System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting sales data; means for forecasting demand based on the sales data; means for collecting and updating current inventory information; means for automatically replenishing inventory based on the collected and forecast data; means for managing proper rotation of inventory and accounting for expiration of goods; and means for monitoring inventory and sales information in real time.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Inventory management is an important task for retail and wholesale companies, but there are risks of excess or shortage of inventory. This can lead to problems such as wasted capital and reduced customer satisfaction. Furthermore, inventory management is often unstable, especially in small and medium-sized enterprises, as it relies on the experience and discretion of the person in charge. A system to solve these issues is needed. [Means for solving the problem]

[0005] The present invention provides an inventory management system that includes a means for collecting sales data, a means for forecasting demand based on the sales data, a means for collecting and updating current inventory information, a means for automatically replenishing inventory based on the collected and forecasted data, a means for managing appropriate inventory rotation and taking product expiration dates into consideration, and a means for monitoring inventory and sales information in real time, thereby achieving improved efficiency and accuracy in inventory management and improved customer satisfaction.

[0006] "Sales data" refers to information about sales of each product in store or online sales activities, including product type, quantity, date and time, sales amount, etc.

[0007] "Demand" refers to the consumer desire to purchase a particular product or service, which determines inventory replenishment and sales planning.

[0008] "Forecasting" refers to estimating future events, in this case primarily sales and inventory needs, based on historical data and current conditions.

[0009] "Current inventory information" refers to information such as the current inventory amount, location, and expiration date of each product in the store or warehouse.

[0010] "Automatically replenish" refers to the system ordering and replenishing inventory based on forecast data and current inventory information without human intervention.

[0011] "Proper inventory rotation" refers to managing products so that they are consumed or sold in the proper order, especially by ensuring that products with shorter expiration dates are used first.

[0012] "Expiration date" refers to the period during which a product can be consumed or used while maintaining its quality, and is an important factor, especially for food and medicine.

[0013] "Real-time monitoring" refers to the system constantly and instantly collecting, displaying, and managing the latest data, which enables rapid response. [Brief explanation of the drawings]

[0014] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0015] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0018] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0019] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0020] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0021] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0025] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0026] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0027] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0028] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0029] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0032] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0033] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0034] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0035] The present invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[0036] ---

[0037] The system has the following components:

[0038] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. Sales data includes product names, quantities sold, sales dates and times, sales prices, etc.

[0039] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[0040] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[0041] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[0042] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[0043] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[0044] ---

[0045] Specific examples

[0046] As a concrete example, the operation of the system in a grocery store will be described.

[0047] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[0048] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[0049] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[0050] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[0051] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[0052] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[0053] This improves the accuracy and efficiency of inventory management, reduces resource waste, and increases customer satisfaction.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[0057] Step 2:

[0058] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[0059] Step 3:

[0060] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[0061] Step 4:

[0062] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[0063] Step 5:

[0064] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[0065] Step 6:

[0066] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[0067] Step 7:

[0068] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[0069] Step 8:

[0070] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[0071] Step 9:

[0072] Users can view the inventory rotation plan through the terminal and manually adjust it if necessary, for example by changing the order in which new arrivals are placed after older stock.

[0073] Step 10:

[0074] The server continuously collects sales and inventory data and updates the system in real time, allowing you to constantly monitor the latest inventory status and sales trends.

[0075] Step 11:

[0076] The server periodically retrains the demand forecasting model based on new data collected, thereby maintaining and further improving the accuracy of the forecasts.

[0077] Step 12:

[0078] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[0079] Through the above processing steps, the system of the present invention can improve the efficiency and accuracy of inventory management, minimize a company's inventory risk, and increase customer satisfaction.

[0080] Example 1

[0081] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0082] With conventional inventory management systems, sales data collection, demand forecasting, and automatic inventory replenishment are often carried out separately, making integrated management difficult. Furthermore, there are issues with overstocking and shortages due to a lack of forecast accuracy and inappropriate replenishment timing. There is also the problem of increased waste due to management methods that ignore product expiration dates.

