to analyze new data, learn patterns, and make predictions.

[0381] "Demand forecasting" is the process of predicting future demand for a product, and it is important for optimizing the efficiency of the supply chain.

[0382] "Inventory management" refers to management activities aimed at maintaining a balance between the supply and consumption of goods, and preventing situations of surplus or shortage.

[0383] A "supply plan" is a plan to ensure an efficient supply of goods in accordance with demand.

[0384] A "supply chain management system" is a system that optimizes the flow of goods and services and manages an organization's supply activities.

[0385] "Feedback" refers to a feedback loop that evaluates the accuracy of predictions in order to improve the model.

[0386] An "emotion analysis engine" is an engine that analyzes and understands a user's emotions based on their voice, behavior, facial expressions, etc.

[0387] A "purchase suggestion" is an activity that presents users with the most suitable purchase options, and these suggestions are based on predictive and sentiment data.

[0388] In this invention, a server, terminal, and user collaborate to build a system. The server collects sales history data and real-time data from numerous databases, and preprocesses and normalizes this data. The preprocessed data is sent to a generative AI model, where it learns patterns and performs demand forecasting. This AI model incorporates a machine learning algorithm using TensorFlow.

[0389] The server proposes inventory management and supply plans based on predicted demand. Furthermore, it integrates with supply chain management systems to display forecast results, making them accessible to stakeholders. The model's prediction accuracy is regularly evaluated, and feedback is used to improve the model.

[0390] The user's device has an emotion analysis engine installed. This engine uses the smartphone's or device's built-in camera and microphone to analyze the user's emotions from their facial expressions and voice tone. By using the OpenCV library and Google Cloud's emotion analysis API, it analyzes facial expressions and voice in real time to identify the user's emotional state.

[0391] This emotional state is sent to the server, which uses this information to modify the predictions of the generating AI model and provide the device with more optimized purchase suggestions. This information is used while the user is shopping in a store, allowing them to receive more personalized product suggestions.

[0392] As a concrete example, if a user shows dissatisfaction or lack of interest after listening to a product description in a store, the system analyzes that facial expression data and suggests a more appealing alternative product. Another example of a prompt message is, "If a customer shows dissatisfaction after listening to the product description, please suggest an alternative product." Such an implementation can improve the quality of the customer experience and stimulate purchasing intent.

[0393] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0394] Step 1:

[0395] The server collects sales history data and real-time data from multiple databases. Inputs are internal and external databases, and output is a raw dataset. The server accesses the databases using API calls and extracts the necessary data.

[0396] Step 2:

[0397] The server preprocesses and normalizes the collected data. The input is the raw dataset, and the output is the normalized dataset. The Python Pandas library is used to impute missing values ​​in the data and scale it to a consistent format.

[0398] Step 3:

[0399] The server generates a normalized dataset, inputs it into an AI model, and performs demand forecasting. The input is a normalized dataset, and the output is a forecast of future demand. A machine learning model built using TensorFlow learns patterns from the data and generates predictions.

[0400] Step 4:

[0401] The server generates inventory management and supply plan suggestions based on predicted demand. The input is the demand forecast, and the output is the inventory management and supply plan suggestions. An algorithm is used to calculate the optimal inventory levels and supply plan based on demand.

[0402] Step 5:

[0403] The server integrates with the supply chain management system, making forecast results visible and accessible to stakeholders. Inputs include demand forecast results and suggestions, while outputs include web dashboards and notification messages. The server provides visualizations using a web framework.

[0404] Step 6:

[0405] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone to recognize their emotional state. Input is real-time data from the camera and microphone, and output is the recognized emotional state. OpenCV and an emotion analysis API are combined to analyze both audio and video.

[0406] Step 7:

[0407] The device sends the recognized emotional state to the server. The input is emotional state data, and the output is the prediction result of the modified generative AI model. The server provides this data as feedback to the AI ​​model to improve its accuracy.

[0408] Step 8:

[0409] The server provides the terminal with purchase suggestions that take the customer's emotional state into account. The input is the modified prediction results and emotional state, and the output is a personalized purchase suggestion for the user. The server sends a notification to the user using the prompt message, "If the customer expresses dissatisfaction after hearing the product description, please suggest an alternative product."

[0410] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0411] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0412] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0413] [Third Embodiment]

[0414] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0415] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0416] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0417] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0418] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0419] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0420] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0421] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0422] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0423] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0424] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0425] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0426] The system of this invention operates through the interaction of a server, terminals, and users. First, the server collects sales history data and real-time data from databases and APIs both inside and outside the company. This enables the rapid acquisition of necessary information. The collected data is pre-processed by the server into an appropriate format and shaped for analysis.

[0427] The server analyzes data formatted using a generative AI model to predict future demand. The AI ​​model considers past sales trends and market factors, enabling it to capture demand fluctuations with high accuracy. The predicted demand data is transmitted from the server to the supply chain management system and displayed in real time on a dashboard on the terminal. This information is used for inventory management and sales strategy development.

[0428] The terminal makes suggestions for ordering and inventory adjustments based on the displayed demand forecast. Users can then develop specific action plans based on these suggestions. For example, if increased demand for a particular product is predicted, users can increase orders or plan store promotions based on the data provided by the server.

[0429] Furthermore, the server continuously monitors the accuracy of predictions, receives feedback based on actual user behavior and market trends, and updates the AI ​​model. This allows for flexible responses to future demand fluctuations while maintaining prediction accuracy. For example, if historical data predicts that demand for a certain product will accelerate during the summer, the server can analyze relevant data in advance and suggest actions such as adjusting inventory for that product.

[0430] This system enables users to prevent inventory shortages and excesses, achieve optimal supply chain management, and improve operational efficiency and reduce costs.

[0431] The following describes the processing flow.

[0432] Step 1:

[0433] The server collects sales history and real-time data from various databases and APIs within the enterprise. This includes information on product sales history, inventory status, and distribution channels. Data collection is performed in a consistent format, forming the basis for subsequent processing.

[0434] Step 2:

[0435] The server preprocesses the collected data. First, it scrutinizes the data to detect and remove incomplete or duplicate data. Next, it normalizes the data and converts it to a unified format. During this process, missing values ​​are imputed and outliers are corrected.

[0436] Step 3:

[0437] The server inputs the pre-processed data into the generating AI model and begins the analysis. This AI model uses machine learning algorithms to forecast demand, learning demand patterns from historical data. The AI ​​model then optimizes its prediction accuracy through iterative learning, with appropriate hyperparameters set.

[0438] Step 4:

[0439] The forecast results are transmitted from the server to the supply chain management system and displayed in real time on the user interface on the terminal. The terminal visualizes the demand forecast data in graphs and charts, helping users make quick decisions based on that information.

[0440] Step 5:

[0441] Users refer to the demand forecast displayed on their terminals to adjust inventory management and ordering plans. For example, if the forecast indicates increased demand for a particular product, users can consider taking specific actions, such as increasing the order quantity, on their terminals.

[0442] Step 6:

[0443] The server collects feedback based on user behavior and actual sales data. This feedback is used to update the AI ​​model, improving the accuracy of future predictions. This allows the system to continuously learn and adapt to changes in the sales environment.

[0444] (Example 1)

[0445] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0446] There is a challenge in improving the accuracy of demand forecasts while simultaneously streamlining inventory management and supply planning. In particular, because it is necessary to respond flexibly to forecast uncertainties and market fluctuations, conventional approaches are insufficient for effective supply network management.

[0447] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0448] In this invention, the server includes means for collecting sales history data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the data using a generative AI model and performing demand forecasting. This makes it possible to improve the accuracy of forecasts while making optimal ordering and inventory adjustment suggestions to the user.

[0449] "Sales history data" refers to data that shows information about the sale of goods and services in past transactions, including sales quantity, unit price, and date.

