system

Abstract

We provide the system. [Solution] Means for collecting and formatting data, A method for training a generative AI model using formatted data, A means for evaluating the generated prediction model and improving its prediction accuracy, A means of processing real-time data and updating supply and demand forecasts, A means of optimizing inventory management based on updated supply and demand forecasts, A means of providing real-time forecast information and notifying replenishment timing, 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 persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In enterprise facility management, inventory management corresponding to demand fluctuations is very important. However, due to insufficient prediction accuracy, there are problems such as the risk of excess inventory and inventory shortages, leading to inefficient supply chain management. Therefore, there is a need for a system that can effectively utilize past data and accurately predict future demand.

Means for Solving the Problems

[0005] The present invention provides a system that includes means for collecting and formatting data, means for training a generated AI model based on the formatted data, means for evaluating the generated predictive model and improving its prediction accuracy, means for processing real-time data and updating supply and demand forecasts, and means for optimizing inventory management based on the updated supply and demand forecasts. This system enables more accurate and rapid supply and demand forecasting, and realizes efficient inventory management and supply chain management.

[0006] "Methods for collecting and formatting data" refers to the process of obtaining logs and records from multiple sources, and then processing and organizing them into a unified format.

[0007] "Methods for training generative AI models" refer to the process of training machine learning algorithms to improve their predictive capabilities by learning patterns based on collected data.

[0008] "Methods for evaluating predictive models and improving prediction accuracy" refer to techniques for improving the accuracy of predictions by evaluating the performance of trained AI models and identifying issues and areas for improvement.

[0009] "A means of processing real-time data and updating supply and demand forecasts" refers to a process that instantly analyzes newly entered data and constantly maintains the generated forecast results in an up-to-date form.

[0010] "Methods for optimizing inventory management" refer to management techniques that minimize inventory surpluses and shortages by adjusting inventory levels and placement based on predicted demand data. [Brief explanation of the drawing]

[0011] [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] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the labeled processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the labeled storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0017] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark), etc.

[0018] 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."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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".

[0032] In this embodiment of the invention, a system is constructed in which data collection, AI model training, model evaluation, real-time data processing, and inventory management optimization are seamlessly integrated. The system's program processing is described below in natural language.

[0033] First, the server retrieves historical demand data from multiple sources. This data collection is automated, drawing from internal company systems and external supply chain information. Data formatting includes digitization and conversion to standard formats.

[0034] Next, the server trains an AI model using the formatted data. This process uses machine learning algorithms, including deep learning, to learn past supply and demand patterns and predict future demand. The generated model is then evaluated on a known dataset to verify its accuracy.

[0035] Furthermore, real-time data updates are crucial. Terminals allow users to input new data, and the system processes this instantly, providing the latest supply and demand forecasts. This real-time processing enables businesses to take immediate action.

[0036] Regarding inventory management optimization, the system automatically controls inventory replenishment and adjustment based on predictive data generated by the server. This allows users to avoid inventory surpluses and shortages, enabling efficient supply chain management.

[0037] As a concrete example, when a user checks the demand forecast for a new product, the server integrates data from similar past products with current market trends to provide a demand forecast. Based on this forecast, the user can proactively adjust inventory.

[0038] In this way, this system supports the efficient operation of businesses by automating supply and demand forecasting and inventory management using AI.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The server automatically collects historical supply and demand data from both within and outside the company. The data is obtained from various system databases and external APIs.

[0042] Step 2:

[0043] The server cleans and formats the collected data. This process removes noise and converts the data into a standard format. Missing values ​​and anomalies are also handled at this stage.

[0044] Step 3:

[0045] The server trains an AI model using the formatted data. The goal here is to learn patterns within the dataset using machine learning algorithms and predict future demand.

[0046] Step 4:

[0047] The server evaluates the trained model. Test data is used for evaluation to check the model's prediction accuracy. Model parameters are adjusted as needed to improve accuracy.

[0048] Step 5:

[0049] The terminal receives new data from the user in real time. The data entered by the user is processed immediately, and the supply and demand forecast is updated.

[0050] Step 6:

[0051] The server optimizes inventory management using the latest forecast data. Specifically, it replenishes and adjusts inventory according to future demand. Users are provided with new supply and demand forecast information.

[0052] Step 7:

[0053] The server periodically generates and provides users with reports based on supply and demand forecasts. These reports include an overview of the demand forecast and recommended adjustments to inventory levels. Users utilize this information to develop business strategies.

[0054] (Example 1)

[0055] 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."

[0056] Efficient data management and optimized supply and demand forecasting are critical challenges in current business operations. In particular, unifying data from diverse sources and building accurate forecasting models is not easy. Furthermore, while real-time data updates are required to rapidly adjust supply and demand, traditional methods struggle to achieve this efficiently.

[0057] 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.

[0058] In this invention, the server includes means for collecting information and converting it into a standard format, means for performing machine learning using the converted information, and means for evaluating the generated prediction method and improving its accuracy. This makes it possible to integrate diverse information and perform rapid and accurate supply and demand forecasting.

[0059] "Means of information gathering" refers to the process of automatically acquiring data from various sources, both internal and external to a company.

[0060] "Methods for converting to a standard format" refers to the process of unifying data in different formats into a consistent format, making it easier to perform subsequent processing and analysis.

[0061] "Methods for performing machine learning" refers to the process of learning patterns based on past data and applying algorithms to gain new insights.

[0062] "Means for evaluating prediction methods" refers to the process of objectively determining the accuracy and reliability of the generated model using specific evaluation metrics.

[0063] "Means of improving accuracy" refers to the process of improving data and algorithms to enhance the performance of predictive models.

[0064] "Means of optimizing the flow of materials" refers to the process of efficiently managing the supply and inventory of goods based on supply and demand forecasts.

[0065] "Means of improving the efficiency of the supply network" refers to the process of optimizing the operation of the entire supply chain and reducing waste of resources.

[0066] "Methods for creating reports" refers to the process of systematically generating documents based on data analysis results, making the situation visually clear.

[0067] "Means of issuing warnings" refers to the process of quickly issuing alerts when a specific threshold is exceeded based on prediction results or real-time data.

[0068] The embodiments for carrying out the present invention will now be described. This system enables efficient supply and demand forecasting and inventory management, and functions in cooperation with a server, terminals, and users.

[0069] First, the server accesses various corporate information sources to collect data. This includes internal ERP systems and external market databases. The server then uses ETL tools to format the collected data into a standard format. This process integrates the data into an analyzable form.

[0070] Next, the server uses machine learning algorithms to train an AI model based on the formatted data. Here, TENSORFLOW® is used as the deep learning framework. The AI ​​model learns past supply and demand patterns and has the ability to predict future demand.

[0071] Subsequently, the accuracy of the generated model is evaluated using a known dataset. This evaluation process measures the model's predictive accuracy and allows for necessary improvements.

[0072] A terminal is used to update real-time data. Users input new data through the terminal, and this data is sent to the server, allowing the system to immediately revise supply and demand forecasts. For example, sales data can be entered using a tablet or smartphone application, and the forecast can be updated in real time.

[0073] Based on the generated supply and demand forecast data, the server automatically controls inventory replenishment and adjustment. This process optimizes the flow of materials, enabling companies to achieve efficient inventory management.

[0074] As a concrete example, when a user plans a sales campaign for a new product, they use a terminal to input campaign information into the system. By sending a prompt message to the server such as, "Please update the supply and demand baseline to reflect next month's new product sales campaign," the system provides the latest supply and demand forecast, allowing the user to adjust their inventory strategy.

[0075] Through this configuration, the system provides a technological foundation that supports the automation and efficiency of supply and demand forecasting and inventory management.

[0076] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0077] Step 1:

[0078] The server uses a database management system to automatically collect data from internal and external sources within the company. Specifically, it periodically retrieves information from ERP systems and market databases via APIs. This input data includes production figures, sales figures, and market trends. The server converts this data into a standard format using ETL tools, making it analyzable. The output is a dataset in a unified format.

[0079] Step 2:

[0080] Based on the formatted data, the server trains an AI model using machine learning algorithms. Specifically, it uses TensorFlow to learn demand forecasting patterns from historical data. The input to this process is a unified dataset, and the output is the trained AI model. During training, the system iterates to minimize the loss function and improve accuracy.

[0081] Step 3:

[0082] The server evaluates the AI ​​model generated using the new dataset. The data calculations performed here involve using existing data as input and comparing the model's predicted values ​​with actual values. Specifically, it calculates metrics such as accuracy, recall, and F1 score to evaluate model performance. The output consists of the model evaluation results and areas for improvement.

[0083] Step 4:

[0084] The terminal accepts real-time data input from the user. Specifically, users input inventory and sales information via a dedicated app on their tablet or smartphone. The server immediately processes the input data and updates the supply and demand forecast. The output is the latest supply and demand forecast.

[0085] Step 5:

[0086] Based on the generated supply and demand data, the server optimizes the flow of materials and adjusts inventory. Specifically, it automatically issues inventory replenishment orders in accordance with predicted demand. The input is updated supply and demand forecast data, and the output is replenishment plans and order orders.

[0087] Step 6:

[0088] The system receives prompt messages to obtain the information users need to adjust inventory and sales strategies. Specifically, prompt messages such as "Please update the supply and demand baseline to reflect next month's new product sales campaign" are used. The server processes these prompts and provides the user with the updated information. The input is the prompt message, and the output is the adjusted supply and demand forecast information.

[0089] (Application Example 1)

[0090] 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."

[0091] Modern logistics centers require efficient inventory management and precise supply and demand forecasting. However, traditional methods are insufficient for real-time updates of supply and demand forecasts, making it difficult to replenish inventory at the appropriate time. As a result, inventory surpluses and shortages often occur, posing a challenge to optimizing the supply chain.

[0092] 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.

[0093] In this invention, the server includes means for collecting and formatting data, means for training a generation AI model using the formatted data, and means for presenting predictive information in real time and notifying replenishment timing. This enables real-time optimization of inventory management in logistics centers and improves the efficiency of the supply chain.

[0094] "Means of collecting and formatting data" refers to the function of converting raw data imported from databases and external information sources into a format suitable for analysis and model creation.

[0095] "Methods for training generative AI models" refer to the step of building a model capable of supply and demand forecasting using AI algorithms based on historical data.

[0096] "Methods for evaluating predictive models" refer to the process of verifying the accuracy and usefulness of the generated AI model and improving or adjusting the model.

[0097] "Means for processing real-time data and updating supply and demand forecasts" refers to a function that immediately analyzes newly obtained data to reflect the current supply and demand situation and update the forecast.

[0098] "Means for optimizing inventory management based on updated supply and demand forecasts" refers to a mechanism that adjusts inventory purchases and placements based on forecast data, thereby ensuring the efficient use of resources.

[0099] "A means of providing real-time forecast information and notifying users of replenishment timing" refers to a function that provides information to quickly inform users of the period when inventory shortages are predicted.

[0100] To implement this invention, it is necessary to build a system in which multiple components work seamlessly together. First, the server automatically collects historical supply and demand data from databases and external information sources. This collected data is then formatted into a format suitable for analysis. This process includes using Python to quantify the data and convert it into a unified format.

[0101] Next, the server uses the formatted data to train a generative AI model. During this process, machine learning libraries such as TensorFlow are used to build the model based on past supply and demand patterns. This enables automated forecasting of future supply and demand. The generated model is then evaluated to check its accuracy and effectiveness, and adjusted as needed.

[0102] Furthermore, the terminals collect new supply and demand data in real time, and the servers process this data immediately to update the supply and demand forecast. This real-time processing enables companies to make immediate decisions. Firebase Cloud Messaging is used to notify users of when to replenish inventory based on the supply and demand forecast. For example, a logistics center manager can receive supply and demand forecasts for new products using their smartphone. When the manager opens the app, a notification appears on the screen stating, "We are displaying the supply and demand forecast for new products. Please replenish inventory based on this information."

[0103] As an example of a prompt message for the generated AI model, by giving instructions to the server such as, "Generate a Python script that predicts next month's demand based on past inventory data and market trends," it is possible to build a model and obtain highly accurate forecast data. In this way, this system can optimize supply and demand forecasting and inventory management in real time, thereby improving the efficiency of the entire supply chain.

[0104] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0105] Step 1:

[0106] The server collects historical supply and demand data from databases and external sources. Using this collected data as input, it performs data formatting using Python to convert the data into numerical values ​​and then into a unified format. This allows for obtaining formatted data suitable for analysis.

[0107] Step 2:

[0108] The server starts training the generative AI model using the formatted data. In this step, the formatted data is used as input, and TensorFlow is used to model past supply and demand patterns using a deep learning algorithm. As output, an AI model for supply and demand forecasting is generated.

[0109] Step 3:

[0110] The server evaluates the generated AI model. In this step, data calculations are performed using a known dataset as input to verify the model's accuracy and usefulness. Based on the evaluation results, the model's parameters are adjusted as needed to improve the model's accuracy.

[0111] Step 4:

[0112] The terminal receives new supply and demand data from the user. Using this new data as input, the server processes the data in real time and updates the current supply and demand forecast. This allows the updated supply and demand forecast data to be output.

[0113] Step 5:

[0114] The server optimizes inventory management based on updated supply and demand forecasts. In this step, it takes supply and demand forecast data as input, automatically calculates the timing and quantity of inventory replenishment, and outputs optimal inventory management information.