[0083] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0084] In this invention, the server includes a means for collecting sales data, a means for forecasting demand based on the sales data, and a means for collecting and updating current inventory information. This allows for integrated management of sales data and inventory information, enabling highly accurate demand forecasting and appropriate inventory replenishment.

[0085] "Sales data" refers to information related to sales, such as product name, number of units sold, sales date and time, and sales price.

[0086] "Demand forecasting" is a method of estimating future demand based on past sales data.

[0087] "Inventory information" refers to detailed inventory data such as product quantity, expiration date, and current stock status.

[0088] "Automatic replenishment" is a method of automatically replenishing inventory before it runs out, based on forecast data and current inventory information.

[0089] "Rotation" is a management method that manages the expiration date of inventory and prioritizes the release of products that were received first.

[0090] "Real-time monitoring" is a method of continuously analyzing data to instantly grasp current inventory status and sales information.

[0091] A "barcode reader" is a device that reads barcodes attached to products.

[0092] "RFID" is a technology that uses wireless communication to read and write information about items.

[0093] An "AI model" is an algorithm that uses machine learning technology to analyze large amounts of data and make predictions and classifications.

[0094] "Supplier" refers to a trader or company that supplies goods.

[0095] This invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. This system is mainly composed of three elements: a server, a terminal, and a user.

[0096] Hardware and software used

[0097] Server: Used for data collection, analysis, prediction, and instruction. The server has machine learning libraries such as TensorFlow and PyTorch and database management systems such as MySQL and PostgreSQL installed.

[0098] Terminals: Used to collect and transmit data. These include barcode readers, RFID devices, and point-of-sale systems.

[0099] User devices: Used to check real-time inventory information. Web dashboard and mobile app installed.

[0100] System processing flow

[0101] 1. Collect sales data:

[0102] The terminal collects sales data such as product name, sales quantity, sales date and time, and sales price through a POS system or online system. The collected data is sent to the server in JSON format.

[0103] 2. Demand forecasting:

[0104] The server stores the received sales data in a database. Next, it uses TensorFlow and PyTorch to train an AI model based on past sales data. This trained model is then used to predict future demand.

[0105] 3. Inventory Management:

[0106] The terminal uses a barcode reader or RFID to collect current inventory information, including product quantities and expiration dates, and sends the collected data to a server, which then updates the database in real time.

[0107] 4. Automatic inventory replenishment:

[0108] The server compares the demand forecast data with current inventory information. If there is a shortage of inventory, the server automatically sends an order to the supplier. The order is placed via API.

[0109] 5. Proper inventory rotation:

[0110] The server manages the expiration dates of inventory and prioritizes the delivery of older inventory, thereby minimizing waste.

[0111] 6. Real-time monitoring:

[0112] Users can check inventory status in real time via a web dashboard or mobile app, allowing them to quickly make any necessary adjustments.

[0113] Specific examples

[0114] As a concrete example, the operation of the system in a grocery store will be described.

[0115] 1. Collect sales data:

[0116] The terminal transmits daily sales data (e.g., milk, 100ml, sales date and time, price) collected from the cash register system to the server in real time.

[0117] 2. Demand forecasting:

[0118] The server trains an AI model using TensorFlow based on past sales data. For example, it uses data showing that milk sales increase in the summer to predict demand for 200 liters next month.

[0119] 3. Inventory Management:

[0120] Every day, the terminal uses a barcode reader to collect inventory data and send it to the server, including information such as the current inventory level being 150 liters.

[0121] 4. Automatic inventory replenishment:

[0122] The server compares the demand forecast results with the current inventory and automatically sends an order to the supplier to replenish the missing 50 liters.

[0123] 5. Proper inventory rotation:

[0124] The server manages the expiration date information of milk and prevents it from being discarded after expiration by implementing a first-in, first-out (FIFO) system.