[0450] "Real-time data" refers to the latest information acquired at the present time, and is dynamic data acquired without any time delay.

[0451] A "generative AI model" is a machine learning model that uses artificial intelligence to train algorithms and perform predictions and classifications from large amounts of data.

[0452] A "supply network management system" is an information system designed to optimize inventory, logistics, and order processing within a supply chain.

[0453] A "user terminal" is a device that a user operates to obtain information, and includes devices such as personal computers, tablets, and smartphones.

[0454] "Feedback" refers to the information returned from a system that is used to evaluate its output or results and to improve or adjust them.

[0455] An "inventory adjustment proposal" is a suggestion that includes advice recommending increases, decreases, or replenishments of inventory based on projected demand.

[0456] This invention relates to an information processing system that optimizes inventory management and supply planning based on demand forecasting. This system efficiently forecasts demand and manages inventory through the collaboration of a server, terminals, and users.

[0457] First, the server collects historical sales data and real-time data from databases and APIs both inside and outside the company. In this process, the server uses scraping tools and database connection drivers to efficiently collect data. For example, servers are often built using Python libraries.

[0458] Next, the data collected by the server is preprocessed. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. This formats the data in a way that is suitable for analysis. Specifically, data processing libraries such as Pandas and NumPy are used.

[0459] Subsequently, the server analyzes the pre-processed data using a generative AI model to predict future demand. The AI ​​model is designed using frameworks such as TensorFlow and PyTorch and includes advanced machine learning algorithms. The model takes into account monthly sales data and market trends to accurately predict future demand.

[0460] Demand forecast data is linked to a supply network management system via a server and displayed on the terminal in real time. The terminal visualizes this data as a dashboard, presenting it in the form of graphs and tables in an easy-to-understand format for the user. It is often built as a browser-based application.

[0461] Based on the forecasts displayed on the terminal, users can formulate specific action plans based on the ordering and inventory adjustment suggestions provided by the server. In particular, by accepting the inventory recommendations suggested by the server, users can prevent inventory shortages and excesses.

[0462] Furthermore, the results of user actions are sent to the server as feedback and used as data to improve the AI ​​model. This process allows the model to continuously learn and improve its accuracy.

[0463] As a concrete example, here is an example of a prompt message: "Consider sales data and market trends from the past three years, forecast demand for a specific product during the summer, and propose inventory management and promotional strategies." This prompt message allows the user to fully utilize the system's capabilities.

[0464] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0465] Step 1:

[0466] The server collects sales history data and real-time data from databases and APIs both inside and outside the company. Database connection information and API keys are required as input. The server uses this information and Python libraries to extract the data. The retrieved data is stored in the server's temporary storage as output. Specifically, the server is scheduled to perform data collection tasks daily.

[0467] Step 2:

[0468] The server preprocesses the collected data. It uses the raw data collected in step 1 as input. It performs data cleansing using the Pandas library to impute missing values ​​and remove outliers. The output is a clean dataset in a format suitable for analysis. Specifically, the server applies outlier detection criteria and filters out unnecessary data.

[0469] Step 3:

[0470] The server inputs pre-processed data into a generating AI model to predict demand. A formatted dataset is required as input. The AI ​​model is trained using TensorFlow and predicts future demand by analyzing historical data and market trend patterns. The output is predicted demand data. Specifically, the server processes multiple datasets in batches, running them through the AI ​​model in parallel.

[0471] Step 4:

[0472] The server prepares to transmit the predicted demand data to the supply network management system and display it on the terminal. The demand forecast data obtained in step 3 is used as input. The server sends this data to the supply management system via API, updating the database in real time. The output is updated supply plan data. Specifically, the server converts the data into a specific format and synchronizes it with the system over the network.

[0473] Step 5:

[0474] The terminal displays supply plan data sent from the server on a dashboard. It receives demand forecast data from the server as input. The terminal launches a browser-based application, presenting information to the user visually through graphs and tables. The output provides user-understandable, visualized information. Specifically, the terminal has an automatic update function, reflecting the latest data in a timely manner.

[0475] Step 6:

[0476] The user reviews proposals based on demand forecasts and develops a concrete action plan. The input is demand forecast information displayed on the terminal. Based on this information, the user adjusts negotiations with suppliers and sales promotion activities. The output is an optimized ordering plan and inventory strategy. In terms of specific actions, the user approves proposals on the system via the terminal and takes specific actions.

[0477] Step 7:

[0478] The server receives user execution results as feedback and uses them to improve the accuracy of the AI ​​model. As input, it collects user behavior results and market response data. The server adds this data to the AI ​​model's training data to improve the model. As output, a more accurate AI model is generated. Specifically, the server periodically retrains the AI ​​model to optimize its performance.

[0479] (Application Example 1)

[0480] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0481] Modern logistics management requires a rapid and appropriate response to fluctuations in demand. However, conventional systems suffer from insufficient accuracy in demand forecasting and inability to efficiently propose inventory adjustments based on that forecasting. This results in excess or shortages of inventory, ultimately leading to decreased operational efficiency of logistics centers and increased costs.

[0482] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0483] In this invention, the server includes means for collecting historical sales data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the preprocessed data using a generative AI model to forecast demand. This enables highly accurate forecasting of demand fluctuations and rapid product adjustments in accordance with inventory levels.

[0484] "Sales history data" refers to records of sales activities conducted in the past.

[0485] "Real-time data" refers to immediate information that reflects the current situation.

[0486] "Preprocessing" refers to the preparatory work required to convert data into a format suitable for analysis.

[0487] "Normalization" is the process of standardizing data that exists on different scales to a common scale.

[0488] A "generative AI model" is an algorithmic model based on artificial intelligence technology that analyzes data and generates results according to a specific purpose.

[0489] "Demand forecasting" is the process of estimating the future demand for a product or service.

[0490] "Inventory management" is a general term for planning and controlling measures to maintain appropriate inventory levels.

[0491] A "supply plan" is the process of formulating the necessary supply quantity and timing based on demand forecasts.

[0492] "Product adjustment" refers to modifying the supply volume of a product in response to fluctuations in market demand.

[0493] An "information processing device" is a device used for calculating, storing, and transferring data.

[0494] "Supply chain management" is the process of effectively managing the entire flow of goods, from production to consumption.

[0495] "Feedback" refers to information that is re-entered based on the system's output results and used to improve the system.

[0496] The server effectively collects historical sales data and real-time data from multiple databases and APIs both inside and outside the company. This process requires infrastructure that leverages cloud computing technology to rapidly process large volumes of data.

[0497] The collected data is preprocessed by the server and converted into a standardized format. This preprocessing is performed using data processing software such as pandas and NumPy, which prepares the data in a format suitable for AI analysis.

[0498] Next, the server analyzes the pre-processed data using a generative AI model to forecast demand. This generative AI model uses machine learning libraries such as scikit-learn and TensorFlow to make predictions that take into account past sales trends and market factors. The forecasted demand data is sent from the server to an information processing device and visualized on the user's terminal. For example, a logistics center manager can use this information to make decisions regarding product adjustments.

[0499] The terminal application used by users provides relevant suggestions based on predicted demand, contributing to inventory adjustments and supply planning. This information is displayed in real time, supporting rapid decision-making. On the information processing device, users can intuitively analyze data using a visual dashboard.

[0500] Furthermore, the server receives feedback from actual user actions and market trends to continuously update the AI ​​model, thereby improving prediction accuracy. This increases the reliability of the predictions and enables it to respond to future demand fluctuations.

[0501] An example of a prompt for a generative AI model is: "Consider historical sales data and current market trends to generate a demand forecast for the next month and output suggestions to help manage inventory at the logistics center." Based on this prompt, the model performs highly accurate data analysis and provides useful information to the user.