[0115] Step 6:

[0116] Users receive supply and demand forecast information from the server via their terminals. Using this information as input, they can receive real-time notifications for inventory replenishment based on the supply and demand forecast, enabling rapid management of the logistics center. As output, specific replenishment instructions are displayed on the terminals.

[0117] 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.

[0118] This invention aims to improve the accuracy of demand management and further streamline the entire supply chain by combining an emotion engine with a supply and demand forecasting system. The program processing of this system is described below in natural language.

[0119] The server first collects and formats supply and demand data from both inside and outside the company. Data formatting includes noise removal and standardization of format, and the data is then used to train a generative AI model.

[0120] Next, the server evaluates the trained model and implements a process to improve its accuracy. This process utilizes an emotion engine, incorporating user sentiment data. For example, the emotion engine analyzes user reactions to the market launch of a new product in real time and incorporates the results as input data for the AI ​​model.

[0121] Furthermore, the device receives input data and feedback from actual users and processes it in real time. During this process, the emotion engine analyzes the received emotion data and uses it to adjust the AI ​​model and update supply and demand forecasts.

[0122] As a concrete example, consider a scenario where a user develops a new promotional strategy. Customer feedback on the effectiveness of the promotion is analyzed by an emotion engine, and the server re-evaluates supply and demand forecasts based on the analysis results, predicting the likelihood of the promotion's success and inventory demand.

[0123] Finally, based on the generated supply and demand forecasts and analysis, the server suggests recommended actions to the user. This enables smoother coordination across the entire supply chain.

[0124] This invention aims to significantly improve the operational efficiency of companies by enabling advanced supply and demand forecasting and supply chain management that incorporates user sentiment data.

[0125] The following describes the processing flow.

[0126] Step 1:

[0127] The server collects historical and current supply and demand data from the company's internal databases and external APIs. This data includes sales history, inventory information, and market trends.

[0128] Step 2:

[0129] The server cleanses, removes noise, and formats the collected data. This includes the process of eliminating unnecessary data and converting the data to a standard format.

[0130] Step 3:

[0131] The server trains a generative AI model based on the formatted data. In this step, machine learning algorithms are used to create a model that learns past patterns and predicts future demand.

[0132] Step 4:

[0133] The server evaluates the model's accuracy and verifies prediction accuracy using test data. If necessary, the model parameters are adjusted to improve prediction accuracy.

[0134] Step 5:

[0135] The device receives real-time data such as quantitative feedback from users and market trends. This data is also used for analysis by the emotion engine.

[0136] Step 6:

[0137] The server uses an emotion engine to analyze user emotion data. This analysis allows the emotional aspects of the feedback to be reflected in the model's adjustments. For example, positive customer responses may be considered as facilitators.

[0138] Step 7:

[0139] The server updates the model based on new information, including sentiment data, and refines the supply and demand forecast. This ensures that the forecast is always up-to-date.

[0140] Step 8:

[0141] The server optimizes inventory management plans based on the supply and demand forecasts it generates. These plans are used to manage inventory replenishment and logistics adjustments.

[0142] Step 9:

[0143] The server periodically generates supply and demand forecasts and analysis information as reports and provides them to users. These reports also include recommended actions to support user decision-making.

[0144] (Example 2)

[0145] 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".

[0146] Improving the accuracy of supply and demand forecasts and streamlining supply chains are crucial challenges in modern business operations. However, traditional methods have limitations in forecast accuracy and supply chain flexibility because it is difficult to analyze consumer sentiment and opinions in real time and incorporate them into demand forecasts. This can lead to problems such as excess inventory and stockouts, potentially resulting in economic losses.

[0147] 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.

[0148] In this invention, the server includes means for acquiring and preprocessing data, means for training a learning model using the preprocessed data, means for evaluating the performance of the trained model and improving its accuracy, means for processing time-series data and revising supply and demand forecasts, means for analyzing user sentiment information and integrating the results into a generating AI model, and means for adjusting inventory levels based on the revised forecasts. This enables highly accurate supply and demand forecasts that reflect consumer sentiment and efficient supply chain management based on them.

[0149] "Acquiring and pre-processing data" means gathering various information from both inside and outside the company, and processing it through noise reduction and format standardization to make it suitable for model training.

[0150] "Training a learning model" is the process of optimizing algorithms that use AI technology to make predictions and classifications using pre-processed data.

[0151] "Evaluating the performance of a model and improving its accuracy" means testing a trained model with real data, measuring its predictive ability, and making adjustments to further improve it.

[0152] "Processing time-series data and revising forecasts" is the process of updating previously generated supply and demand forecasts using newly obtained data to more accurately reflect current trends.

[0153] "Analyzing user emotional information and integrating the results into a generative AI model" means analyzing emotions from user feedback and reactions, incorporating that information into a predictive model, and making predictions that take emotional factors into account.

[0154] "Adjusting inventory levels" means determining the optimal inventory level based on supply and demand forecasts and managing inventory to prevent excess stock and stockouts.

[0155] This invention combines an emotion engine with a supply and demand forecasting system, with the aim of improving the accuracy of supply and demand forecasts and increasing the efficiency of the supply chain.

[0156] First, the server collects and preprocesses the data. Specifically, it retrieves information from databases both inside and outside the company via the network, removes noise, and uses data processing software to standardize the data format. As an example, Python and the Pandas library are used for data processing.

[0157] Next, the server uses the preprocessed data to train a generative AI model. Here, TensorFlow is used as the AI ​​framework to build a neural network and optimize the algorithm for supply and demand forecasting from the data.

[0158] Furthermore, the server utilizes an emotion engine to acquire and analyze user emotional information in real time. This involves using emotion analysis software to convert user feedback and reactions into emotional data. For example, tools like Affectiva are used for emotion analysis.

[0159] As real-time data processing takes place and emotional data is integrated into the generating AI model, the server revises demand forecasts. This enables efficient adjustments to prevent inventory surpluses and shortages.

[0160] Furthermore, the terminal receives the latest input and feedback from users and sends it to the server. This ensures that supply and demand forecasts are more accurate to the current situation, supporting corporate decision-making.

[0161] For example, when implementing a new promotion, a user can input a prompt into the AI ​​model such as, "Please generate a supply and demand forecast for the next quarter and output the results reflecting consumer sentiment data." This system can then perform the supply and demand forecast according to the input instructions and output relevant reports and recommended actions.

[0162] This invention enables users to achieve highly accurate supply and demand forecasts that take consumer sentiment into account, and optimizes the supply chain management of companies.

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

[0164] Step 1:

[0165] The server first collects data. It retrieves supply and demand-related data from internal and external databases and online resources. The input data includes sales history, inventory information, and external market trends. Because this data initially contains various formats and noise, it is collected using database queries and APIs. The output is a raw dataset.

[0166] Step 2:

[0167] The server preprocesses the collected data. A raw dataset is provided as input. This step involves noise reduction, missing data imputation, and format conversion. The Python Pandas library is used to perform data cleaning, outputting formatted data that allows the trained model to function correctly.

[0168] Step 3:

[0169] The server trains a generative AI model using formatted data. A pre-processed dataset is provided as input. TensorFlow is used to build a neural network and train the model. The output is a trained model with improved prediction accuracy.

[0170] Step 4:

[0171] The server evaluates the performance of the trained model and implements measures to improve its accuracy. It uses the test dataset as input. Evaluation metrics such as accuracy and the F1 score are calculated. This optimizes the model's output, resulting in a more accurate model for new data.

[0172] Step 5:

[0173] The server uses an emotion engine to analyze user emotional information. Inputs include user feedback and reviews. Sentiment analysis software is used to analyze the data and quantify the user's emotions. The output is the analyzed emotional data.

[0174] Step 6:

[0175] The server integrates sentiment data into a generating AI model to revise supply and demand forecasts. Inputs include model outputs and sentiment data. Historical sales data and sentiment data are combined to adjust the forecasts. This results in highly accurate supply and demand forecasts that take sentiment into account.

[0176] Step 7:

[0177] The terminal receives new input and feedback from the user and immediately sends it to the server. Input includes new prompts and market fluctuation information. Processing the data in real time updates supply and demand forecasts. The output is the updated supply and demand forecast information.

[0178] Step 8:

[0179] The server optimizes inventory management based on supply and demand forecasts. The input is updated supply and demand forecast data. This step adjusts inventory levels to prevent excess inventory and stockouts. The output is an optimized inventory management plan.

[0180] (Application Example 2)

[0181] 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".

[0182] In increasingly complex supply networks, there is a growing need for improved accuracy in supply and demand forecasting and optimized inventory control. Traditional supply and demand forecasting is often based on historical numerical data, making it difficult to respond flexibly to customer sentiment. Furthermore, it may not be able to respond quickly to sudden demand fluctuations or market changes based on customer sentiment, potentially leading to inventory shortages or surpluses. This reduces the efficiency of the entire supply network, and as a result, there is a need to solve the problems that undermine business reliability and customer satisfaction.

[0183] 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.

[0184] In this invention, the server includes a device for collecting and formatting data, a device for training a generative AI model using the formatted data, a device for processing real-time data and updating supply and demand forecasts, and a device for analyzing sentiment data and reflecting it in the supply and demand forecasts. This enables highly accurate supply and demand forecasting and optimization of inventory control using sentiment data.

[0185] A "data collection and formatting device" is a device that takes in data from both inside and outside a company, removes noise, standardizes the format, and converts it into a form suitable for training AI models.

[0186] A "device for training generative AI models" is a device that uses formatted data to train AI models and build the knowledge necessary for supply and demand forecasting.

[0187] A "device for evaluating generated predictive models and improving their prediction accuracy" is a device that evaluates trained AI models and makes adjustments to improve their accuracy.

[0188] A "device that processes real-time data and updates supply and demand forecasts" is a device that uses the latest data acquired from the market and users to constantly update supply and demand forecasts to the most up-to-date state.

[0189] A "device that analyzes emotional data and reflects it in supply and demand forecasts" is a device that analyzes data based on user and market sentiment and incorporates the results into supply and demand forecasts, thereby enabling more accurate predictions.

[0190] A "device for optimizing inventory control" is a device that, based on updated supply and demand forecasts, plans to maintain appropriate inventory levels and prevent surpluses and shortages.

[0191] A "device for optimizing the supply network" is a device that improves the efficiency of the entire supply chain by optimizing supply and demand forecasting and inventory control.

[0192] A "notification and warning generation device" is a device that detects important changes or abnormal situations based on supply and demand forecasts and generates information to immediately inform relevant parties.

[0193] The system implementing this invention consists of multiple devices. The server first collects and formats data from both inside and outside the company. Here, it removes noise from data in various formats obtained through REST APIs using Pandas or similar tools, and standardizes the format. This formatted data is then used as a dataset for training a generative AI model.

[0194] The server then trains a generative AI model using TensorFlow. This model possesses fundamental knowledge for supply and demand forecasting, and the server performs evaluation and adjustments to improve prediction accuracy. Furthermore, Azure Cognitive Services is used to analyze sentiment data, feeding this sentiment data from users and the market back into the AI ​​model. This process is continuous, leading to more accurate supply and demand forecasts.

[0195] The terminals are responsible for processing real-time data and updating supply and demand forecasts. They receive input data and feedback from users and send it to the server. Based on the data obtained, the server updates the supply and demand forecast and optimizes inventory control. This enables proper inventory management at logistics centers and improves the efficiency of the entire supply network.

[0196] A concrete example is a scenario where a logistics center manager uses an application to respond to a sudden surge in demand. The application uses real-time updated supply and demand forecast data to suggest the optimal amount of inventory to replenish, preventing disruption to the supply network. Since the results of sentiment data analysis are also utilized in this process, the factors influencing demand fluctuations can be captured more accurately.

[0197] An example of a prompt for the generated AI model is, "Based on the latest supply and demand data, forecast demand for next week and propose an inventory replenishment plan that incorporates sentiment data." This enables highly accurate supply and demand forecasting and efficient inventory management using artificial intelligence.

[0198] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0199] Step 1:

[0200] The server collects data from both within and outside the company. Input data is obtained from various APIs and databases. This data includes inventory information, transaction history, and customer feedback. The output is raw data that requires formatting. Data analysis tools such as Pandas are used to remove noise and standardize the format.

[0201] Step 2:

[0202] The server formats the acquired raw data. The raw data obtained in step 1 is used as input. Data processing is performed to remove noise and standardize the format, resulting in a clean and consistent dataset as output. This dataset is used to train the generative AI model.

[0203] Step 3:

[0204] The server trains a generative AI model using formatted data. A formatted dataset is provided as input, and the model is trained using a framework such as TensorFlow. The output is an AI model for supply and demand forecasting. This model makes predictions based on user input and external data.

[0205] Step 4:

[0206] The server evaluates the generated model and improves its prediction accuracy. The evaluation uses a comparison between real-time data and past prediction results. New data and prediction results are taken as input, and the model is adjusted through evaluation, resulting in an output AI model with improved prediction accuracy.

[0207] Step 5:

[0208] The terminal processes real-time data and updates supply and demand forecasts. Real-time data from user actions is provided as input, including inventory movements and new order information. The server updates the model, instantly updating the supply and demand forecast and providing the latest forecast data as output.

[0209] Step 6:

[0210] The server analyzes sentiment data and incorporates it into supply and demand forecasts. Azure Cognitive Services is used to analyze user sentiment data. Customer feedback data is provided as input. The analysis results are used as model input, resulting in more accurate supply and demand forecasts.