[0125] 6. Real-time monitoring:

[0126] Users can use the mobile app to check milk inventory and sales in real time, allowing them to make additional adjustments or implement promotional campaigns on the fly.

[0127] Prompt Sentence Examples

[0128] "Please outline a program that uses an inventory control system to forecast milk demand and automatically replenish it appropriately."

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1: Collect sales data

[0131] The terminal collects sales data in real time from stores and online systems. Specifically, it uses a POS system or web application to obtain information such as product name, number of units sold, sales date and time, and sales price. This collected data is sent to the server in JSON format. The input data is sales information, and the output data is the sales data sent to the server.

[0132] Step 2: Demand forecast

[0133] The server stores the received sales data in a database. Next, it uses TensorFlow to train an AI model. The input data used for training is past sales data, and the model is used to predict future demand. The output data is the predicted demand figure. For example, based on past data, it predicts that next month's demand for milk will be 200 liters.

[0134] Step 3: Manage inventory information

[0135] The terminal collects inventory information using a barcode reader or RFID. The collected inventory information includes product quantities, expiration dates, etc., and is sent to the server in JSON format. The input data is the inventory information obtained from the barcode reader or RFID, and the output data is the latest inventory information sent to the server. For example, the server will know that the current amount of milk in stock is 150 liters.

[0136] Step 4: Automatically replenish inventory

[0137] The server compares demand forecast data with current inventory information and analyzes it. The input data is the demand forecast value and current inventory information, and as a result of the analysis, it generates order data to make up for any shortages in inventory. For example, if the forecast demand is 200 liters and the current inventory is 150 liters, the server will order the missing 50 liters from the supplier. This order is placed automatically via API.

[0138] Step 5: Rotate your inventory appropriately

[0139] The server manages inventory expiration date information and adjusts the order so that older inventory is shipped first. The input data is inventory expiration date information, and generates the rotation data required to adjust the shipping order. The output data is the adjusted shipping order information. For example, a first-in, first-out (FIFO) order is implemented using an inventory management script.

[0140] Step 6: Real-time monitoring

[0141] The server continuously analyzes data collected from the devices and monitors inventory status in real time. The input data is sales and inventory information sent from the devices, and the server outputs analyzed inventory status data. Users can access this analysis data and check inventory information in real time via a web dashboard or mobile app. For example, users can instantly check milk inventory levels and sales and make any necessary adjustments or promotional activities.

[0142] (Application example 1)

[0143] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0144] Conventional inventory management systems are prone to inventory shortages and excess inventory, making inventory management, particularly in logistics warehouses, time-consuming and labor-intensive. In addition, inaccurate demand forecasts make it difficult to create accurate inventory plans, resulting in lower customer satisfaction and increased management costs. Furthermore, inventory replenishment work is often done manually, resulting in inefficiency. The present invention aims to solve these problems and achieve efficient and accurate inventory management.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0146] In this invention, the server includes a means for collecting sales data, a means for forecasting demand, a means for collecting and updating inventory information, a means for automatically replenishing inventory based on the collected and forecasted data, a means for managing appropriate inventory rotation, a means for monitoring inventory and sales information in real time, and a means for automatically replenishing inventory in the logistics warehouse using a robot. This enables efficient inventory management, accurate demand forecasting, and reduced labor through automatic replenishment.

[0147] Definitions of important words

[0148] "Sales data" is information indicating the sales status of a product, and includes details such as the number of units sold, the date and time of sale, the product name, and the sales price.

[0149] "Demand forecasting" is the process of estimating future sales volumes based on past sales data and market trends.

[0150] "Inventory information" is information indicating the quantity and expiration date of products held in a warehouse or store.

[0151] "Auto-replenish" means that the system automatically places an order for more stock before it runs out.

[0152] "Rotation" refers to managing products so that they are consumed in a specific order, and is often used to refer to first-in, first-out (FIFO).

[0153] "Real-time monitoring" means instantly understanding current inventory status and sales information.