[0502] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0503] Step 1:

[0504] The server collects historical sales data and real-time data from internal and external databases and APIs. Inputs are database queries and API requests, and outputs are raw sales and market data. This operation involves using database connection libraries to retrieve data quickly and in a structured format.

[0505] Step 2:

[0506] The server preprocesses and normalizes the collected data. The input is the raw data collected in step 1, and the output is data formatted for use with the AI ​​model. The data undergoes data transformations such as imputation of missing values, handling of outliers, and scaling using pandas or NumPy.

[0507] Step 3:

[0508] The server analyzes preprocessed data using a generative AI model and performs demand forecasting. The input is the data processed in step 2, and the output is the resulting demand forecast data. Using libraries such as scikit-learn and TensorFlow, the model learns past data patterns and performs calculations to predict future demand.

[0509] Step 4:

[0510] The server transmits the demand forecast results to the information processing device, where they are visualized on the user's terminal. The input is the demand forecast data obtained in step 3, and the output is visualized data displayed on a graphical user interface. This allows the user to intuitively analyze the data through the dashboard and supports their decision-making.

[0511] Step 5:

[0512] The user's device generates inventory adjustment and supply plan suggestions based on predicted demand. The input is the visualization data displayed in step 4, and the output is specific product adjustment and supply strategy suggestions. Automated alerts and recommended actions are provided, allowing the user to take immediate, concrete action.

[0513] Step 6:

[0514] The server analyzes user behavior and market changes to generate feedback and improve the accuracy of the generated AI model. The input is actual sales data and user feedback, and the output is the updated AI model. Here, the AI ​​model adapts to the real world through a continuous learning process.

[0515] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0516] This invention is a system that combines a demand forecasting system with an emotion engine that recognizes user emotions. First, the server collects sales history data and real-time data from databases both inside and outside the company. This prepares the basic data necessary for demand forecasting. The collected data is preprocessed, such as through normalization, and formatted to be suitable for analysis.

[0517] Using a generative AI model, the server analyzes pre-processed data and predicts future demand. The AI ​​model learns patterns from historical data and optimizes prediction accuracy. This predicted data is used by the server to propose inventory management and supply chain planning.

[0518] Furthermore, the user's device has an emotion engine built in. This emotion engine can recognize emotions from the user's input and actions and analyze the user's response. For example, if the emotion engine recognizes that the user is dissatisfied with the prediction results, it can provide an interface that takes the user's emotions into consideration and offer different suggestions.

[0519] The analysis results from the emotion engine are sent to the server as feedback, and the generated AI model is improved based on this feedback. This allows the model to reflect user opinions and enable more appropriate predictions and suggestions. For example, the emotion engine can detect user anxiety and readjust the supply plan to be more cautious.

[0520] Thus, by integrating emotion understanding and demand forecasting, this invention enables more rational and reliable supply chain management for users, thereby improving corporate operational efficiency and customer satisfaction.

[0521] The following describes the processing flow.

[0522] Step 1:

[0523] The server collects historical and real-time sales data from the company's databases and APIs. This provides a wide range of information about sales trends and current market conditions. The data is collected in a consistent format and prepared for subsequent analysis.

[0524] Step 2:

[0525] The server preprocesses the collected data. It performs data cleaning, supplements missing data, and removes duplicate data. Next, it normalizes the data and converts it into a unified format for analysis, ensuring processing accuracy and speed.

[0526] Step 3:

[0527] The server inputs the pre-processed data into a generating AI model and begins the analysis. This model is tuned using machine learning algorithms to maximize prediction accuracy and has the ability to forecast future demand based on sales history and market factors.

[0528] Step 4:

[0529] Based on predicted demand, the server generates inventory management and supply plan suggestions. These suggestions guide the implementation of an efficient supply chain and optimize the company's resource management.

[0530] Step 5:

[0531] The terminal displays prediction results and inventory management suggestions in the user interface. Here, the emotion engine monitors the user's reactions and acquires emotion data. The terminal analyzes emotions based on user input and facial recognition data, etc., and determines how the user is reacting to the displayed content.

[0532] Step 6:

[0533] The user's reactions, recognized by the emotion engine, are sent to the server, where this information is fed back to the generating AI model. The server uses this feedback to readjust the AI ​​model, enabling it to reflect user expectations and frustrations in future predictions.

[0534] Step 7:

[0535] Users can evaluate the emotionally sensitive supply plan displayed on the device and manually adjust it as needed. For example, if the emotion engine detects that the user is feeling anxious, the device will provide more detailed explanations and additional information to enhance the user's sense of security.

[0536] Through the above process, the system takes user sentiment into consideration, responds promptly to demand fluctuations, and supports the efficient management of a company's supply chain.

[0537] (Example 2)

[0538] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0539] Traditional demand forecasting systems were unable to adjust their forecasts to reflect consumer sentiment, making it difficult to respond quickly to changes in consumer trends. Furthermore, there was a lack of efficient methods for improving AI algorithms using feedback. This left challenges in both usability and forecasting accuracy.

[0540] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0541] In this invention, the server includes means for collecting historical time-series data and real-time information, means for preprocessing and normalizing the collected information, means for analyzing the preprocessed information using a generative AI algorithm and making consumption predictions, means for recognizing the user's psychology using an emotion analysis mechanism and sending it to the server as feedback, and means for adjusting the interface based on the user's emotions and presenting different suggestions. This enables demand forecasting that takes user emotions into account and improvement of the AI ​​algorithm using feedback.

[0542] "Time-series data" refers to information recorded in chronological order of specific phenomena or actions, and is used for analyzing past sales history and trends.

[0543] "Real-time information" refers to timely data obtained based on the current situation and recent events.

[0544] "Preprocessing" refers to a series of processes that format raw data into a form suitable for analysis, including imputation of missing values ​​and data normalization.

[0545] "Normalization" is a data processing technique that unifies the scale of data to improve the accuracy and efficiency of analysis.

[0546] A "generative AI algorithm" is a statistical model or computer program that uses machine learning techniques to learn patterns and predict future demand.

[0547] "Consumption forecasting" is the process of estimating future demand for goods based on past data and trends, and it forms the basis for resource management and supply planning.

[0548] An "emotion analysis mechanism" is a technology that recognizes and understands a user's psychological state based on their input and actions, and is an element that adjusts the responsiveness of the system.

[0549] "Interface adjustment" refers to the act of customizing the display and operating environment of a system or application in response to user emotions and feedback.

[0550] This system is designed to improve user-involved demand forecasting. First, the server accesses internal and external information sources to collect time-series and real-time data. This information is obtained through database queries and APIs. The collected data is preprocessed and normalized using data processing tools such as the "Pandas" library. This process includes imputing missing values, scaling, and formatting.

[0551] Next, the server uses generative AI algorithms such as TensorFlow and PyTorch to perform demand forecasting using the pre-processed data. By modeling consumption patterns from past sales data and related information, it is possible to predict future demand with high accuracy. The forecast results are immediately reflected in the supply chain plan and inventory management, which are updated instantly.

[0552] Meanwhile, the user's device incorporates an emotion analysis mechanism that utilizes natural language processing. This mechanism analyzes the user's input and actions, and understands the user's psychological state from reactions such as "This prediction result is unacceptable." Models like "OpenAI" are used for emotion analysis, and the interface is adjusted to be more responsive to the user's emotions.

[0553] As a concrete example, when the program is executed, the server inputs a prompt message to the generated AI model such as, "Based on this month's sales trends, predict next month's demand," and the actual demand forecast is performed. Such prompts allow the server to obtain accurate forecast output.

[0554] Finally, the server records user feedback and continuously improves the generating AI algorithm. This ensures that the entire system maintains high predictive accuracy and a high quality user experience.