[0211] Step 7:

[0212] The server optimizes inventory control based on updated supply and demand forecasts and notifies the user. The user is then presented with a proposed inventory replenishment plan. The latest supply and demand forecasts and inventory data are used as input. The output provides specific inventory management strategies to improve the efficiency of the supply network.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] [Second Embodiment]

[0217] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0218] 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.

[0219] 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).

[0220] 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.

[0221] 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.

[0222] 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).

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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".

[0229] In this embodiment of the invention, a system is constructed in which data collection, AI model training, model evaluation, real-time data processing, and inventory management optimization are seamlessly integrated. The system's program processing is described below in natural language.

[0230] First, the server retrieves historical demand data from multiple sources. This data collection is automated, drawing from internal company systems and external supply chain information. Data formatting includes digitization and conversion to standard formats.

[0231] Next, the server trains an AI model using the formatted data. This process uses machine learning algorithms, including deep learning, to learn past supply and demand patterns and predict future demand. The generated model is then evaluated on a known dataset to verify its accuracy.

[0232] Furthermore, real-time data updates are crucial. Terminals allow users to input new data, and the system processes this instantly, providing the latest supply and demand forecasts. This real-time processing enables businesses to take immediate action.

[0233] Regarding inventory management optimization, the system automatically controls inventory replenishment and adjustment based on predictive data generated by the server. This allows users to avoid inventory surpluses and shortages, enabling efficient supply chain management.

[0234] As a concrete example, when a user checks the demand forecast for a new product, the server integrates data from similar past products with current market trends to provide a demand forecast. Based on this forecast, the user can proactively adjust inventory.

[0235] In this way, this system supports the efficient operation of businesses by automating supply and demand forecasting and inventory management using AI.

[0236] The following describes the processing flow.

[0237] Step 1:

[0238] The server automatically collects historical supply and demand data from both within and outside the company. The data is obtained from various system databases and external APIs.

[0239] Step 2:

[0240] The server cleans and formats the collected data. This process removes noise and converts the data into a standard format. Missing values ​​and anomalies are also handled at this stage.

[0241] Step 3:

[0242] The server trains an AI model using the formatted data. The goal here is to learn patterns within the dataset using machine learning algorithms and predict future demand.

[0243] Step 4:

[0244] The server evaluates the trained model. Test data is used for evaluation to check the model's prediction accuracy. Model parameters are adjusted as needed to improve accuracy.

[0245] Step 5:

[0246] The terminal receives new data from the user in real time. The data entered by the user is processed immediately, and the supply and demand forecast is updated.

[0247] Step 6:

[0248] The server optimizes inventory management using the latest forecast data. Specifically, it replenishes and adjusts inventory according to future demand. Users are provided with new supply and demand forecast information.

[0249] Step 7:

[0250] The server periodically generates and provides users with reports based on supply and demand forecasts. These reports include an overview of the demand forecast and recommended adjustments to inventory levels. Users utilize this information to develop business strategies.

[0251] (Example 1)

[0252] 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".

[0253] Efficient data management and optimized supply and demand forecasting are critical challenges in current business operations. In particular, unifying data from diverse sources and building accurate forecasting models is not easy. Furthermore, while real-time data updates are required to rapidly adjust supply and demand, traditional methods struggle to achieve this efficiently.

[0254] 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.

[0255] In this invention, the server includes means for collecting information and converting it into a standard format, means for performing machine learning using the converted information, and means for evaluating the generated prediction method and improving its accuracy. This makes it possible to integrate diverse information and perform rapid and accurate supply and demand forecasting.

[0256] "Means of information gathering" refers to the process of automatically acquiring data from various sources, both internal and external to a company.

[0257] "Methods for converting to a standard format" refers to the process of unifying data in different formats into a consistent format, making it easier to perform subsequent processing and analysis.

[0258] "Methods for performing machine learning" refers to the process of learning patterns based on past data and applying algorithms to gain new insights.

[0259] "Means for evaluating prediction methods" refers to the process of objectively determining the accuracy and reliability of the generated model using specific evaluation metrics.

[0260] "Means of improving accuracy" refers to the process of improving data and algorithms to enhance the performance of predictive models.

[0261] "Means of optimizing the flow of materials" refers to the process of efficiently managing the supply and inventory of goods based on supply and demand forecasts.

[0262] "Means of improving the efficiency of the supply network" refers to the process of optimizing the operation of the entire supply chain and reducing waste of resources.

[0263] "Methods for creating reports" refers to the process of systematically generating documents based on data analysis results, making the situation visually clear.

[0264] "Means of issuing warnings" refers to the process of quickly issuing alerts when a specific threshold is exceeded based on prediction results or real-time data.

[0265] The embodiments for carrying out the present invention will now be described. This system enables efficient supply and demand forecasting and inventory management, and functions in cooperation with a server, terminals, and users.

[0266] First, the server accesses various corporate information sources to collect data. This includes internal ERP systems and external market databases. The server then uses ETL tools to format the collected data into a standard format. This process integrates the data into an analyzable form.

[0267] Next, the server uses machine learning algorithms to train an AI model based on the formatted data. Here, TensorFlow is used as the deep learning framework. The AI ​​model learns past supply and demand patterns and gains the ability to predict future demand.

[0268] Subsequently, the accuracy of the generated model is evaluated using a known dataset. This evaluation process measures the model's predictive accuracy and allows for necessary improvements.

[0269] A terminal is used to update real-time data. Users input new data through the terminal, and this data is sent to the server, allowing the system to immediately revise supply and demand forecasts. For example, sales data can be entered using a tablet or smartphone application, and the forecast can be updated in real time.

[0270] Based on the generated supply and demand forecast data, the server automatically controls inventory replenishment and adjustment. This process optimizes the flow of materials, enabling companies to achieve efficient inventory management.

[0271] As a concrete example, when a user plans a sales campaign for a new product, they use a terminal to input campaign information into the system. By sending a prompt message to the server such as, "Please update the supply and demand baseline to reflect next month's new product sales campaign," the system provides the latest supply and demand forecast, allowing the user to adjust their inventory strategy.

[0272] Through this configuration, the system provides a technological foundation that supports the automation and efficiency of supply and demand forecasting and inventory management.

[0273] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0274] Step 1:

[0275] The server uses a database management system to automatically collect data from internal and external sources within the company. Specifically, it periodically retrieves information from ERP systems and market databases via APIs. This input data includes production figures, sales figures, and market trends. The server converts this data into a standard format using ETL tools, making it analyzable. The output is a dataset in a unified format.

[0276] Step 2:

[0277] Based on the preprocessed data, the server trains an AI model using machine learning algorithms. Specifically, it uses TensorFlow to learn the demand prediction patterns from historical data. The input to this process is a unified dataset, and the output is a trained AI model. During training, the system performs iterative calculations to minimize the loss function and improve accuracy.

[0278] Step 3:

[0279] The server evaluates the AI model generated using the new dataset. The data operations performed here involve using existing data as input and comparing the predicted values and actual performance of the model. As specific actions, metrics such as accuracy, recall, and F1-score are calculated to evaluate the model performance. The output is the evaluation result and improvement points of the model.

[0280] Step 4:

[0281] The terminal accepts real-time data input by the user. The specific operation is to input inventory and sales information through dedicated apps on tablets or smartphones. The input data is immediately processed by the server to update the supply-demand prediction. The output is the latest supply-demand prediction.

[0282] Step 5:

[0283] Based on the generated supply-demand data, the server optimizes the material flow and adjusts the inventory. As a specific action, it automatically issues inventory replenishment instructions according to the predicted demand. The input is the updated supply-demand prediction data, and the output is the replenishment plan and order instruction.

[0284] Step 6:

[0285] The user sends a prompt sentence to the system in order to obtain the information necessary for adjusting inventory and sales strategies. Specifically, a prompt sentence such as "Please update the supply-demand baseline reflecting the new product sales campaign for the next month" is used. The server processes this and provides the user with the latest information. The input is the prompt sentence, and the output is the adjusted supply-demand prediction information.

[0286] (Application Example 1)

[0287] 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".

[0288] In modern logistics centers, there is a demand for improving inventory management efficiency and refining supply-demand forecasting. However, with conventional methods, real-time supply-demand forecast updates are insufficient, and it is difficult to replenish inventory at the appropriate timing. For this reason, there are often problems such as overstocking or shortages of inventory, and it is difficult to optimize the supply chain.

[0289] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0290] In this invention, the server includes means for collecting and shaping data, means for training a generated AI model using the shaped data, and means for presenting prediction information in real time and notifying the replenishment timing. As a result, it becomes possible to optimize inventory management in the logistics center in real time and improve the efficiency of the supply chain.

[0291] The "means for collecting and shaping data" is a function that converts raw data imported from a database or external information source into a format suitable for analysis and model creation.

[0292] The "means for training a generated AI model" is a step of constructing a model capable of supply-demand prediction using an AI algorithm based on past data.

[0293] "Methods for evaluating predictive models" refer to the process of verifying the accuracy and usefulness of the generated AI model and improving or adjusting the model.

[0294] "Means for processing real-time data and updating supply and demand forecasts" refers to a function that immediately analyzes newly obtained data to reflect the current supply and demand situation and update the forecast.

[0295] "Means for optimizing inventory management based on updated supply and demand forecasts" refers to a mechanism that adjusts inventory purchases and placements based on forecast data, thereby ensuring the efficient use of resources.

[0296] "A means of providing real-time forecast information and notifying users of replenishment timing" refers to a function that provides information to quickly inform users of the period when inventory shortages are predicted.

[0297] To implement this invention, it is necessary to build a system in which multiple components work seamlessly together. First, the server automatically collects historical supply and demand data from databases and external information sources. This collected data is then formatted into a format suitable for analysis. This process includes using Python to quantify the data and convert it into a unified format.

[0298] Next, the server uses the formatted data to train a generative AI model. During this process, machine learning libraries such as TensorFlow are used to build the model based on past supply and demand patterns. This enables automated forecasting of future supply and demand. The generated model is then evaluated to check its accuracy and effectiveness, and adjusted as needed.

[0299] Furthermore, the terminals collect new supply and demand data in real time, and the servers process this data immediately to update the supply and demand forecast. This real-time processing enables companies to make immediate decisions. Firebase Cloud Messaging is used to notify users of when to replenish inventory based on the supply and demand forecast. For example, a logistics center manager can receive supply and demand forecasts for new products using their smartphone. When the manager opens the app, a notification appears on the screen stating, "We are displaying the supply and demand forecast for new products. Please replenish inventory based on this information."

[0300] As an example of a prompt message for the generated AI model, by giving instructions to the server such as, "Generate a Python script that predicts next month's demand based on past inventory data and market trends," it is possible to build a model and obtain highly accurate forecast data. In this way, this system can optimize supply and demand forecasting and inventory management in real time, thereby improving the efficiency of the entire supply chain.

[0301] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0302] Step 1:

[0303] The server collects historical supply and demand data from databases and external sources. Using this collected data as input, it performs data formatting using Python to convert the data into numerical values ​​and then into a unified format. This allows for obtaining formatted data suitable for analysis.

[0304] Step 2:

[0305] The server starts training the generative AI model using the formatted data. In this step, the formatted data is used as input, and TensorFlow is used to model past supply and demand patterns using a deep learning algorithm. As output, an AI model for supply and demand forecasting is generated.

[0306] Step 3:

[0307] The server evaluates the generated AI model. In this step, a known dataset is used as input, and data operations are performed to verify the accuracy and usefulness of the model. Based on the evaluation results, the model parameters are adjusted as necessary to improve the model's accuracy.

[0308] Step 4:

[0309] The terminal receives new supply and demand data from the user. Using this new data as input, the server performs real-time data processing and updates the current supply and demand forecast. As a result, updated supply and demand forecast data can be output.

[0310] Step 5:

[0311] The server performs a process to optimize inventory management based on the updated supply and demand forecast. In this step, using the supply and demand forecast data as input, the timing and quantity of inventory replenishment are automatically calculated, and optimal inventory management information is output.

[0312] Step 6:

[0313] The user receives supply and demand forecast information from the server through the terminal. Using this information as input, by receiving real-time inventory replenishment notifications based on the supply and demand forecast, it is possible to quickly manage the logistics center. As output, a notification of specific replenishment instructions is displayed on the terminal.

[0314] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion.

[0315] This invention aims to improve the accuracy of demand management and further streamline the entire supply chain by combining an emotion engine with a supply and demand forecasting system. The program processing of this system is described below in natural language.

[0316] The server first collects and formats supply and demand data from both inside and outside the company. Data formatting includes noise removal and standardization of format, and the data is then used to train a generative AI model.

[0317] Next, the server evaluates the trained model and implements a process to improve its accuracy. This process utilizes an emotion engine, incorporating user sentiment data. For example, the emotion engine analyzes user reactions to the market launch of a new product in real time and incorporates the results as input data for the AI ​​model.

[0318] Furthermore, the device receives input data and feedback from actual users and processes it in real time. During this process, the emotion engine analyzes the received emotion data and uses it to adjust the AI ​​model and update supply and demand forecasts.

[0319] As a concrete example, consider a scenario where a user develops a new promotional strategy. Customer feedback on the effectiveness of the promotion is analyzed by an emotion engine, and the server re-evaluates supply and demand forecasts based on the analysis results, predicting the likelihood of the promotion's success and inventory demand.

[0320] Finally, based on the generated supply and demand forecasts and analysis, the server suggests recommended actions to the user. This enables smoother coordination across the entire supply chain.