[0154] A "robot" is a mechanical device that automatically replenishes inventory in a logistics warehouse according to programmed instructions.

[0155] An "AI model" is a mathematical algorithm or machine learning model that uses artificial intelligence to extract insights from data and make predictions and classifications.

[0156] A "sensor" is a device that detects physical phenomena and converts them into data. Examples include cameras and pressure sensors.

[0157] "Form for carrying out the invention" of the specification

[0158] The present invention is an automatic inventory replenishment system that uses AI to achieve efficient inventory management in logistics centers. This system uses specific hardware and software to collect sales data, forecast demand, manage inventory information, automatically replenish inventory, rotate inventory, and perform real-time monitoring. Specific embodiments for implementing the present invention are described below.

[0159] Hardware Configuration

[0160] The system includes the following hardware:

[0161] 1. Sensors: Detect the amount of inventory on shelves or in warehouses. For example, cameras and pressure sensors are used.

[0162] 2. Robot: A mechanical device that replenishes inventory in a distribution warehouse according to programmed instructions.

[0163] 3. Terminal: A device used for data collection and for administrators to check information in real time. Examples include smartphones and tablets.

[0164] 4. Server: A central device for aggregating data, analyzing it, and running AI models.

[0165] Software Configuration

[0166] The system includes the following software:

[0167] 1. Sales data collection program: Collects data from sensors in real time and sends it to the server.

[0168] 2. AI models: Built using machine learning libraries such as TensorFlow and PyTorch to perform demand forecasting.

[0169] 3. Inventory management program: Collects, updates, and manages inventory data and manages expiration date information.

[0170] 4. Automatic replenishment program: Based on demand forecasts and inventory information, calculates the required inventory level and sends replenishment instructions to the robot.

[0171] 5. Real-time monitoring interface: An application that monitors inventory status and sales information on a smartphone or tablet.

[0172] Processing flow

[0173] The server first receives sales data sent from sensors and terminals. It then trains an AI model based on the collected sales data to make demand forecasts. This forecast takes market trends and seasonal fluctuations into account. The server also collects current inventory information and updates the database in real time. It compares the forecast results with the inventory information, and if there is a shortage of inventory, it automatically calculates the required inventory amount and sends a replenishment instruction to the robot. The robot replenishes the inventory based on the calculated amount. The server also manages inventory expiration dates and maintains appropriate stock rotation. Users can use their terminals to check inventory status and sales information in real time.

[0174] Specific examples

[0175] As a concrete example, consider the case of managing milk inventory in a distribution warehouse. A sensor detects milk inventory and sends the current inventory amount to a server. Based on past sales data, an AI model predicts the demand for milk for next month. For example, let's say that based on past data, the amount of milk needed next month is predicted to be 200 liters. If the current inventory is 150 liters, a robot automatically picks up an additional 50 liters from the warehouse to replenish the missing 50 liters.

[0176] Prompt Sentence Examples

[0177] "Please predict next month's demand based on the following historical sales data:

[0178] Product Name: Dairy Products

[0179] Monthly sales for the past year (liters):

[0180] January: 200, February: 180, March: 250, April: 300, May: 280, June: 350, July: 400, August: 350, September: 320, October: 300, November: 250, December: 220

[0181] Anticipate future demand.

[0182] As a result, a system that can achieve efficient and accurate inventory management is constructed.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Processing steps of the system program that realizes the application example

[0185] Step 1:

[0186] Sensors and terminals monitor inventory on shelves and in warehouses in real time and collect inventory information.

[0187] Input: Shelf inventory status (product name, quantity, expiration date, etc.)

[0188] Processing: Collect inventory data from sensors (cameras and pressure sensors) and convert it into JSON format data.

[0189] Output: Inventory data in JSON format

[0190] Step 2:

[0191] The server receives the inventory data sent from the terminal and stores it in a database.

[0192] Input: Inventory data in JSON format

[0193] Processing: Store the received data in the database and update the current inventory information.