[0555] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0556] Step 1:

[0557] The server collects historical time-series data and real-time information from internal and external sources within the company. It connects to databases and retrieves new data through queries to gather the necessary information. The input is the query conditions, and the output is the collected raw data. This data includes sales history and trend information.

[0558] Step 2:

[0559] The server preprocesses and normalizes the collected data. It uses the "Pandas" library to impute missing values, convert data types, and scale the data. The input is the raw data obtained in step 1, and the output is formatted data suitable for analysis. This ensures data consistency.

[0560] Step 3:

[0561] The server uses a generative AI model to analyze preprocessed data and forecast demand. It uses TensorFlow and PyTorch to learn past patterns and predict future demand. The input is the formatted data from step 2, and the output is the demand forecast result. This result is used in supply planning.

[0562] Step 4:

[0563] The device monitors user input and actions, and recognizes the user's emotions through an emotion analysis mechanism. Using OpenAI's natural language processing technology, it extracts user feedback as emotional information. Input is user text input and action information, and output is the analyzed emotional information. The interface is adjusted based on this information.

[0564] Step 5:

[0565] The server receives the results of the emotion analysis mechanism as feedback. Based on this, it improves the generative AI model. The model is retrained and the prediction algorithm is updated. The input is the emotion information from step 4, and the output is the improved AI model. This improves the accuracy of the predictions.

[0566] Step 6:

[0567] The server ultimately integrates demand forecast results and user feedback to update the supply chain plan and present it to the user. The plan includes inventory management and resource allocation, forming the foundation for improving operational efficiency. Inputs are forecast results and sentiment feedback, and output is the adjusted supply chain plan.

[0568] (Application Example 2)

[0569] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0570] Conventional demand forecasting systems could predict product demand and manage supply chains based on historical and real-time data, but they lacked suggestions that reflected user emotions. As a result, it was difficult to maximize user satisfaction and purchasing intent. This invention aims to improve the user experience by realizing demand forecasting and purchasing suggestions that take user emotions into account.

[0571] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0572] In this invention, the server includes means for collecting historical sales data and real-time data; means for preprocessing and normalizing the collected data; means for analyzing the preprocessed data using a generative AI model and making demand forecasts; means for proposing inventory management and supply plans based on the forecasted demand; means for displaying and referencing the forecast results in cooperation with a supply chain management system; means for evaluating the accuracy of the forecast and improving the model based on feedback; means for recognizing the user's emotional state using an emotion analysis engine; and means for adapting purchase suggestions based on the user's emotional state. This enables appropriate product suggestions that take into account the user's emotions, thereby improving the user experience and increasing purchasing intent.

[0573] "Sales history data" refers to data that shows records of past sales, quantities, and consumer purchasing activities for a product.

[0574] "Real-time data" refers to data that shows the latest information and records based on the current situation.

[0575] "Preprocessing" refers to the process of normalizing data for analysis and converting it into a format suitable for analysis.

[0576] A "generative AI model" is an artificial intelligence framework that uses data-based algorithms to analyze new data, learn patterns, and make predictions.

[0577] "Demand forecasting" is the process of predicting future demand for a product, and it is important for optimizing the efficiency of the supply chain.

[0578] "Inventory management" refers to management activities aimed at maintaining a balance between the supply and consumption of goods, and preventing situations of surplus or shortage.

[0579] A "supply plan" is a plan to ensure an efficient supply of goods in accordance with demand.

[0580] A "supply chain management system" is a system that optimizes the flow of goods and services and manages an organization's supply activities.

[0581] "Feedback" refers to a feedback loop that evaluates the accuracy of predictions in order to improve the model.

[0582] An "emotion analysis engine" is an engine that analyzes and understands a user's emotions based on their voice, behavior, facial expressions, etc.

[0583] A "purchase suggestion" is an activity that presents users with the most suitable purchase options, and these suggestions are based on predictive and sentiment data.

[0584] In this invention, a server, terminal, and user collaborate to build a system. The server collects sales history data and real-time data from numerous databases, and preprocesses and normalizes this data. The preprocessed data is sent to a generative AI model, where it learns patterns and performs demand forecasting. This AI model incorporates a machine learning algorithm using TensorFlow.

[0585] The server proposes inventory management and supply plans based on predicted demand. Furthermore, it integrates with supply chain management systems to display forecast results, making them accessible to stakeholders. The model's prediction accuracy is regularly evaluated, and feedback is used to improve the model.

[0586] The user's device has an emotion analysis engine installed. This engine uses the smartphone's or device's built-in camera and microphone to analyze the user's emotions from their facial expressions and voice tone. By using the OpenCV library and Google Cloud's emotion analysis API, it analyzes facial expressions and voice in real time to identify the user's emotional state.

[0587] This emotional state is sent to the server, which uses this information to modify the predictions of the generating AI model and provide the device with more optimized purchase suggestions. This information is used while the user is shopping in a store, allowing them to receive more personalized product suggestions.

[0588] As a concrete example, if a user shows dissatisfaction or lack of interest after listening to a product description in a store, the system analyzes that facial expression data and suggests a more appealing alternative product. Another example of a prompt message is, "If a customer shows dissatisfaction after listening to the product description, please suggest an alternative product." Such an implementation can improve the quality of the customer experience and stimulate purchasing intent.

[0589] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0590] Step 1:

[0591] The server collects sales history data and real-time data from multiple databases. Inputs are internal and external databases, and output is a raw dataset. The server accesses the databases using API calls and extracts the necessary data.

[0592] Step 2:

[0593] The server preprocesses and normalizes the collected data. The input is the raw dataset, and the output is the normalized dataset. The Python Pandas library is used to impute missing values ​​in the data and scale it to a consistent format.

[0594] Step 3:

[0595] The server generates a normalized dataset, inputs it into an AI model, and performs demand forecasting. The input is a normalized dataset, and the output is a forecast of future demand. A machine learning model built using TensorFlow learns patterns from the data and generates predictions.

[0596] Step 4:

[0597] The server generates inventory management and supply plan suggestions based on predicted demand. The input is the demand forecast, and the output is the inventory management and supply plan suggestions. An algorithm is used to calculate the optimal inventory levels and supply plan based on demand.

[0598] Step 5:

[0599] The server integrates with the supply chain management system, making forecast results visible and accessible to stakeholders. Inputs include demand forecast results and suggestions, while outputs include web dashboards and notification messages. The server provides visualizations using a web framework.

[0600] Step 6:

[0601] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone to recognize their emotional state. Input is real-time data from the camera and microphone, and output is the recognized emotional state. OpenCV and an emotion analysis API are combined to analyze both audio and video.

[0602] Step 7:

[0603] The device sends the recognized emotional state to the server. The input is emotional state data, and the output is the prediction result of the modified generative AI model. The server provides this data as feedback to the AI ​​model to improve its accuracy.

[0604] Step 8:

[0605] The server provides the terminal with purchase suggestions that take the customer's emotional state into account. The input is the modified prediction results and emotional state, and the output is a personalized purchase suggestion for the user. The server sends a notification to the user using the prompt message, "If the customer expresses dissatisfaction after hearing the product description, please suggest an alternative product."

[0606] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0607] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0608] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0609] [Fourth Embodiment]

[0610] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0611] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0612] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0613] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0614] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0615] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0616] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0617] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0618] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0619] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0620] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0621] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0622] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0623] The system of this invention operates through the interaction of a server, terminals, and users. First, the server collects sales history data and real-time data from databases and APIs both inside and outside the company. This enables the rapid acquisition of necessary information. The collected data is pre-processed by the server into an appropriate format and shaped for analysis.

[0624] The server analyzes data formatted using a generative AI model to predict future demand. The AI ​​model considers past sales trends and market factors, enabling it to capture demand fluctuations with high accuracy. The predicted demand data is transmitted from the server to the supply chain management system and displayed in real time on a dashboard on the terminal. This information is used for inventory management and sales strategy development.