[0321] This invention aims to significantly improve the operational efficiency of companies by enabling advanced supply and demand forecasting and supply chain management that incorporates user sentiment data.

[0322] The following describes the processing flow.

[0323] Step 1:

[0324] The server collects historical and current supply and demand data from the company's internal databases and external APIs. This data includes sales history, inventory information, and market trends.

[0325] Step 2:

[0326] The server cleanses, removes noise, and formats the collected data. This includes the process of eliminating unnecessary data and converting the data to a standard format.

[0327] Step 3:

[0328] The server trains a generative AI model based on the formatted data. In this step, machine learning algorithms are used to create a model that learns past patterns and predicts future demand.

[0329] Step 4:

[0330] The server evaluates the model's accuracy and verifies prediction accuracy using test data. If necessary, the model parameters are adjusted to improve prediction accuracy.

[0331] Step 5:

[0332] The device receives real-time data such as quantitative feedback from users and market trends. This data is also used for analysis by the emotion engine.

[0333] Step 6:

[0334] The server uses an emotion engine to analyze user emotion data. This analysis allows the emotional aspects of the feedback to be reflected in the model's adjustments. For example, positive customer responses may be considered as facilitators.

[0335] Step 7:

[0336] The server updates the model based on new information, including sentiment data, and refines the supply and demand forecast. This ensures that the forecast is always up-to-date.

[0337] Step 8:

[0338] The server optimizes inventory management plans based on the supply and demand forecasts it generates. These plans are used to manage inventory replenishment and logistics adjustments.

[0339] Step 9:

[0340] The server periodically generates supply and demand forecasts and analysis information as reports and provides them to users. These reports also include recommended actions to support user decision-making.

[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] Improving the accuracy of supply and demand forecasts and streamlining supply chains are crucial challenges in modern business operations. However, traditional methods have limitations in forecast accuracy and supply chain flexibility because it is difficult to analyze consumer sentiment and opinions in real time and incorporate them into demand forecasts. This can lead to problems such as excess inventory and stockouts, potentially resulting in economic losses.

[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 acquiring and preprocessing data, means for training a learning model using the preprocessed data, means for evaluating the performance of the trained model and improving its accuracy, means for processing time-series data and revising supply and demand forecasts, means for analyzing user sentiment information and integrating the results into a generating AI model, and means for adjusting inventory levels based on the revised forecasts. This enables highly accurate supply and demand forecasts that reflect consumer sentiment and efficient supply chain management based on them.

[0346] "Acquiring and pre-processing data" means gathering various information from both inside and outside the company, and processing it through noise reduction and format standardization to make it suitable for model training.

[0347] "Training a learning model" is the process of optimizing algorithms that use AI technology to make predictions and classifications using pre-processed data.

[0348] "Evaluating the performance of a model and improving its accuracy" means testing a trained model with real data, measuring its predictive ability, and making adjustments to further improve it.

[0349] "Processing time-series data and revising forecasts" is the process of updating previously generated supply and demand forecasts using newly obtained data to more accurately reflect current trends.

[0350] "Analyzing user emotional information and integrating the results into a generative AI model" means analyzing emotions from user feedback and reactions, incorporating that information into a predictive model, and making predictions that take emotional factors into account.

[0351] "Adjusting inventory levels" means determining the optimal inventory level based on supply and demand forecasts and managing inventory to prevent excess stock and stockouts.

[0352] This invention combines an emotion engine with a supply and demand forecasting system, with the aim of improving the accuracy of supply and demand forecasts and increasing the efficiency of the supply chain.

[0353] First, the server collects and preprocesses the data. Specifically, it retrieves information from databases both inside and outside the company via the network, removes noise, and uses data processing software to standardize the data format. As an example, Python and the Pandas library are used for data processing.

[0354] Next, the server uses the preprocessed data to train a generative AI model. Here, TensorFlow is used as the AI ​​framework to build a neural network and optimize the algorithm for supply and demand forecasting from the data.

[0355] Furthermore, the server utilizes an emotion engine to acquire and analyze user emotional information in real time. This involves using emotion analysis software to convert user feedback and reactions into emotional data. For example, tools like Affectiva are used for emotion analysis.

[0356] As real-time data processing takes place and emotional data is integrated into the generating AI model, the server revises demand forecasts. This enables efficient adjustments to prevent inventory surpluses and shortages.

[0357] Furthermore, the terminal receives the latest input and feedback from users and sends it to the server. This ensures that supply and demand forecasts are more accurate to the current situation, supporting corporate decision-making.

[0358] For example, when implementing a new promotion, a user can input a prompt into the AI ​​model such as, "Please generate a supply and demand forecast for the next quarter and output the results reflecting consumer sentiment data." This system can then perform the supply and demand forecast according to the input instructions and output relevant reports and recommended actions.

[0359] This invention enables users to achieve highly accurate supply and demand forecasts that take consumer sentiment into account, and optimizes the supply chain management of companies.

[0360] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0361] Step 1:

[0362] The server first collects data. It retrieves supply and demand-related data from internal and external databases and online resources. The input data includes sales history, inventory information, and external market trends. Because this data initially contains various formats and noise, it is collected using database queries and APIs. The output is a raw dataset.

[0363] Step 2:

[0364] The server preprocesses the collected data. A raw dataset is provided as input. This step involves noise reduction, missing data imputation, and format conversion. The Python Pandas library is used to perform data cleaning, outputting formatted data that allows the trained model to function correctly.

[0365] Step 3:

[0366] The server trains a generative AI model using formatted data. A pre-processed dataset is provided as input. TensorFlow is used to build a neural network and train the model. The output is a trained model with improved prediction accuracy.

[0367] Step 4:

[0368] The server evaluates the performance of the trained model and implements measures to improve its accuracy. It uses the test dataset as input. Evaluation metrics such as accuracy and the F1 score are calculated. This optimizes the model's output, resulting in a more accurate model for new data.

[0369] Step 5:

[0370] The server uses an emotion engine to analyze user emotional information. Inputs include user feedback and reviews. Sentiment analysis software is used to analyze the data and quantify the user's emotions. The output is the analyzed emotional data.

[0371] Step 6:

[0372] The server integrates sentiment data into a generating AI model to revise supply and demand forecasts. Inputs include model outputs and sentiment data. Historical sales data and sentiment data are combined to adjust the forecasts. This results in highly accurate supply and demand forecasts that take sentiment into account.

[0373] Step 7:

[0374] The terminal receives new input and feedback from the user and immediately sends it to the server. Input includes new prompts and market fluctuation information. Processing the data in real time updates supply and demand forecasts. The output is the updated supply and demand forecast information.

[0375] Step 8:

[0376] The server optimizes inventory management based on supply and demand forecasts. The input is updated supply and demand forecast data. This step adjusts inventory levels to prevent excess inventory and stockouts. The output is an optimized inventory management plan.

[0377] (Application Example 2)

[0378] 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."

[0379] In increasingly complex supply networks, there is a growing need for improved accuracy in supply and demand forecasting and optimized inventory control. Traditional supply and demand forecasting is often based on historical numerical data, making it difficult to respond flexibly to customer sentiment. Furthermore, it may not be able to respond quickly to sudden demand fluctuations or market changes based on customer sentiment, potentially leading to inventory shortages or surpluses. This reduces the efficiency of the entire supply network, and as a result, there is a need to solve the problems that undermine business reliability and customer satisfaction.

[0380] 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.

[0381] In this invention, the server includes a device for collecting and formatting data, a device for training a generative AI model using the formatted data, a device for processing real-time data and updating supply and demand forecasts, and a device for analyzing sentiment data and reflecting it in the supply and demand forecasts. This enables highly accurate supply and demand forecasting and optimization of inventory control using sentiment data.

[0382] A "data collection and formatting device" is a device that takes in data from both inside and outside a company, removes noise, standardizes the format, and converts it into a form suitable for training AI models.

[0383] A "device for training generative AI models" is a device that uses formatted data to train AI models and build the knowledge necessary for supply and demand forecasting.

[0384] A "device for evaluating generated predictive models and improving their prediction accuracy" is a device that evaluates trained AI models and makes adjustments to improve their accuracy.

[0385] A "device that processes real-time data and updates supply and demand forecasts" is a device that uses the latest data acquired from the market and users to constantly update supply and demand forecasts to the most up-to-date state.

[0386] A "device that analyzes emotional data and reflects it in supply and demand forecasts" is a device that analyzes data based on user and market sentiment and incorporates the results into supply and demand forecasts, thereby enabling more accurate predictions.

[0387] A "device for optimizing inventory control" is a device that, based on updated supply and demand forecasts, plans to maintain appropriate inventory levels and prevent surpluses and shortages.

[0388] A "device for optimizing the supply network" is a device that improves the efficiency of the entire supply chain by optimizing supply and demand forecasting and inventory control.

[0389] A "notification and warning generation device" is a device that detects important changes or abnormal situations based on supply and demand forecasts and generates information to immediately inform relevant parties.

[0390] The system implementing this invention consists of multiple devices. The server first collects and formats data from both inside and outside the company. Here, it removes noise from data in various formats obtained through REST APIs using Pandas or similar tools, and standardizes the format. This formatted data is then used as a dataset for training a generative AI model.

[0391] The server then trains a generative AI model using TensorFlow. This model possesses fundamental knowledge for supply and demand forecasting, and the server performs evaluation and adjustments to improve prediction accuracy. Furthermore, Azure Cognitive Services is used to analyze sentiment data, feeding this sentiment data from users and the market back into the AI ​​model. This process is continuous, leading to more accurate supply and demand forecasts.

[0392] The terminals are responsible for processing real-time data and updating supply and demand forecasts. They receive input data and feedback from users and send it to the server. Based on the data obtained, the server updates the supply and demand forecast and optimizes inventory control. This enables proper inventory management at logistics centers and improves the efficiency of the entire supply network.

[0393] A concrete example is a scenario where a logistics center manager uses an application to respond to a sudden surge in demand. The application uses real-time updated supply and demand forecast data to suggest the optimal amount of inventory to replenish, preventing disruption to the supply network. Since the results of sentiment data analysis are also utilized in this process, the factors influencing demand fluctuations can be captured more accurately.

[0394] An example of a prompt for the generated AI model is, "Based on the latest supply and demand data, forecast demand for next week and propose an inventory replenishment plan that incorporates sentiment data." This enables highly accurate supply and demand forecasting and efficient inventory management using artificial intelligence.

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] The server collects data from both within and outside the company. Input data is obtained from various APIs and databases. This data includes inventory information, transaction history, and customer feedback. The output is raw data that requires formatting. Data analysis tools such as Pandas are used to remove noise and standardize the format.

[0398] Step 2:

[0399] The server formats the acquired raw data. The raw data obtained in step 1 is used as input. Data processing is performed to remove noise and standardize the format, resulting in a clean and consistent dataset as output. This dataset is used to train the generative AI model.

[0400] Step 3:

[0401] The server trains a generative AI model using formatted data. A formatted dataset is provided as input, and the model is trained using a framework such as TensorFlow. The output is an AI model for supply and demand forecasting. This model makes predictions based on user input and external data.

[0402] Step 4:

[0403] The server evaluates the generated model and improves its prediction accuracy. The evaluation uses a comparison between real-time data and past prediction results. New data and prediction results are taken as input, and the model is adjusted through evaluation, resulting in an output AI model with improved prediction accuracy.

[0404] Step 5:

[0405] The terminal processes real-time data and updates supply and demand forecasts. Real-time data from user actions is provided as input, including inventory movements and new order information. The server updates the model, instantly updating the supply and demand forecast and providing the latest forecast data as output.

[0406] Step 6:

[0407] The server analyzes sentiment data and incorporates it into supply and demand forecasts. Azure Cognitive Services is used to analyze user sentiment data. Customer feedback data is provided as input. The analysis results are used as model input, resulting in more accurate supply and demand forecasts.

[0408] Step 7:

[0409] The server optimizes inventory control based on updated supply and demand forecasts and notifies the user. The user is then presented with a proposed inventory replenishment plan. The latest supply and demand forecasts and inventory data are used as input. The output provides specific inventory management strategies to improve the efficiency of the supply network.

[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] In this embodiment of the invention, a system is constructed in which data collection, AI model training, model evaluation, real-time data processing, and inventory management optimization are seamlessly integrated. The system's program processing is described below in natural language.

[0427] First, the server retrieves historical demand data from multiple sources. This data collection is automated, drawing from internal company systems and external supply chain information. Data formatting includes digitization and conversion to standard formats.

[0428] Next, the server trains an AI model using the formatted data. This process uses machine learning algorithms, including deep learning, to learn past supply and demand patterns and predict future demand. The generated model is then evaluated on a known dataset to verify its accuracy.

[0429] Furthermore, real-time data updates are crucial. Terminals allow users to input new data, and the system processes this instantly, providing the latest supply and demand forecasts. This real-time processing enables businesses to take immediate action.

[0430] Regarding inventory management optimization, the system automatically controls inventory replenishment and adjustment based on predictive data generated by the server. This allows users to avoid inventory surpluses and shortages, enabling efficient supply chain management.

[0431] As a concrete example, when a user checks the demand forecast for a new product, the server integrates data from similar past products with current market trends to provide a demand forecast. Based on this forecast, the user can proactively adjust inventory.

[0432] In this way, this system supports the efficient operation of businesses by automating supply and demand forecasting and inventory management using AI.

[0433] The following describes the processing flow.

[0434] Step 1:

[0435] The server automatically collects historical supply and demand data from both within and outside the company. The data is obtained from various system databases and external APIs.

[0436] Step 2:

[0437] The server cleans and formats the collected data. This process removes noise and converts the data into a standard format. Missing values ​​and anomalies are also handled at this stage.

[0438] Step 3:

[0439] The server trains an AI model using the formatted data. The goal here is to learn patterns within the dataset using machine learning algorithms and predict future demand.

[0440] Step 4:

[0441] The server evaluates the trained model. Test data is used for evaluation to check the model's prediction accuracy. Model parameters are adjusted as needed to improve accuracy.

[0442] Step 5:

[0443] The terminal receives new data from the user in real time. The data entered by the user is processed immediately, and the supply and demand forecast is updated.

[0444] Step 6:

[0445] The server optimizes inventory management using the latest forecast data. Specifically, it replenishes and adjusts inventory according to future demand. Users are provided with new supply and demand forecast information.

[0446] Step 7:

[0447] The server periodically generates and provides users with reports based on supply and demand forecasts. These reports include an overview of the demand forecast and recommended adjustments to inventory levels. Users utilize this information to develop business strategies.

[0448] (Example 1)

[0449] 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."

[0450] Efficient data management and optimized supply and demand forecasting are critical challenges in current business operations. In particular, unifying data from diverse sources and building accurate forecasting models is not easy. Furthermore, while real-time data updates are required to rapidly adjust supply and demand, traditional methods struggle to achieve this efficiently.

[0451] 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.

[0452] In this invention, the server includes means for collecting information and converting it into a standard format, means for performing machine learning using the converted information, and means for evaluating the generated prediction method and improving its accuracy. This makes it possible to integrate diverse information and perform rapid and accurate supply and demand forecasting.

[0453] "Means of information gathering" refers to the process of automatically acquiring data from various sources, both internal and external to a company.

[0454] "Methods for converting to a standard format" refers to the process of unifying data in different formats into a consistent format, making it easier to perform subsequent processing and analysis.

[0455] "Methods for performing machine learning" refers to the process of learning patterns based on past data and applying algorithms to gain new insights.

[0456] "Means for evaluating prediction methods" refers to the process of objectively determining the accuracy and reliability of the generated model using specific evaluation metrics.

[0457] "Means of improving accuracy" refers to the process of improving data and algorithms to enhance the performance of predictive models.

[0458] "Means of optimizing the flow of materials" refers to the process of efficiently managing the supply and inventory of goods based on supply and demand forecasts.

[0459] "Means of improving the efficiency of the supply network" refers to the process of optimizing the operation of the entire supply chain and reducing waste of resources.

[0460] "Methods for creating reports" refers to the process of systematically generating documents based on data analysis results, making the situation visually clear.

[0461] "Means of issuing warnings" refers to the process of quickly issuing alerts when a specific threshold is exceeded based on prediction results or real-time data.

[0462] The embodiments for carrying out the present invention will now be described. This system enables efficient supply and demand forecasting and inventory management, and functions in cooperation with a server, terminals, and users.

[0463] First, the server accesses various corporate information sources to collect data. This includes internal ERP systems and external market databases. The server then uses ETL tools to format the collected data into a standard format. This process integrates the data into an analyzable form.

[0464] Next, the server uses machine learning algorithms to train an AI model based on the formatted data. Here, TensorFlow is used as the deep learning framework. The AI ​​model learns past supply and demand patterns and gains the ability to predict future demand.

[0465] Subsequently, the accuracy of the generated model is evaluated using a known dataset. This evaluation process measures the model's predictive accuracy and allows for necessary improvements.

[0466] A terminal is used to update real-time data. Users input new data through the terminal, and this data is sent to the server, allowing the system to immediately revise supply and demand forecasts. For example, sales data can be entered using a tablet or smartphone application, and the forecast can be updated in real time.

[0467] Based on the generated supply and demand forecast data, the server automatically controls inventory replenishment and adjustment. This process optimizes the flow of materials, enabling companies to achieve efficient inventory management.

[0468] As a concrete example, when a user plans a sales campaign for a new product, they use a terminal to input campaign information into the system. By sending a prompt message to the server such as, "Please update the supply and demand baseline to reflect next month's new product sales campaign," the system provides the latest supply and demand forecast, allowing the user to adjust their inventory strategy.

[0469] Through this configuration, the system provides a technological foundation that supports the automation and efficiency of supply and demand forecasting and inventory management.

[0470] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0471] Step 1:

[0472] The server uses a database management system to automatically collect data from internal and external sources within the company. Specifically, it periodically retrieves information from ERP systems and market databases via APIs. This input data includes production figures, sales figures, and market trends. The server converts this data into a standard format using ETL tools, making it analyzable. The output is a dataset in a unified format.

[0473] Step 2:

[0474] Based on the formatted data, the server trains an AI model using machine learning algorithms. Specifically, it uses TensorFlow to learn demand forecasting patterns from historical data. The input to this process is a unified dataset, and the output is the trained AI model. During training, the system iterates to minimize the loss function and improve accuracy.

[0475] Step 3:

[0476] The server evaluates the AI ​​model generated using the new dataset. The data calculations performed here involve using existing data as input and comparing the model's predicted values ​​with actual values. Specifically, it calculates metrics such as accuracy, recall, and F1 score to evaluate model performance. The output consists of the model evaluation results and areas for improvement.

[0477] Step 4:

[0478] The terminal accepts real-time data input from the user. Specifically, users input inventory and sales information via a dedicated app on their tablet or smartphone. The server immediately processes the input data and updates the supply and demand forecast. The output is the latest supply and demand forecast.

[0479] Step 5:

[0480] Based on the generated supply and demand data, the server optimizes the flow of materials and adjusts inventory. Specifically, it automatically issues inventory replenishment orders in accordance with predicted demand. The input is updated supply and demand forecast data, and the output is replenishment plans and order orders.

[0481] Step 6:

[0482] The system receives prompt messages to obtain the information users need to adjust inventory and sales strategies. Specifically, prompt messages such as "Please update the supply and demand baseline to reflect next month's new product sales campaign" are used. The server processes these prompts and provides the user with the updated information. The input is the prompt message, and the output is the adjusted supply and demand forecast information.

[0483] (Application Example 1)

[0484] 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."

[0485] Modern logistics centers require efficient inventory management and precise supply and demand forecasting. However, traditional methods are insufficient for real-time updates of supply and demand forecasts, making it difficult to replenish inventory at the appropriate time. As a result, inventory surpluses and shortages often occur, posing a challenge to optimizing the supply chain.

[0486] 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.

[0487] In this invention, the server includes means for collecting and formatting data, means for training a generation AI model using the formatted data, and means for presenting predictive information in real time and notifying replenishment timing. This enables real-time optimization of inventory management in logistics centers and improves the efficiency of the supply chain.

[0488] "Means of collecting and formatting data" refers to the function of converting raw data imported from databases and external information sources into a format suitable for analysis and model creation.

[0489] "Methods for training generative AI models" refer to the step of building a model capable of supply and demand forecasting using AI algorithms based on historical data.

[0490] "Methods for evaluating predictive models" refer to the process of verifying the accuracy and usefulness of the generated AI model and improving or adjusting the model.

[0491] "Means for processing real-time data and updating supply and demand forecasts" refers to a function that immediately analyzes newly obtained data to reflect the current supply and demand situation and update the forecast.

[0492] "Means for optimizing inventory management based on updated supply and demand forecasts" refers to a mechanism that adjusts inventory purchases and placements based on forecast data, thereby ensuring the efficient use of resources.

[0493] "A means of providing real-time forecast information and notifying users of replenishment timing" refers to a function that provides information to quickly inform users of the period when inventory shortages are predicted.

[0494] To implement this invention, it is necessary to build a system in which multiple components work seamlessly together. First, the server automatically collects historical supply and demand data from databases and external information sources. This collected data is then formatted into a format suitable for analysis. This process includes using Python to quantify the data and convert it into a unified format.

[0495] Next, the server uses the formatted data to train a generative AI model. During this process, machine learning libraries such as TensorFlow are used to build the model based on past supply and demand patterns. This enables automated forecasting of future supply and demand. The generated model is then evaluated to check its accuracy and effectiveness, and adjusted as needed.

[0496] Furthermore, the terminals collect new supply and demand data in real time, and the servers process this data immediately to update the supply and demand forecast. This real-time processing enables companies to make immediate decisions. Firebase Cloud Messaging is used to notify users of when to replenish inventory based on the supply and demand forecast. For example, a logistics center manager can receive supply and demand forecasts for new products using their smartphone. When the manager opens the app, a notification appears on the screen stating, "We are displaying the supply and demand forecast for new products. Please replenish inventory based on this information."

[0497] As an example of a prompt message for the generated AI model, by giving instructions to the server such as, "Generate a Python script that predicts next month's demand based on past inventory data and market trends," it is possible to build a model and obtain highly accurate forecast data. In this way, this system can optimize supply and demand forecasting and inventory management in real time, thereby improving the efficiency of the entire supply chain.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The server collects historical supply and demand data from databases and external sources. Using this collected data as input, it performs data formatting using Python to convert the data into numerical values ​​and then into a unified format. This allows for obtaining formatted data suitable for analysis.

[0501] Step 2:

[0502] The server starts training the generative AI model using the formatted data. In this step, the formatted data is used as input, and TensorFlow is used to model past supply and demand patterns using a deep learning algorithm. As output, an AI model for supply and demand forecasting is generated.

[0503] Step 3:

[0504] The server evaluates the generated AI model. In this step, data calculations are performed using a known dataset as input to verify the model's accuracy and usefulness. Based on the evaluation results, the model's parameters are adjusted as needed to improve the model's accuracy.

[0505] Step 4:

[0506] The terminal receives new supply and demand data from the user. Using this new data as input, the server processes the data in real time and updates the current supply and demand forecast. This allows the updated supply and demand forecast data to be output.

[0507] Step 5:

[0508] The server optimizes inventory management based on updated supply and demand forecasts. In this step, it takes supply and demand forecast data as input, automatically calculates the timing and quantity of inventory replenishment, and outputs optimal inventory management information.

[0509] Step 6:

[0510] Users receive supply and demand forecast information from the server via their terminals. Using this information as input, they can receive real-time notifications for inventory replenishment based on the supply and demand forecast, enabling rapid management of the logistics center. As output, specific replenishment instructions are displayed on the terminals.

[0511] 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.

[0512] This invention aims to improve the accuracy of demand management and further streamline the entire supply chain by combining an emotion engine with a supply and demand forecasting system. The program processing of this system is described below in natural language.

[0513] The server first collects and formats supply and demand data from both inside and outside the company. Data formatting includes noise removal and standardization of format, and the data is then used to train a generative AI model.

[0514] Next, the server evaluates the trained model and implements a process to improve its accuracy. This process utilizes an emotion engine, incorporating user sentiment data. For example, the emotion engine analyzes user reactions to the market launch of a new product in real time and incorporates the results as input data for the AI ​​model.

[0515] Furthermore, the device receives input data and feedback from actual users and processes it in real time. During this process, the emotion engine analyzes the received emotion data and uses it to adjust the AI ​​model and update supply and demand forecasts.

[0516] As a concrete example, consider a scenario where a user develops a new promotional strategy. Customer feedback on the effectiveness of the promotion is analyzed by an emotion engine, and the server re-evaluates supply and demand forecasts based on the analysis results, predicting the likelihood of the promotion's success and inventory demand.

[0517] Finally, based on the generated supply and demand forecasts and analysis, the server suggests recommended actions to the user. This enables smoother coordination across the entire supply chain.

[0518] This invention aims to significantly improve the operational efficiency of companies by enabling advanced supply and demand forecasting and supply chain management that incorporates user sentiment data.

[0519] The following describes the processing flow.

[0520] Step 1:

[0521] The server collects historical and current supply and demand data from the company's internal databases and external APIs. This data includes sales history, inventory information, and market trends.

[0522] Step 2:

[0523] The server cleanses, removes noise, and formats the collected data. This includes the process of eliminating unnecessary data and converting the data to a standard format.

[0524] Step 3:

[0525] The server trains a generative AI model based on the formatted data. In this step, machine learning algorithms are used to create a model that learns past patterns and predicts future demand.

[0526] Step 4:

[0527] The server evaluates the model's accuracy and verifies prediction accuracy using test data. If necessary, the model parameters are adjusted to improve prediction accuracy.

[0528] Step 5:

[0529] The device receives real-time data such as quantitative feedback from users and market trends. This data is also used for analysis by the emotion engine.

[0530] Step 6:

[0531] The server uses an emotion engine to analyze user emotion data. This analysis allows the emotional aspects of the feedback to be reflected in the model's adjustments. For example, positive customer responses may be considered as facilitators.

[0532] Step 7:

[0533] The server updates the model based on new information, including sentiment data, and refines the supply and demand forecast. This ensures that the forecast is always up-to-date.

[0534] Step 8:

[0535] The server optimizes inventory management plans based on the supply and demand forecasts it generates. These plans are used to manage inventory replenishment and logistics adjustments.

[0536] Step 9:

[0537] The server periodically generates supply and demand forecasts and analysis information as reports and provides them to users. These reports also include recommended actions to support user decision-making.

[0538] (Example 2)

[0539] 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."

[0540] Improving the accuracy of supply and demand forecasts and streamlining supply chains are crucial challenges in modern business operations. However, traditional methods have limitations in forecast accuracy and supply chain flexibility because it is difficult to analyze consumer sentiment and opinions in real time and incorporate them into demand forecasts. This can lead to problems such as excess inventory and stockouts, potentially resulting in economic losses.