[0625] The terminal makes suggestions for ordering and inventory adjustments based on the displayed demand forecast. Users can then develop specific action plans based on these suggestions. For example, if increased demand for a particular product is predicted, users can increase orders or plan store promotions based on the data provided by the server.

[0626] Furthermore, the server continuously monitors the accuracy of predictions, receives feedback based on actual user behavior and market trends, and updates the AI ​​model. This allows for flexible responses to future demand fluctuations while maintaining prediction accuracy. For example, if historical data predicts that demand for a certain product will accelerate during the summer, the server can analyze relevant data in advance and suggest actions such as adjusting inventory for that product.

[0627] This system enables users to prevent inventory shortages and excesses, achieve optimal supply chain management, and improve operational efficiency and reduce costs.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The server collects sales history and real-time data from various databases and APIs within the enterprise. This includes information on product sales history, inventory status, and distribution channels. Data collection is performed in a consistent format, forming the basis for subsequent processing.

[0631] Step 2:

[0632] The server preprocesses the collected data. First, it scrutinizes the data to detect and remove incomplete or duplicate data. Next, it normalizes the data and converts it to a unified format. During this process, missing values ​​are imputed and outliers are corrected.

[0633] Step 3:

[0634] The server inputs the pre-processed data into the generating AI model and begins the analysis. This AI model uses machine learning algorithms to forecast demand, learning demand patterns from historical data. The AI ​​model then optimizes its prediction accuracy through iterative learning, with appropriate hyperparameters set.

[0635] Step 4:

[0636] The forecast results are transmitted from the server to the supply chain management system and displayed in real time on the user interface on the terminal. The terminal visualizes the demand forecast data in graphs and charts, helping users make quick decisions based on that information.

[0637] Step 5:

[0638] Users refer to the demand forecast displayed on their terminals to adjust inventory management and ordering plans. For example, if the forecast indicates increased demand for a particular product, users can consider taking specific actions, such as increasing the order quantity, on their terminals.

[0639] Step 6:

[0640] The server collects feedback based on user behavior and actual sales data. This feedback is used to update the AI ​​model, improving the accuracy of future predictions. This allows the system to continuously learn and adapt to changes in the sales environment.

[0641] (Example 1)

[0642] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0643] There is a challenge in improving the accuracy of demand forecasts while simultaneously streamlining inventory management and supply planning. In particular, because it is necessary to respond flexibly to forecast uncertainties and market fluctuations, conventional approaches are insufficient for effective supply network management.

[0644] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0645] In this invention, the server includes means for collecting sales history data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the data using a generative AI model and performing demand forecasting. This makes it possible to improve the accuracy of forecasts while making optimal ordering and inventory adjustment suggestions to the user.

[0646] "Sales history data" refers to data that shows information about the sale of goods and services in past transactions, including sales quantity, unit price, and date.

[0647] "Real-time data" refers to the latest information acquired at the present time, and is dynamic data acquired without any time delay.

[0648] A "generative AI model" is a machine learning model that uses artificial intelligence to train algorithms and perform predictions and classifications from large amounts of data.

[0649] A "supply network management system" is an information system designed to optimize inventory, logistics, and order processing within a supply chain.

[0650] A "user terminal" is a device that a user operates to obtain information, and includes devices such as personal computers, tablets, and smartphones.

[0651] "Feedback" refers to the information returned from a system that is used to evaluate its output or results and to improve or adjust them.

[0652] An "inventory adjustment proposal" is a suggestion that includes advice recommending increases, decreases, or replenishments of inventory based on projected demand.

[0653] This invention relates to an information processing system that optimizes inventory management and supply planning based on demand forecasting. This system efficiently forecasts demand and manages inventory through the collaboration of a server, terminals, and users.

[0654] First, the server collects historical sales data and real-time data from databases and APIs both inside and outside the company. In this process, the server uses scraping tools and database connection drivers to efficiently collect data. For example, servers are often built using Python libraries.

[0655] Next, the data collected by the server is preprocessed. This preprocessing includes imputing missing values, removing outliers, and normalizing the data. This formats the data in a way that is suitable for analysis. Specifically, data processing libraries such as Pandas and NumPy are used.

[0656] Subsequently, the server analyzes the pre-processed data using a generative AI model to predict future demand. The AI ​​model is designed using frameworks such as TensorFlow and PyTorch and includes advanced machine learning algorithms. The model takes into account monthly sales data and market trends to accurately predict future demand.

[0657] Demand forecast data is linked to a supply network management system via a server and displayed on the terminal in real time. The terminal visualizes this data as a dashboard, presenting it in the form of graphs and tables in an easy-to-understand format for the user. It is often built as a browser-based application.

[0658] Based on the forecasts displayed on the terminal, users can formulate specific action plans based on the ordering and inventory adjustment suggestions provided by the server. In particular, by accepting the inventory recommendations suggested by the server, users can prevent inventory shortages and excesses.

[0659] Furthermore, the results of user actions are sent to the server as feedback and used as data to improve the AI ​​model. This process allows the model to continuously learn and improve its accuracy.

[0660] As a concrete example, here is an example of a prompt message: "Consider sales data and market trends from the past three years, forecast demand for a specific product during the summer, and propose inventory management and promotional strategies." This prompt message allows the user to fully utilize the system's capabilities.

[0661] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0662] Step 1:

[0663] The server collects sales history data and real-time data from databases and APIs both inside and outside the company. Database connection information and API keys are required as input. The server uses this information and Python libraries to extract the data. The retrieved data is stored in the server's temporary storage as output. Specifically, the server is scheduled to perform data collection tasks daily.

[0664] Step 2:

[0665] The server preprocesses the collected data. It uses the raw data collected in step 1 as input. It performs data cleansing using the Pandas library to impute missing values ​​and remove outliers. The output is a clean dataset in a format suitable for analysis. Specifically, the server applies outlier detection criteria and filters out unnecessary data.

[0666] Step 3:

[0667] The server inputs pre-processed data into a generating AI model to predict demand. A formatted dataset is required as input. The AI ​​model is trained using TensorFlow and predicts future demand by analyzing historical data and market trend patterns. The output is predicted demand data. Specifically, the server processes multiple datasets in batches, running them through the AI ​​model in parallel.

[0668] Step 4:

[0669] The server prepares to transmit the predicted demand data to the supply network management system and display it on the terminal. The demand forecast data obtained in step 3 is used as input. The server sends this data to the supply management system via API, updating the database in real time. The output is updated supply plan data. Specifically, the server converts the data into a specific format and synchronizes it with the system over the network.

[0670] Step 5:

[0671] The terminal displays supply plan data sent from the server on a dashboard. It receives demand forecast data from the server as input. The terminal launches a browser-based application, presenting information to the user visually through graphs and tables. The output provides user-understandable, visualized information. Specifically, the terminal has an automatic update function, reflecting the latest data in a timely manner.

[0672] Step 6:

[0673] The user reviews proposals based on demand forecasts and develops a concrete action plan. The input is demand forecast information displayed on the terminal. Based on this information, the user adjusts negotiations with suppliers and sales promotion activities. The output is an optimized ordering plan and inventory strategy. In terms of specific actions, the user approves proposals on the system via the terminal and takes specific actions.

[0674] Step 7:

[0675] The server receives user execution results as feedback and uses them to improve the accuracy of the AI ​​model. As input, it collects user behavior results and market response data. The server adds this data to the AI ​​model's training data to improve the model. As output, a more accurate AI model is generated. Specifically, the server periodically retrains the AI ​​model to optimize its performance.