[0541] 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.

[0542] In this invention, the server includes means for acquiring and preprocessing data, means for training a learning model using the preprocessed data, means for evaluating the performance of the trained model and improving its accuracy, means for processing time-series data and revising supply and demand forecasts, means for analyzing user sentiment information and integrating the results into a generating AI model, and means for adjusting inventory levels based on the revised forecasts. This enables highly accurate supply and demand forecasts that reflect consumer sentiment and efficient supply chain management based on them.

[0543] "Acquiring and pre-processing data" means gathering various information from both inside and outside the company, and processing it through noise reduction and format standardization to make it suitable for model training.

[0544] "Training a learning model" is the process of optimizing algorithms that use AI technology to make predictions and classifications using pre-processed data.

[0545] "Evaluating the performance of a model and improving its accuracy" means testing a trained model with real data, measuring its predictive ability, and making adjustments to further improve it.

[0546] "Processing time-series data and revising forecasts" is the process of updating previously generated supply and demand forecasts using newly obtained data to more accurately reflect current trends.

[0547] "Analyzing user emotional information and integrating the results into a generative AI model" means analyzing emotions from user feedback and reactions, incorporating that information into a predictive model, and making predictions that take emotional factors into account.

[0548] "Adjusting inventory levels" means determining the optimal inventory level based on supply and demand forecasts and managing inventory to prevent excess stock and stockouts.

[0549] This invention combines an emotion engine with a supply and demand forecasting system, with the aim of improving the accuracy of supply and demand forecasts and increasing the efficiency of the supply chain.

[0550] First, the server collects and preprocesses the data. Specifically, it retrieves information from databases both inside and outside the company via the network, removes noise, and uses data processing software to standardize the data format. As an example, Python and the Pandas library are used for data processing.

[0551] Next, the server uses the preprocessed data to train a generative AI model. Here, TensorFlow is used as the AI ​​framework to build a neural network and optimize the algorithm for supply and demand forecasting from the data.

[0552] Furthermore, the server utilizes an emotion engine to acquire and analyze user emotional information in real time. This involves using emotion analysis software to convert user feedback and reactions into emotional data. For example, tools like Affectiva are used for emotion analysis.

[0553] As real-time data processing takes place and emotional data is integrated into the generating AI model, the server revises demand forecasts. This enables efficient adjustments to prevent inventory surpluses and shortages.

[0554] Furthermore, the terminal receives the latest input and feedback from users and sends it to the server. This ensures that supply and demand forecasts are more accurate to the current situation, supporting corporate decision-making.

[0555] For example, when implementing a new promotion, a user can input a prompt into the AI ​​model such as, "Please generate a supply and demand forecast for the next quarter and output the results reflecting consumer sentiment data." This system can then perform the supply and demand forecast according to the input instructions and output relevant reports and recommended actions.

[0556] This invention enables users to achieve highly accurate supply and demand forecasts that take consumer sentiment into account, and optimizes the supply chain management of companies.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The server first collects data. It retrieves supply and demand-related data from internal and external databases and online resources. The input data includes sales history, inventory information, and external market trends. Because this data initially contains various formats and noise, it is collected using database queries and APIs. The output is a raw dataset.

[0560] Step 2:

[0561] The server preprocesses the collected data. A raw dataset is provided as input. This step involves noise reduction, missing data imputation, and format conversion. The Python Pandas library is used to perform data cleaning, outputting formatted data that allows the trained model to function correctly.

[0562] Step 3:

[0563] The server trains a generative AI model using formatted data. A pre-processed dataset is provided as input. TensorFlow is used to build a neural network and train the model. The output is a trained model with improved prediction accuracy.

[0564] Step 4:

[0565] The server evaluates the performance of the trained model and implements measures to improve its accuracy. It uses the test dataset as input. Evaluation metrics such as accuracy and the F1 score are calculated. This optimizes the model's output, resulting in a more accurate model for new data.

[0566] Step 5:

[0567] The server uses an emotion engine to analyze user emotional information. Inputs include user feedback and reviews. Sentiment analysis software is used to analyze the data and quantify the user's emotions. The output is the analyzed emotional data.

[0568] Step 6:

[0569] The server integrates sentiment data into a generating AI model to revise supply and demand forecasts. Inputs include model outputs and sentiment data. Historical sales data and sentiment data are combined to adjust the forecasts. This results in highly accurate supply and demand forecasts that take sentiment into account.

[0570] Step 7:

[0571] The terminal receives new input and feedback from the user and immediately sends it to the server. Input includes new prompts and market fluctuation information. Processing the data in real time updates supply and demand forecasts. The output is the updated supply and demand forecast information.

[0572] Step 8:

[0573] The server optimizes inventory management based on supply and demand forecasts. The input is updated supply and demand forecast data. This step adjusts inventory levels to prevent excess inventory and stockouts. The output is an optimized inventory management plan.

[0574] (Application Example 2)

[0575] 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."

[0576] In increasingly complex supply networks, there is a growing need for improved accuracy in supply and demand forecasting and optimized inventory control. Traditional supply and demand forecasting is often based on historical numerical data, making it difficult to respond flexibly to customer sentiment. Furthermore, it may not be able to respond quickly to sudden demand fluctuations or market changes based on customer sentiment, potentially leading to inventory shortages or surpluses. This reduces the efficiency of the entire supply network, and as a result, there is a need to solve the problems that undermine business reliability and customer satisfaction.

[0577] 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.

[0578] In this invention, the server includes a device for collecting and formatting data, a device for training a generative AI model using the formatted data, a device for processing real-time data and updating supply and demand forecasts, and a device for analyzing sentiment data and reflecting it in the supply and demand forecasts. This enables highly accurate supply and demand forecasting and optimization of inventory control using sentiment data.

[0579] A "data collection and formatting device" is a device that takes in data from both inside and outside a company, removes noise, standardizes the format, and converts it into a form suitable for training AI models.

[0580] A "device for training generative AI models" is a device that uses formatted data to train AI models and build the knowledge necessary for supply and demand forecasting.

[0581] A "device for evaluating generated predictive models and improving their prediction accuracy" is a device that evaluates trained AI models and makes adjustments to improve their accuracy.

[0582] A "device that processes real-time data and updates supply and demand forecasts" is a device that uses the latest data acquired from the market and users to constantly update supply and demand forecasts to the most up-to-date state.

[0583] A "device that analyzes emotional data and reflects it in supply and demand forecasts" is a device that analyzes data based on user and market sentiment and incorporates the results into supply and demand forecasts, thereby enabling more accurate predictions.

[0584] A "device for optimizing inventory control" is a device that, based on updated supply and demand forecasts, plans to maintain appropriate inventory levels and prevent surpluses and shortages.

[0585] A "device for optimizing the supply network" is a device that improves the efficiency of the entire supply chain by optimizing supply and demand forecasting and inventory control.

[0586] A "notification and warning generation device" is a device that detects important changes or abnormal situations based on supply and demand forecasts and generates information to immediately inform relevant parties.

[0587] The system implementing this invention consists of multiple devices. The server first collects and formats data from both inside and outside the company. Here, it removes noise from data in various formats obtained through REST APIs using Pandas or similar tools, and standardizes the format. This formatted data is then used as a dataset for training a generative AI model.

[0588] The server then trains a generative AI model using TensorFlow. This model possesses fundamental knowledge for supply and demand forecasting, and the server performs evaluation and adjustments to improve prediction accuracy. Furthermore, Azure Cognitive Services is used to analyze sentiment data, feeding this sentiment data from users and the market back into the AI ​​model. This process is continuous, leading to more accurate supply and demand forecasts.

[0589] The terminals are responsible for processing real-time data and updating supply and demand forecasts. They receive input data and feedback from users and send it to the server. Based on the data obtained, the server updates the supply and demand forecast and optimizes inventory control. This enables proper inventory management at logistics centers and improves the efficiency of the entire supply network.

[0590] A concrete example is a scenario where a logistics center manager uses an application to respond to a sudden surge in demand. The application uses real-time updated supply and demand forecast data to suggest the optimal amount of inventory to replenish, preventing disruption to the supply network. Since the results of sentiment data analysis are also utilized in this process, the factors influencing demand fluctuations can be captured more accurately.

[0591] An example of a prompt for the generated AI model is, "Based on the latest supply and demand data, forecast demand for next week and propose an inventory replenishment plan that incorporates sentiment data." This enables highly accurate supply and demand forecasting and efficient inventory management using artificial intelligence.

[0592] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0593] Step 1:

[0594] The server collects data from both within and outside the company. Input data is obtained from various APIs and databases. This data includes inventory information, transaction history, and customer feedback. The output is raw data that requires formatting. Data analysis tools such as Pandas are used to remove noise and standardize the format.

[0595] Step 2:

[0596] The server formats the acquired raw data. The raw data obtained in step 1 is used as input. Data processing is performed to remove noise and standardize the format, resulting in a clean and consistent dataset as output. This dataset is used to train the generative AI model.

[0597] Step 3:

[0598] The server trains a generative AI model using formatted data. A formatted dataset is provided as input, and the model is trained using a framework such as TensorFlow. The output is an AI model for supply and demand forecasting. This model makes predictions based on user input and external data.

[0599] Step 4:

[0600] The server evaluates the generated model and improves its prediction accuracy. The evaluation uses a comparison between real-time data and past prediction results. New data and prediction results are taken as input, and the model is adjusted through evaluation, resulting in an output AI model with improved prediction accuracy.

[0601] Step 5:

[0602] The terminal processes real-time data and updates supply and demand forecasts. Real-time data from user actions is provided as input, including inventory movements and new order information. The server updates the model, instantly updating the supply and demand forecast and providing the latest forecast data as output.

[0603] Step 6:

[0604] The server analyzes sentiment data and incorporates it into supply and demand forecasts. Azure Cognitive Services is used to analyze user sentiment data. Customer feedback data is provided as input. The analysis results are used as model input, resulting in more accurate supply and demand forecasts.

[0605] Step 7:

[0606] The server optimizes inventory control based on updated supply and demand forecasts and notifies the user. The user is then presented with a proposed inventory replenishment plan. The latest supply and demand forecasts and inventory data are used as input. The output provides specific inventory management strategies to improve the efficiency of the supply network.

[0607] 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.

[0608] 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.

[0609] 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.

[0610] [Fourth Embodiment]

[0611] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0612] 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.

[0613] 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).

[0614] 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.

[0615] 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.

[0616] 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).

[0617] 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.

[0618] 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.

[0619] 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.

[0620] 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.

[0621] 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.

[0622] 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.

[0623] 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".

[0624] In this embodiment of the invention, a system is constructed in which data collection, AI model training, model evaluation, real-time data processing, and inventory management optimization are seamlessly integrated. The system's program processing is described below in natural language.

[0625] First, the server retrieves historical demand data from multiple sources. This data collection is automated, drawing from internal company systems and external supply chain information. Data formatting includes digitization and conversion to standard formats.

[0626] Next, the server trains an AI model using the formatted data. This process uses machine learning algorithms, including deep learning, to learn past supply and demand patterns and predict future demand. The generated model is then evaluated on a known dataset to verify its accuracy.

[0627] Furthermore, real-time data updates are crucial. Terminals allow users to input new data, and the system processes this instantly, providing the latest supply and demand forecasts. This real-time processing enables businesses to take immediate action.

[0628] Regarding inventory management optimization, the system automatically controls inventory replenishment and adjustment based on predictive data generated by the server. This allows users to avoid inventory surpluses and shortages, enabling efficient supply chain management.

[0629] As a concrete example, when a user checks the demand forecast for a new product, the server integrates data from similar past products with current market trends to provide a demand forecast. Based on this forecast, the user can proactively adjust inventory.

[0630] In this way, this system supports the efficient operation of businesses by automating supply and demand forecasting and inventory management using AI.

[0631] The following describes the processing flow.

[0632] Step 1:

[0633] The server automatically collects historical supply and demand data from both within and outside the company. The data is obtained from various system databases and external APIs.

[0634] Step 2:

[0635] The server cleans and formats the collected data. This process removes noise and converts the data into a standard format. Missing values ​​and anomalies are also handled at this stage.

[0636] Step 3:

[0637] The server trains an AI model using the formatted data. The goal here is to learn patterns within the dataset using machine learning algorithms and predict future demand.

[0638] Step 4:

[0639] The server evaluates the trained model. Test data is used for evaluation to check the model's prediction accuracy. Model parameters are adjusted as needed to improve accuracy.

[0640] Step 5:

[0641] The terminal receives new data from the user in real time. The data entered by the user is processed immediately, and the supply and demand forecast is updated.

[0642] Step 6:

[0643] The server optimizes inventory management using the latest forecast data. Specifically, it replenishes and adjusts inventory according to future demand. Users are provided with new supply and demand forecast information.

[0644] Step 7:

[0645] The server periodically generates and provides users with reports based on supply and demand forecasts. These reports include an overview of the demand forecast and recommended adjustments to inventory levels. Users utilize this information to develop business strategies.

[0646] (Example 1)

[0647] 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".

[0648] Efficient data management and optimized supply and demand forecasting are critical challenges in current business operations. In particular, unifying data from diverse sources and building accurate forecasting models is not easy. Furthermore, while real-time data updates are required to rapidly adjust supply and demand, traditional methods struggle to achieve this efficiently.

[0649] 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.

[0650] In this invention, the server includes means for collecting information and converting it into a standard format, means for performing machine learning using the converted information, and means for evaluating the generated prediction method and improving its accuracy. This makes it possible to integrate diverse information and perform rapid and accurate supply and demand forecasting.

[0651] "Means of information gathering" refers to the process of automatically acquiring data from various sources, both internal and external to a company.

[0652] "Methods for converting to a standard format" refers to the process of unifying data in different formats into a consistent format, making it easier to perform subsequent processing and analysis.

[0653] "Methods for performing machine learning" refers to the process of learning patterns based on past data and applying algorithms to gain new insights.

[0654] "Means for evaluating prediction methods" refers to the process of objectively determining the accuracy and reliability of the generated model using specific evaluation metrics.

[0655] "Means of improving accuracy" refers to the process of improving data and algorithms to enhance the performance of predictive models.

[0656] "Means of optimizing the flow of materials" refers to the process of efficiently managing the supply and inventory of goods based on supply and demand forecasts.

[0657] "Means of improving the efficiency of the supply network" refers to the process of optimizing the operation of the entire supply chain and reducing waste of resources.

[0658] "Methods for creating reports" refers to the process of systematically generating documents based on data analysis results, making the situation visually clear.

[0659] "Means of issuing warnings" refers to the process of quickly issuing alerts when a specific threshold is exceeded based on prediction results or real-time data.

[0660] The embodiments for carrying out the present invention will now be described. This system enables efficient supply and demand forecasting and inventory management, and functions in cooperation with a server, terminals, and users.

[0661] First, the server accesses various corporate information sources to collect data. This includes internal ERP systems and external market databases. The server then uses ETL tools to format the collected data into a standard format. This process integrates the data into an analyzable form.

[0662] Next, the server uses machine learning algorithms to train an AI model based on the formatted data. Here, TensorFlow is used as the deep learning framework. The AI ​​model learns past supply and demand patterns and gains the ability to predict future demand.

[0663] Subsequently, the accuracy of the generated model is evaluated using a known dataset. This evaluation process measures the model's predictive accuracy and allows for necessary improvements.

[0664] A terminal is used to update real-time data. Users input new data through the terminal, and this data is sent to the server, allowing the system to immediately revise supply and demand forecasts. For example, sales data can be entered using a tablet or smartphone application, and the forecast can be updated in real time.

[0665] Based on the generated supply and demand forecast data, the server automatically controls inventory replenishment and adjustment. This process optimizes the flow of materials, enabling companies to achieve efficient inventory management.

[0666] As a concrete example, when a user plans a sales campaign for a new product, they use a terminal to input campaign information into the system. By sending a prompt message to the server such as, "Please update the supply and demand baseline to reflect next month's new product sales campaign," the system provides the latest supply and demand forecast, allowing the user to adjust their inventory strategy.

[0667] Through this configuration, the system provides a technological foundation that supports the automation and efficiency of supply and demand forecasting and inventory management.

[0668] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0669] Step 1:

[0670] The server uses a database management system to automatically collect data from internal and external sources within the company. Specifically, it periodically retrieves information from ERP systems and market databases via APIs. This input data includes production figures, sales figures, and market trends. The server converts this data into a standard format using ETL tools, making it analyzable. The output is a dataset in a unified format.

[0671] Step 2:

[0672] Based on the formatted data, the server trains an AI model using machine learning algorithms. Specifically, it uses TensorFlow to learn demand forecasting patterns from historical data. The input to this process is a unified dataset, and the output is the trained AI model. During training, the system iterates to minimize the loss function and improve accuracy.

[0673] Step 3:

[0674] The server evaluates the AI ​​model generated using the new dataset. The data calculations performed here involve using existing data as input and comparing the model's predicted values ​​with actual values. Specifically, it calculates metrics such as accuracy, recall, and F1 score to evaluate model performance. The output consists of the model evaluation results and areas for improvement.

[0675] Step 4:

[0676] The terminal accepts real-time data input from the user. Specifically, users input inventory and sales information via a dedicated app on their tablet or smartphone. The server immediately processes the input data and updates the supply and demand forecast. The output is the latest supply and demand forecast.

[0677] Step 5:

[0678] Based on the generated supply and demand data, the server optimizes the flow of materials and adjusts inventory. Specifically, it automatically issues inventory replenishment orders in accordance with predicted demand. The input is updated supply and demand forecast data, and the output is replenishment plans and order orders.

[0679] Step 6:

[0680] The system receives prompt messages to obtain the information users need to adjust inventory and sales strategies. Specifically, prompt messages such as "Please update the supply and demand baseline to reflect next month's new product sales campaign" are used. The server processes these prompts and provides the user with the updated information. The input is the prompt message, and the output is the adjusted supply and demand forecast information.

[0681] (Application Example 1)

[0682] 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".

[0683] Modern logistics centers require efficient inventory management and precise supply and demand forecasting. However, traditional methods are insufficient for real-time updates of supply and demand forecasts, making it difficult to replenish inventory at the appropriate time. As a result, inventory surpluses and shortages often occur, posing a challenge to optimizing the supply chain.

[0684] 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.

[0685] In this invention, the server includes means for collecting and formatting data, means for training a generation AI model using the formatted data, and means for presenting predictive information in real time and notifying replenishment timing. This enables real-time optimization of inventory management in logistics centers and improves the efficiency of the supply chain.

[0686] "Means of collecting and formatting data" refers to the function of converting raw data imported from databases and external information sources into a format suitable for analysis and model creation.

[0687] "Methods for training generative AI models" refer to the step of building a model capable of supply and demand forecasting using AI algorithms based on historical data.

[0688] "Methods for evaluating predictive models" refer to the process of verifying the accuracy and usefulness of the generated AI model and improving or adjusting the model.

[0689] "Means for processing real-time data and updating supply and demand forecasts" refers to a function that immediately analyzes newly obtained data to reflect the current supply and demand situation and update the forecast.

[0690] "Means for optimizing inventory management based on updated supply and demand forecasts" refers to a mechanism that adjusts inventory purchases and placements based on forecast data, thereby ensuring the efficient use of resources.

[0691] "A means of providing real-time forecast information and notifying users of replenishment timing" refers to a function that provides information to quickly inform users of the period when inventory shortages are predicted.

[0692] To implement this invention, it is necessary to build a system in which multiple components work seamlessly together. First, the server automatically collects historical supply and demand data from databases and external information sources. This collected data is then formatted into a format suitable for analysis. This process includes using Python to quantify the data and convert it into a unified format.

[0693] Next, the server uses the formatted data to train a generative AI model. During this process, machine learning libraries such as TensorFlow are used to build the model based on past supply and demand patterns. This enables automated forecasting of future supply and demand. The generated model is then evaluated to check its accuracy and effectiveness, and adjusted as needed.

[0694] Furthermore, the terminals collect new supply and demand data in real time, and the servers process this data immediately to update the supply and demand forecast. This real-time processing enables companies to make immediate decisions. Firebase Cloud Messaging is used to notify users of when to replenish inventory based on the supply and demand forecast. For example, a logistics center manager can receive supply and demand forecasts for new products using their smartphone. When the manager opens the app, a notification appears on the screen stating, "We are displaying the supply and demand forecast for new products. Please replenish inventory based on this information."

[0695] As an example of a prompt message for the generated AI model, by giving instructions to the server such as, "Generate a Python script that predicts next month's demand based on past inventory data and market trends," it is possible to build a model and obtain highly accurate forecast data. In this way, this system can optimize supply and demand forecasting and inventory management in real time, thereby improving the efficiency of the entire supply chain.

[0696] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0697] Step 1:

[0698] The server collects historical supply and demand data from databases and external sources. Using this collected data as input, it performs data formatting using Python to convert the data into numerical values ​​and then into a unified format. This allows for obtaining formatted data suitable for analysis.

[0699] Step 2:

[0700] The server starts training the generative AI model using the formatted data. In this step, the formatted data is used as input, and TensorFlow is used to model past supply and demand patterns using a deep learning algorithm. As output, an AI model for supply and demand forecasting is generated.

[0701] Step 3:

[0702] The server evaluates the generated AI model. In this step, data calculations are performed using a known dataset as input to verify the model's accuracy and usefulness. Based on the evaluation results, the model's parameters are adjusted as needed to improve the model's accuracy.

[0703] Step 4:

[0704] The terminal receives new supply and demand data from the user. Using this new data as input, the server processes the data in real time and updates the current supply and demand forecast. This allows the updated supply and demand forecast data to be output.

[0705] Step 5:

[0706] The server optimizes inventory management based on updated supply and demand forecasts. In this step, it takes supply and demand forecast data as input, automatically calculates the timing and quantity of inventory replenishment, and outputs optimal inventory management information.

[0707] Step 6:

[0708] Users receive supply and demand forecast information from the server via their terminals. Using this information as input, they can receive real-time notifications for inventory replenishment based on the supply and demand forecast, enabling rapid management of the logistics center. As output, specific replenishment instructions are displayed on the terminals.

[0709] 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.

[0710] This invention aims to improve the accuracy of demand management and further streamline the entire supply chain by combining an emotion engine with a supply and demand forecasting system. The program processing of this system is described below in natural language.

[0711] The server first collects and formats supply and demand data from both inside and outside the company. Data formatting includes noise removal and standardization of format, and the data is then used to train a generative AI model.

[0712] Next, the server evaluates the trained model and implements a process to improve its accuracy. This process utilizes an emotion engine, incorporating user sentiment data. For example, the emotion engine analyzes user reactions to the market launch of a new product in real time and incorporates the results as input data for the AI ​​model.

[0713] Furthermore, the device receives input data and feedback from actual users and processes it in real time. During this process, the emotion engine analyzes the received emotion data and uses it to adjust the AI ​​model and update supply and demand forecasts.

[0714] As a concrete example, consider a scenario where a user develops a new promotional strategy. Customer feedback on the effectiveness of the promotion is analyzed by an emotion engine, and the server re-evaluates supply and demand forecasts based on the analysis results, predicting the likelihood of the promotion's success and inventory demand.

[0715] Finally, based on the generated supply and demand forecasts and analysis, the server suggests recommended actions to the user. This enables smoother coordination across the entire supply chain.

[0716] This invention aims to significantly improve the operational efficiency of companies by enabling advanced supply and demand forecasting and supply chain management that incorporates user sentiment data.

[0717] The following describes the processing flow.

[0718] Step 1:

[0719] The server collects historical and current supply and demand data from the company's internal databases and external APIs. This data includes sales history, inventory information, and market trends.

[0720] Step 2:

[0721] The server cleanses, removes noise, and formats the collected data. This includes the process of eliminating unnecessary data and converting the data to a standard format.

[0722] Step 3:

[0723] The server trains a generative AI model based on the formatted data. In this step, machine learning algorithms are used to create a model that learns past patterns and predicts future demand.

[0724] Step 4:

[0725] The server evaluates the model's accuracy and verifies prediction accuracy using test data. If necessary, the model parameters are adjusted to improve prediction accuracy.

[0726] Step 5:

[0727] The device receives real-time data such as quantitative feedback from users and market trends. This data is also used for analysis by the emotion engine.

[0728] Step 6:

[0729] The server uses an emotion engine to analyze user emotion data. This analysis allows the emotional aspects of the feedback to be reflected in the model's adjustments. For example, positive customer responses may be considered as facilitators.

[0730] Step 7:

[0731] The server updates the model based on new information, including sentiment data, and refines the supply and demand forecast. This ensures that the forecast is always up-to-date.

[0732] Step 8:

[0733] The server optimizes inventory management plans based on the supply and demand forecasts it generates. These plans are used to manage inventory replenishment and logistics adjustments.

[0734] Step 9:

[0735] The server periodically generates supply and demand forecasts and analysis information as reports and provides them to users. These reports also include recommended actions to support user decision-making.

[0736] (Example 2)

[0737] 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".

[0738] Improving the accuracy of supply and demand forecasts and streamlining supply chains are crucial challenges in modern business operations. However, traditional methods have limitations in forecast accuracy and supply chain flexibility because it is difficult to analyze consumer sentiment and opinions in real time and incorporate them into demand forecasts. This can lead to problems such as excess inventory and stockouts, potentially resulting in economic losses.

[0739] 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.

[0740] In this invention, the server includes means for acquiring and preprocessing data, means for training a learning model using the preprocessed data, means for evaluating the performance of the trained model and improving its accuracy, means for processing time-series data and revising supply and demand forecasts, means for analyzing user sentiment information and integrating the results into a generating AI model, and means for adjusting inventory levels based on the revised forecasts. This enables highly accurate supply and demand forecasts that reflect consumer sentiment and efficient supply chain management based on them.

[0741] "Acquiring and pre-processing data" means gathering various information from both inside and outside the company, and processing it through noise reduction and format standardization to make it suitable for model training.

[0742] "Training a learning model" is the process of optimizing algorithms that use AI technology to make predictions and classifications using pre-processed data.

[0743] "Evaluating the performance of a model and improving its accuracy" means testing a trained model with real data, measuring its predictive ability, and making adjustments to further improve it.

[0744] "Processing time-series data and revising forecasts" is the process of updating previously generated supply and demand forecasts using newly obtained data to more accurately reflect current trends.

[0745] "Analyzing user emotional information and integrating the results into a generative AI model" means analyzing emotions from user feedback and reactions, incorporating that information into a predictive model, and making predictions that take emotional factors into account.

[0746] "Adjusting inventory levels" means determining the optimal inventory level based on supply and demand forecasts and managing inventory to prevent excess stock and stockouts.