[0676] (Application Example 1)

[0677] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0678] Modern logistics management requires a rapid and appropriate response to fluctuations in demand. However, conventional systems suffer from insufficient accuracy in demand forecasting and inability to efficiently propose inventory adjustments based on that forecasting. This results in excess or shortages of inventory, ultimately leading to decreased operational efficiency of logistics centers and increased costs.

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

[0680] In this invention, the server includes means for collecting historical sales data and real-time data, means for preprocessing and normalizing the collected data, and means for analyzing the preprocessed data using a generative AI model to forecast demand. This enables highly accurate forecasting of demand fluctuations and rapid product adjustments in accordance with inventory levels.

[0681] "Sales history data" refers to records of sales activities conducted in the past.

[0682] "Real-time data" refers to immediate information that reflects the current situation.

[0683] "Preprocessing" refers to the preparatory work required to convert data into a format suitable for analysis.

[0684] "Normalization" is the process of standardizing data that exists on different scales to a common scale.

[0685] A "generative AI model" is an algorithmic model based on artificial intelligence technology that analyzes data and generates results according to a specific purpose.

[0686] "Demand forecasting" is the process of estimating the future demand for a product or service.

[0687] "Inventory management" is a general term for planning and controlling measures to maintain appropriate inventory levels.

[0688] A "supply plan" is the process of formulating the necessary supply quantity and timing based on demand forecasts.

[0689] "Product adjustment" refers to modifying the supply volume of a product in response to fluctuations in market demand.

[0690] An "information processing device" is a device used for calculating, storing, and transferring data.

[0691] "Supply chain management" is the process of effectively managing the entire flow of goods, from production to consumption.

[0692] "Feedback" refers to information that is re-entered based on the system's output results and used to improve the system.

[0693] The server effectively collects historical sales data and real-time data from multiple databases and APIs both inside and outside the company. This process requires infrastructure that leverages cloud computing technology to rapidly process large volumes of data.

[0694] The collected data is preprocessed by the server and converted into a standardized format. This preprocessing is performed using data processing software such as pandas and NumPy, which prepares the data in a format suitable for AI analysis.

[0695] Next, the server analyzes the pre-processed data using a generative AI model to forecast demand. This generative AI model uses machine learning libraries such as scikit-learn and TensorFlow to make predictions that take into account past sales trends and market factors. The forecasted demand data is sent from the server to an information processing device and visualized on the user's terminal. For example, a logistics center manager can use this information to make decisions regarding product adjustments.

[0696] The terminal application used by users provides relevant suggestions based on predicted demand, contributing to inventory adjustments and supply planning. This information is displayed in real time, supporting rapid decision-making. On the information processing device, users can intuitively analyze data using a visual dashboard.

[0697] Furthermore, the server receives feedback from actual user actions and market trends to continuously update the AI ​​model, thereby improving prediction accuracy. This increases the reliability of the predictions and enables it to respond to future demand fluctuations.

[0698] An example of a prompt for a generative AI model is: "Consider historical sales data and current market trends to generate a demand forecast for the next month and output suggestions to help manage inventory at the logistics center." Based on this prompt, the model performs highly accurate data analysis and provides useful information to the user.

[0699] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0700] Step 1:

[0701] The server collects historical sales data and real-time data from internal and external databases and APIs. Inputs are database queries and API requests, and outputs are raw sales and market data. This operation involves using database connection libraries to retrieve data quickly and in a structured format.

[0702] Step 2:

[0703] The server preprocesses and normalizes the collected data. The input is the raw data collected in step 1, and the output is data formatted for use with the AI ​​model. The data undergoes data transformations such as imputation of missing values, handling of outliers, and scaling using pandas or NumPy.

[0704] Step 3:

[0705] The server analyzes preprocessed data using a generative AI model and performs demand forecasting. The input is the data processed in step 2, and the output is the resulting demand forecast data. Using libraries such as scikit-learn and TensorFlow, the model learns past data patterns and performs calculations to predict future demand.

[0706] Step 4:

[0707] The server transmits the demand forecast results to the information processing device, where they are visualized on the user's terminal. The input is the demand forecast data obtained in step 3, and the output is visualized data displayed on a graphical user interface. This allows the user to intuitively analyze the data through the dashboard and supports their decision-making.

[0708] Step 5:

[0709] The user's device generates inventory adjustment and supply plan suggestions based on predicted demand. The input is the visualization data displayed in step 4, and the output is specific product adjustment and supply strategy suggestions. Automated alerts and recommended actions are provided, allowing the user to take immediate, concrete action.

[0710] Step 6:

[0711] The server analyzes user behavior and market changes to generate feedback and improve the accuracy of the generated AI model. The input is actual sales data and user feedback, and the output is the updated AI model. Here, the AI ​​model adapts to the real world through a continuous learning process.

[0712] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0713] This invention is a system that combines a demand forecasting system with an emotion engine that recognizes user emotions. First, the server collects sales history data and real-time data from databases both inside and outside the company. This prepares the basic data necessary for demand forecasting. The collected data is preprocessed, such as through normalization, and formatted to be suitable for analysis.

[0714] Using a generative AI model, the server analyzes pre-processed data and predicts future demand. The AI ​​model learns patterns from historical data and optimizes prediction accuracy. This predicted data is used by the server to propose inventory management and supply chain planning.

[0715] Furthermore, the user's device has an emotion engine built in. This emotion engine can recognize emotions from the user's input and actions and analyze the user's response. For example, if the emotion engine recognizes that the user is dissatisfied with the prediction results, it can provide an interface that takes the user's emotions into consideration and offer different suggestions.

[0716] The analysis results from the emotion engine are sent to the server as feedback, and the generated AI model is improved based on this feedback. This allows the model to reflect user opinions and enable more appropriate predictions and suggestions. For example, the emotion engine can detect user anxiety and readjust the supply plan to be more cautious.

[0717] Thus, by integrating emotion understanding and demand forecasting, this invention enables more rational and reliable supply chain management for users, thereby improving corporate operational efficiency and customer satisfaction.

[0718] The following describes the processing flow.

[0719] Step 1:

[0720] The server collects historical and real-time sales data from the company's databases and APIs. This provides a wide range of information about sales trends and current market conditions. The data is collected in a consistent format and prepared for subsequent analysis.

[0721] Step 2:

[0722] The server preprocesses the collected data. It performs data cleaning, supplements missing data, and removes duplicate data. Next, it normalizes the data and converts it into a unified format for analysis, ensuring processing accuracy and speed.

[0723] Step 3:

[0724] The server inputs the pre-processed data into a generating AI model and begins the analysis. This model is tuned using machine learning algorithms to maximize prediction accuracy and has the ability to forecast future demand based on sales history and market factors.

[0725] Step 4:

[0726] Based on predicted demand, the server generates inventory management and supply plan suggestions. These suggestions guide the implementation of an efficient supply chain and optimize the company's resource management.

[0727] Step 5:

[0728] The terminal displays prediction results and inventory management suggestions in the user interface. Here, the emotion engine monitors the user's reactions and acquires emotion data. The terminal analyzes emotions based on user input and facial recognition data, etc., and determines how the user is reacting to the displayed content.

[0729] Step 6:

[0730] The user's reactions, recognized by the emotion engine, are sent to the server, where this information is fed back to the generating AI model. The server uses this feedback to readjust the AI ​​model, enabling it to reflect user expectations and frustrations in future predictions.

[0731] Step 7:

[0732] Users can evaluate the emotionally sensitive supply plan displayed on the device and manually adjust it as needed. For example, if the emotion engine detects that the user is feeling anxious, the device will provide more detailed explanations and additional information to enhance the user's sense of security.

[0733] Through the above process, the system takes user sentiment into consideration, responds promptly to demand fluctuations, and supports the efficient management of a company's supply chain.

[0734] (Example 2)

[0735] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0736] Traditional demand forecasting systems were unable to adjust their forecasts to reflect consumer sentiment, making it difficult to respond quickly to changes in consumer trends. Furthermore, there was a lack of efficient methods for improving AI algorithms using feedback. This left challenges in both usability and forecasting accuracy.

[0737] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0738] In this invention, the server includes means for collecting historical time-series data and real-time information, means for preprocessing and normalizing the collected information, means for analyzing the preprocessed information using a generative AI algorithm and making consumption predictions, means for recognizing the user's psychology using an emotion analysis mechanism and sending it to the server as feedback, and means for adjusting the interface based on the user's emotions and presenting different suggestions. This enables demand forecasting that takes user emotions into account and improvement of the AI ​​algorithm using feedback.

[0739] "Time-series data" refers to information recorded in chronological order of specific phenomena or actions, and is used for analyzing past sales history and trends.

[0740] "Real-time information" refers to timely data obtained based on the current situation and recent events.

[0741] "Preprocessing" refers to a series of processes that format raw data into a form suitable for analysis, including imputation of missing values ​​and data normalization.

[0742] "Normalization" is a data processing technique that unifies the scale of data to improve the accuracy and efficiency of analysis.

[0743] A "generative AI algorithm" is a statistical model or computer program that uses machine learning techniques to learn patterns and predict future demand.

[0744] "Consumption forecasting" is the process of estimating future demand for goods based on past data and trends, and it forms the basis for resource management and supply planning.

[0745] An "emotion analysis mechanism" is a technology that recognizes and understands a user's psychological state based on their input and actions, and is an element that adjusts the responsiveness of the system.

[0746] "Interface adjustment" refers to the act of customizing the display and operating environment of a system or application in response to user emotions and feedback.

[0747] This system is designed to improve user-involved demand forecasting. First, the server accesses internal and external information sources to collect time-series and real-time data. This information is obtained through database queries and APIs. The collected data is preprocessed and normalized using data processing tools such as the "Pandas" library. This process includes imputing missing values, scaling, and formatting.

[0748] Next, the server uses generative AI algorithms such as TensorFlow and PyTorch to perform demand forecasting using the pre-processed data. By modeling consumption patterns from past sales data and related information, it is possible to predict future demand with high accuracy. The forecast results are immediately reflected in the supply chain plan and inventory management, which are updated instantly.

[0749] Meanwhile, the user's device incorporates an emotion analysis mechanism that utilizes natural language processing. This mechanism analyzes the user's input and actions, and understands the user's psychological state from reactions such as "This prediction result is unacceptable." Models like "OpenAI" are used for emotion analysis, and the interface is adjusted to be more responsive to the user's emotions.

[0750] As a concrete example, when the program is executed, the server inputs a prompt message to the generated AI model such as, "Based on this month's sales trends, predict next month's demand," and the actual demand forecast is performed. Such prompts allow the server to obtain accurate forecast output.

[0751] Finally, the server records user feedback and continuously improves the generating AI algorithm. This ensures that the entire system maintains high predictive accuracy and a high quality user experience.

[0752] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0753] Step 1:

[0754] The server collects historical time-series data and real-time information from internal and external sources within the company. It connects to databases and retrieves new data through queries to gather the necessary information. The input is the query conditions, and the output is the collected raw data. This data includes sales history and trend information.

[0755] Step 2:

[0756] The server preprocesses and normalizes the collected data. It uses the "Pandas" library to impute missing values, convert data types, and scale the data. The input is the raw data obtained in step 1, and the output is formatted data suitable for analysis. This ensures data consistency.

[0757] Step 3:

[0758] The server uses a generative AI model to analyze preprocessed data and forecast demand. It uses TensorFlow and PyTorch to learn past patterns and predict future demand. The input is the formatted data from step 2, and the output is the demand forecast result. This result is used in supply planning.

[0759] Step 4:

[0760] The device monitors user input and actions, and recognizes the user's emotions through an emotion analysis mechanism. Using OpenAI's natural language processing technology, it extracts user feedback as emotional information. Input is user text input and action information, and output is the analyzed emotional information. The interface is adjusted based on this information.

[0761] Step 5:

[0762] The server receives the results of the emotion analysis mechanism as feedback. Based on this, it improves the generative AI model. The model is retrained and the prediction algorithm is updated. The input is the emotion information from step 4, and the output is the improved AI model. This improves the accuracy of the predictions.

[0763] Step 6:

[0764] The server ultimately integrates demand forecast results and user feedback to update the supply chain plan and present it to the user. The plan includes inventory management and resource allocation, forming the foundation for improving operational efficiency. Inputs are forecast results and sentiment feedback, and output is the adjusted supply chain plan.

[0765] (Application Example 2)

[0766] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0767] Conventional demand forecasting systems could predict product demand and manage supply chains based on historical and real-time data, but they lacked suggestions that reflected user emotions. As a result, it was difficult to maximize user satisfaction and purchasing intent. This invention aims to improve the user experience by realizing demand forecasting and purchasing suggestions that take user emotions into account.

[0768] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0769] In this invention, the server includes means for collecting historical sales data and real-time data; means for preprocessing and normalizing the collected data; means for analyzing the preprocessed data using a generative AI model and making demand forecasts; means for proposing inventory management and supply plans based on the forecasted demand; means for displaying and referencing the forecast results in cooperation with a supply chain management system; means for evaluating the accuracy of the forecast and improving the model based on feedback; means for recognizing the user's emotional state using an emotion analysis engine; and means for adapting purchase suggestions based on the user's emotional state. This enables appropriate product suggestions that take into account the user's emotions, thereby improving the user experience and increasing purchasing intent.

[0770] "Sales history data" refers to data that shows records of past sales, quantities, and consumer purchasing activities for a product.

[0771] "Real-time data" refers to data that shows the latest information and records based on the current situation.

[0772] "Preprocessing" refers to the process of normalizing data for analysis and converting it into a format suitable for analysis.

[0773] A "generative AI model" is an artificial intelligence framework that uses data-based algorithms to analyze new data, learn patterns, and make predictions.

[0774] "Demand forecasting" is the process of predicting future demand for a product, and it is important for optimizing the efficiency of the supply chain.

[0775] "Inventory management" refers to management activities aimed at maintaining a balance between the supply and consumption of goods, and preventing situations of surplus or shortage.

[0776] A "supply plan" is a plan to ensure an efficient supply of goods in accordance with demand.

[0777] A "supply chain management system" is a system that optimizes the flow of goods and services and manages an organization's supply activities.

[0778] "Feedback" refers to a feedback loop that evaluates the accuracy of predictions in order to improve the model.

[0779] An "emotion analysis engine" is an engine that analyzes and understands a user's emotions based on their voice, behavior, facial expressions, etc.

[0780] A "purchase suggestion" is an activity that presents users with the most suitable purchase options, and these suggestions are based on predictive and sentiment data.

[0781] In this invention, a server, terminal, and user collaborate to build a system. The server collects sales history data and real-time data from numerous databases, and preprocesses and normalizes this data. The preprocessed data is sent to a generative AI model, where it learns patterns and performs demand forecasting. This AI model incorporates a machine learning algorithm using TensorFlow.

[0782] The server proposes inventory management and supply plans based on predicted demand. Furthermore, it integrates with supply chain management systems to display forecast results, making them accessible to stakeholders. The model's prediction accuracy is regularly evaluated, and feedback is used to improve the model.

[0783] The user's device has an emotion analysis engine installed. This engine uses the smartphone's or device's built-in camera and microphone to analyze the user's emotions from their facial expressions and voice tone. By using the OpenCV library and Google Cloud's emotion analysis API, it analyzes facial expressions and voice in real time to identify the user's emotional state.

[0784] This emotional state is sent to the server, which uses this information to modify the predictions of the generating AI model and provide the device with more optimized purchase suggestions. This information is used while the user is shopping in a store, allowing them to receive more personalized product suggestions.