[0747] This invention combines an emotion engine with a supply and demand forecasting system, with the aim of improving the accuracy of supply and demand forecasts and increasing the efficiency of the supply chain.

[0748] First, the server collects and preprocesses the data. Specifically, it retrieves information from databases both inside and outside the company via the network, removes noise, and uses data processing software to standardize the data format. As an example, Python and the Pandas library are used for data processing.

[0749] Next, the server uses the preprocessed data to train a generative AI model. Here, TensorFlow is used as the AI ​​framework to build a neural network and optimize the algorithm for supply and demand forecasting from the data.

[0750] Furthermore, the server utilizes an emotion engine to acquire and analyze user emotional information in real time. This involves using emotion analysis software to convert user feedback and reactions into emotional data. For example, tools like Affectiva are used for emotion analysis.

[0751] As real-time data processing takes place and emotional data is integrated into the generating AI model, the server revises demand forecasts. This enables efficient adjustments to prevent inventory surpluses and shortages.

[0752] Furthermore, the terminal receives the latest input and feedback from users and sends it to the server. This ensures that supply and demand forecasts are more accurate to the current situation, supporting corporate decision-making.

[0753] For example, when implementing a new promotion, a user can input a prompt into the AI ​​model such as, "Please generate a supply and demand forecast for the next quarter and output the results reflecting consumer sentiment data." This system can then perform the supply and demand forecast according to the input instructions and output relevant reports and recommended actions.

[0754] This invention enables users to achieve highly accurate supply and demand forecasts that take consumer sentiment into account, and optimizes the supply chain management of companies.

[0755] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0756] Step 1:

[0757] The server first collects data. It retrieves supply and demand-related data from internal and external databases and online resources. The input data includes sales history, inventory information, and external market trends. Because this data initially contains various formats and noise, it is collected using database queries and APIs. The output is a raw dataset.

[0758] Step 2:

[0759] The server preprocesses the collected data. A raw dataset is provided as input. This step involves noise reduction, missing data imputation, and format conversion. The Python Pandas library is used to perform data cleaning, outputting formatted data that allows the trained model to function correctly.

[0760] Step 3:

[0761] The server trains a generative AI model using formatted data. A pre-processed dataset is provided as input. TensorFlow is used to build a neural network and train the model. The output is a trained model with improved prediction accuracy.

[0762] Step 4:

[0763] The server evaluates the performance of the trained model and implements measures to improve its accuracy. It uses the test dataset as input. Evaluation metrics such as accuracy and the F1 score are calculated. This optimizes the model's output, resulting in a more accurate model for new data.

[0764] Step 5:

[0765] The server uses an emotion engine to analyze user emotional information. Inputs include user feedback and reviews. Sentiment analysis software is used to analyze the data and quantify the user's emotions. The output is the analyzed emotional data.

[0766] Step 6:

[0767] The server integrates sentiment data into a generating AI model to revise supply and demand forecasts. Inputs include model outputs and sentiment data. Historical sales data and sentiment data are combined to adjust the forecasts. This results in highly accurate supply and demand forecasts that take sentiment into account.

[0768] Step 7:

[0769] The terminal receives new input and feedback from the user and immediately sends it to the server. Input includes new prompts and market fluctuation information. Processing the data in real time updates supply and demand forecasts. The output is the updated supply and demand forecast information.

[0770] Step 8:

[0771] The server optimizes inventory management based on supply and demand forecasts. The input is updated supply and demand forecast data. This step adjusts inventory levels to prevent excess inventory and stockouts. The output is an optimized inventory management plan.

[0772] (Application Example 2)

[0773] 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".

[0774] In increasingly complex supply networks, there is a growing need for improved accuracy in supply and demand forecasting and optimized inventory control. Traditional supply and demand forecasting is often based on historical numerical data, making it difficult to respond flexibly to customer sentiment. Furthermore, it may not be able to respond quickly to sudden demand fluctuations or market changes based on customer sentiment, potentially leading to inventory shortages or surpluses. This reduces the efficiency of the entire supply network, and as a result, there is a need to solve the problems that undermine business reliability and customer satisfaction.

[0775] 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.

[0776] In this invention, the server includes a device for collecting and formatting data, a device for training a generative AI model using the formatted data, a device for processing real-time data and updating supply and demand forecasts, and a device for analyzing sentiment data and reflecting it in the supply and demand forecasts. This enables highly accurate supply and demand forecasting and optimization of inventory control using sentiment data.

[0777] A "data collection and formatting device" is a device that takes in data from both inside and outside a company, removes noise, standardizes the format, and converts it into a form suitable for training AI models.

[0778] A "device for training generative AI models" is a device that uses formatted data to train AI models and build the knowledge necessary for supply and demand forecasting.

[0779] A "device for evaluating generated predictive models and improving their prediction accuracy" is a device that evaluates trained AI models and makes adjustments to improve their accuracy.

[0780] A "device that processes real-time data and updates supply and demand forecasts" is a device that uses the latest data acquired from the market and users to constantly update supply and demand forecasts to the most up-to-date state.

[0781] A "device that analyzes emotional data and reflects it in supply and demand forecasts" is a device that analyzes data based on user and market sentiment and incorporates the results into supply and demand forecasts, thereby enabling more accurate predictions.

[0782] A "device for optimizing inventory control" is a device that, based on updated supply and demand forecasts, plans to maintain appropriate inventory levels and prevent surpluses and shortages.

[0783] A "device for optimizing the supply network" is a device that improves the efficiency of the entire supply chain by optimizing supply and demand forecasting and inventory control.

[0784] A "notification and warning generation device" is a device that detects important changes or abnormal situations based on supply and demand forecasts and generates information to immediately inform relevant parties.

[0785] The system implementing this invention consists of multiple devices. The server first collects and formats data from both inside and outside the company. Here, it removes noise from data in various formats obtained through REST APIs using Pandas or similar tools, and standardizes the format. This formatted data is then used as a dataset for training a generative AI model.

[0786] The server then trains a generative AI model using TensorFlow. This model possesses fundamental knowledge for supply and demand forecasting, and the server performs evaluation and adjustments to improve prediction accuracy. Furthermore, Azure Cognitive Services is used to analyze sentiment data, feeding this sentiment data from users and the market back into the AI ​​model. This process is continuous, leading to more accurate supply and demand forecasts.

[0787] The terminals are responsible for processing real-time data and updating supply and demand forecasts. They receive input data and feedback from users and send it to the server. Based on the data obtained, the server updates the supply and demand forecast and optimizes inventory control. This enables proper inventory management at logistics centers and improves the efficiency of the entire supply network.

[0788] A concrete example is a scenario where a logistics center manager uses an application to respond to a sudden surge in demand. The application uses real-time updated supply and demand forecast data to suggest the optimal amount of inventory to replenish, preventing disruption to the supply network. Since the results of sentiment data analysis are also utilized in this process, the factors influencing demand fluctuations can be captured more accurately.

[0789] An example of a prompt for the generated AI model is, "Based on the latest supply and demand data, forecast demand for next week and propose an inventory replenishment plan that incorporates sentiment data." This enables highly accurate supply and demand forecasting and efficient inventory management using artificial intelligence.

[0790] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0791] Step 1:

[0792] The server collects data from both within and outside the company. Input data is obtained from various APIs and databases. This data includes inventory information, transaction history, and customer feedback. The output is raw data that requires formatting. Data analysis tools such as Pandas are used to remove noise and standardize the format.

[0793] Step 2:

[0794] The server formats the acquired raw data. The raw data obtained in step 1 is used as input. Data processing is performed to remove noise and standardize the format, resulting in a clean and consistent dataset as output. This dataset is used to train the generative AI model.

[0795] Step 3:

[0796] The server trains a generative AI model using formatted data. A formatted dataset is provided as input, and the model is trained using a framework such as TensorFlow. The output is an AI model for supply and demand forecasting. This model makes predictions based on user input and external data.

[0797] Step 4:

[0798] The server evaluates the generated model and improves its prediction accuracy. The evaluation uses a comparison between real-time data and past prediction results. New data and prediction results are taken as input, and the model is adjusted through evaluation, resulting in an output AI model with improved prediction accuracy.

[0799] Step 5:

[0800] The terminal processes real-time data and updates supply and demand forecasts. Real-time data from user actions is provided as input, including inventory movements and new order information. The server updates the model, instantly updating the supply and demand forecast and providing the latest forecast data as output.

[0801] Step 6:

[0802] The server analyzes sentiment data and incorporates it into supply and demand forecasts. Azure Cognitive Services is used to analyze user sentiment data. Customer feedback data is provided as input. The analysis results are used as model input, resulting in more accurate supply and demand forecasts.

[0803] Step 7:

[0804] The server optimizes inventory control based on updated supply and demand forecasts and notifies the user. The user is then presented with a proposed inventory replenishment plan. The latest supply and demand forecasts and inventory data are used as input. The output provides specific inventory management strategies to improve the efficiency of the supply network.

[0805] 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.

[0806] 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.

[0807] 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.

[0808] 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.

[0809] 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.

[0810] 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.

[0811] 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.

[0812] 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.

[0813] 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."

[0814] 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.

[0815] 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.

[0816] 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.

[0817] 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.

[0818] 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.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] 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.

[0823] 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.

[0824] 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.

[0825] 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.

[0826] The following is further disclosed regarding the embodiments described above.

[0827] (Claim 1)

[0828] Means for collecting and formatting data,

[0829] A method for training a generative AI model using formatted data,

[0830] A means for evaluating the generated prediction model and improving its prediction accuracy,

[0831] A means of processing real-time data and updating supply and demand forecasts,

[0832] A means of optimizing inventory management based on updated supply and demand forecasts,

[0833] A system that includes this.

[0834] (Claim 2)

[0835] The system according to claim 1, comprising means for improving the efficiency of the supply chain using a generative AI model.

[0836] (Claim 3)

[0837] The system according to claim 1, comprising means for periodically generating reports and issuing alerts based on supply and demand forecast results.

[0838] "Example 1"

[0839] (Claim 1)

[0840] A means of collecting information and converting it into a standard format,

[0841] A means of performing machine learning using the transformed information,

[0842] A means to evaluate the generated prediction method and improve its accuracy,

[0843] A means of processing the latest information and revising supply and demand forecasts,

[0844] Means for optimizing the flow of materials based on revised supply and demand forecasts,

[0845] A system that includes this.

[0846] (Claim 2)

[0847] The system according to claim 1, comprising means for improving the efficiency of the supply network using machine learning.

[0848] (Claim 3)

[0849] The system according to claim 1, comprising means for periodically generating reports and issuing alarms based on supply and demand forecast results.

[0850] "Application Example 1"

[0851] (Claim 1)

[0852] Means for collecting and formatting data,

[0853] A method for training a generative AI model using formatted data,

[0854] A means for evaluating the generated prediction model and improving its prediction accuracy,

[0855] A means of processing real-time data and updating supply and demand forecasts,

[0856] A means of optimizing inventory management based on updated supply and demand forecasts,

[0857] A means of providing real-time forecast information and notifying replenishment timing,

[0858] A system that includes this.

[0859] (Claim 2)

[0860] The system according to claim 1, comprising means for improving the efficiency of the supply chain using a generative AI model.

[0861] (Claim 3)

[0862] The system according to claim 1, comprising means for periodically generating reports and issuing alerts based on supply and demand forecast results, and means for managing inventory information using a recording device.

[0863] "Example 2 of combining an emotion engine"

[0864] (Claim 1)

[0865] A means for acquiring data and performing preprocessing,

[0866] A means of training a learning model using preprocessed data,

[0867] A means of evaluating the performance of a trained model and improving its accuracy,

[0868] A means of processing time series data and revising demand and supply forecasts,

[0869] A means of analyzing user sentiment information and integrating the results into a generating AI model,

[0870] Means for adjusting inventory levels based on revised forecasts,

[0871] A system that includes this.

[0872] (Claim 2)

[0873] The system according to claim 1, which improves the efficiency of a supply chain using a generative AI model.

[0874] (Claim 3)

[0875] The system according to claim 1, which generates a report and provides notification based on the results of supply and demand forecasts.

[0876] "Application example 2 when combining with an emotional engine"

[0877] (Claim 1)

[0878] A device for collecting and formatting data,

[0879] A device for training a generative AI model using formatted data,

[0880] A device for evaluating the generated prediction model and improving its prediction accuracy,

[0881] A device that processes real-time data and updates supply and demand forecasts,

[0882] A device that optimizes inventory control based on updated supply and demand forecasts,

[0883] A device that analyzes emotional data and reflects it in supply and demand forecasts,

[0884] A system that includes this.

[0885] (Claim 2)

[0886] The system according to claim 1, comprising a device that improves the efficiency of the supply network using a generative AI model.

[0887] (Claim 3)

[0888] The system according to claim 1, comprising a device that periodically generates notifications and issues warnings based on supply and demand forecast results. [Explanation of symbols]

[0889] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means for collecting and formatting data, A method for training a generative AI model using formatted data, A means for evaluating the generated prediction model and improving its prediction accuracy, A means of processing real-time data and updating supply and demand forecasts, A means of optimizing inventory management based on updated supply and demand forecasts, A means of providing real-time forecast information and notifying replenishment timing, A system that includes this.

2. The system according to claim 1, comprising means for improving the efficiency of the supply chain using a generative AI model.

3. The system according to claim 1, comprising means for periodically generating reports and issuing alerts based on supply and demand forecast results, and means for managing inventory information using a recording device.

Images