[0785] As a concrete example, if a user shows dissatisfaction or lack of interest after listening to a product description in a store, the system analyzes that facial expression data and suggests a more appealing alternative product. Another example of a prompt message is, "If a customer shows dissatisfaction after listening to the product description, please suggest an alternative product." Such an implementation can improve the quality of the customer experience and stimulate purchasing intent.

[0786] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0787] Step 1:

[0788] The server collects sales history data and real-time data from multiple databases. Inputs are internal and external databases, and output is a raw dataset. The server accesses the databases using API calls and extracts the necessary data.

[0789] Step 2:

[0790] The server preprocesses and normalizes the collected data. The input is the raw dataset, and the output is the normalized dataset. The Python Pandas library is used to impute missing values ​​in the data and scale it to a consistent format.

[0791] Step 3:

[0792] The server generates a normalized dataset, inputs it into an AI model, and performs demand forecasting. The input is a normalized dataset, and the output is a forecast of future demand. A machine learning model built using TensorFlow learns patterns from the data and generates predictions.

[0793] Step 4:

[0794] The server generates inventory management and supply plan suggestions based on predicted demand. The input is the demand forecast, and the output is the inventory management and supply plan suggestions. An algorithm is used to calculate the optimal inventory levels and supply plan based on demand.

[0795] Step 5:

[0796] The server integrates with the supply chain management system, making forecast results visible and accessible to stakeholders. Inputs include demand forecast results and suggestions, while outputs include web dashboards and notification messages. The server provides visualizations using a web framework.

[0797] Step 6:

[0798] The device uses an emotion analysis engine to analyze the user's facial expressions and voice tone to recognize their emotional state. Input is real-time data from the camera and microphone, and output is the recognized emotional state. OpenCV and an emotion analysis API are combined to analyze both audio and video.

[0799] Step 7:

[0800] The device sends the recognized emotional state to the server. The input is emotional state data, and the output is the prediction result of the modified generative AI model. The server provides this data as feedback to the AI ​​model to improve its accuracy.

[0801] Step 8:

[0802] The server provides the terminal with purchase suggestions that take the customer's emotional state into account. The input is the modified prediction results and emotional state, and the output is a personalized purchase suggestion for the user. The server sends a notification to the user using the prompt message, "If the customer expresses dissatisfaction after hearing the product description, please suggest an alternative product."

[0803] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0804] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0805] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0806] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0807] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0808] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0809] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0810] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0811] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0812] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0813] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0814] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0815] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0816] 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.

[0817] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0818] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0819] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0820] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0821] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0822] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0823] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0824] The following is further disclosed regarding the embodiments described above.

[0825] (Claim 1)

[0826] A means of collecting past sales history data and real-time data,

[0827] Methods for preprocessing and normalizing the collected data,

[0828] A means of analyzing preprocessed data using a generative AI model to perform demand forecasting,

[0829] A means of proposing inventory management and supply plans based on predicted demand,

[0830] A means for displaying and referencing prediction results in conjunction with a supply chain management system,

[0831] A means to evaluate the accuracy of predictions and improve the model based on feedback,

[0832] A system that includes this.

[0833] (Claim 2)

[0834] The system according to claim 1, wherein the generating AI model is designed to optimize prediction accuracy using a machine learning algorithm.

[0835] (Claim 3)

[0836] The system according to claim 1, further comprising means for automatically generating an action plan based on prediction results and proposing it to the user.

[0837] "Example 1"

[0838] (Claim 1)

[0839] A means of collecting past sales history data and real-time data,

[0840] Methods for preprocessing and normalizing the collected data,

[0841] A means of analyzing preprocessed data using a generative AI model to perform demand forecasting,

[0842] A means for linking demand forecast data with a supply network management system, making it displayable and accessible,

[0843] A means for displaying order and inventory adjustment suggestions based on predicted demand on the user terminal,

[0844] A means of continuously improving the accuracy of predictions by applying user behavior results as feedback to the AI ​​model,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, wherein the generating AI model is designed to dynamically improve its prediction accuracy using a machine learning algorithm.

[0848] (Claim 3)

[0849] The system according to claim 1, further comprising means for automatically generating a specific action plan based on prediction results and displaying it to the user for selection.

[0850] "Application Example 1"

[0851] (Claim 1)

[0852] A means of collecting past sales history data and real-time data,

[0853] Methods for preprocessing and normalizing the collected data,

[0854] A means of analyzing preprocessed data using a generative AI model to perform demand forecasting,

[0855] A means to visualize fluctuations in demand and propose product adjustments according to inventory levels,

[0856] A means for automatically generating a supply plan and displaying the proposed results on an information processing device,

[0857] A means for displaying and referencing prediction results in conjunction with a supply chain management system,

[0858] A means to evaluate the accuracy of predictions and improve the model based on feedback,

[0859] A system that includes this.

[0860] (Claim 2)

[0861] The system according to claim 1, wherein the generating AI model is designed to optimize prediction accuracy using a machine learning algorithm.

[0862] (Claim 3)

[0863] The system according to claim 1, further comprising means for automatically generating an action plan based on prediction results and proposing it to the user.

[0864] "Example 2 of combining an emotion engine"

[0865] (Claim 1)

[0866] A means for collecting historical time-series data and real-time information,

[0867] A means of preprocessing and normalizing the collected information,

[0868] A means of analyzing pre-processed information using a generative AI algorithm to predict consumption,

[0869] A means of proposing resource management and supply plans based on predicted consumption,

[0870] A means to display and make referable forecast results in cooperation with the supply chain management mechanism,

[0871] A means for evaluating the accuracy of the estimation and improving the algorithm based on the analysis results,

[0872] A means of recognizing the user's psychology using an emotion analysis mechanism and sending it to a server as feedback,

[0873] A means of adjusting the interface based on the user's emotions and presenting different suggestions,

[0874] A system that includes this.

[0875] (Claim 2)

[0876] The system according to claim 1, wherein the generation AI algorithm is designed to optimize prediction accuracy using a learning algorithm.

[0877] (Claim 3)

[0878] The system according to claim 1, further comprising means for automatically generating an action plan based on prediction results and proposing it to the user.

[0879] "Application example 2 when combining with an emotional engine"

[0880] (Claim 1)

[0881] A means of collecting past sales history data and real-time data,

[0882] Methods for preprocessing and normalizing the collected data,

[0883] A means of analyzing preprocessed data using a generative AI model to perform demand forecasting,

[0884] A means of proposing inventory management and supply plans based on predicted demand,

[0885] A means for displaying and referencing prediction results in conjunction with a supply chain management system,

[0886] A means to evaluate the accuracy of predictions and improve the model based on feedback,

[0887] A means of recognizing the user's emotional state using an emotion analysis engine,

[0888] A means of adapting purchase suggestions based on the user's emotional state,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, wherein the generating AI model is designed to optimize prediction accuracy using a machine learning algorithm.

[0892] (Claim 3)

[0893] The system according to claim 1, further comprising means for automatically generating an action plan based on prediction results and sentiment analysis results and proposing it to the user. [Explanation of Symbols]

[0894] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting past sales history data and real-time data, Methods for preprocessing and normalizing the collected data, A means of analyzing preprocessed data using a generative AI model to perform demand forecasting, A means of proposing inventory management and supply plans based on predicted demand, A means for displaying and referencing prediction results in conjunction with a supply chain management system, A means to evaluate the accuracy of predictions and improve the model based on feedback, A system that includes this.

2. The system according to claim 1, wherein the generating AI model is designed to optimize prediction accuracy using a machine learning algorithm.

3. The system according to claim 1, further comprising means for automatically generating an action plan based on prediction results and proposing it to the user.

Images