[0194] Output: Updated inventory database

[0195] Step 3:

[0196] The server collects sales data and creates a dataset to be input into the AI ​​model.

[0197] Input: Past sales data (product name, number of units sold, sales date and time, sales price, etc.)

[0198] Processing: Organizing and consolidating each sales data to generate a dataset suitable for the AI ​​model.

[0199] Output: Dataset for AI model

[0200] Step 4:

[0201] The server uses an AI model to make demand forecasts.

[0202] Input: Dataset for AI model

[0203] Processing: Run trained AI models using TensorFlow and PyTorch to predict future demand.

[0204] Output: Forecasted demand data

[0205] Step 5:

[0206] The server compares the forecast results with current inventory information and calculates the amount of inventory that is lacking.

[0207] Inputs: Forecasted demand data, current inventory data

[0208] Processing: Calculate the missing inventory by subtracting the current inventory from the forecasted demand.

[0209] Output: Data on shortage quantity

[0210] Step 6:

[0211] The server sends an automatic replenishment instruction to the robot.

[0212] Input: Data on the shortage amount

[0213] Processing: Generates and sends replenishment instructions to the robot, specifically instructions to retrieve the items the robot needs from the warehouse and replenish them.

[0214] Output: Replenishment instructions (instructions to the robot)

[0215] Step 7:

[0216] The robot follows replenishment instructions, retrieves products from the warehouse, and replenishes them on the designated shelves.

[0217] Input: Replenishment instructions

[0218] Processing: The robot moves, picks up the specified product, and places it appropriately on the specified shelf.

[0219] Output: Notification of replenishment completion

[0220] Step 8:

[0221] The server receives the report of the completion of stock replenishment and updates the database.

[0222] Input: Replenishment completion notification

[0223] Action: Update the database as available stock and check the real-time stock status again.

[0224] Output: Updated database, real-time inventory status

[0225] Step 9:

[0226] The terminal can monitor the latest inventory status and sales information in real time.

[0227] Input: Updated database

[0228] Processing: Retrieves the latest inventory and sales information from the database and provides an interface that allows users to visually check it.

[0229] Output: Inventory status and sales information display interface

[0230] Step 10:

[0231] The user uses the terminal to check inventory status and sales information, and issues additional replenishment instructions or implements sales promotion campaigns as necessary.

[0232] Input: Inventory status and sales information

[0233] Action: View information through the interface and plan replenishment and promotional campaigns. For example, alerts for low-stock items and planning campaigns to balance supply and demand.

[0234] Output: User decision support

[0235] Through the above processing steps, the system of the present invention realizes efficient and practical inventory management and automatic replenishment.

[0236] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0237] The present invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0238] ---

[0239] The system has the following components:

[0240] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. The sales data includes product name, number of units sold, date and time of sale, sales price, etc.

[0241] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[0242] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[0243] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[0244] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[0245] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[0246] 7. Emotion engine: The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. This emotional data is sent to the server and used for inventory management and product recommendations.

[0247] 8. Utilizing Emotional Data: The server can use emotional data to predict user purchasing intent and product popularity, providing additional data for optimizing inventory replenishment and marketing strategies.

[0248] ---

[0249] Specific examples

[0250] As a concrete example, the operation of the system in a grocery store will be described.

[0251] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[0252] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[0253] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[0254] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[0255] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[0256] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[0257] 7. Use of emotion engine: Using the camera and microphone on the device, the system analyzes the user's facial expressions and voice to collect emotional data. For example, analyzing the user's facial expressions and voice tone when purchasing milk can be used to assess the user's willingness to purchase.

[0258] 8. Utilizing Emotional Data: The server analyzes the collected emotional data to assess user interest in specific products. For example, if users express excitement about a product, the server can stock more of that product. It can also adjust marketing efforts and implement promotions that evoke specific emotions.

[0259] This will further improve the accuracy and efficiency of inventory management, and will also improve customer satisfaction based on user emotions.

[0260] The processing flow will be explained below.

[0261] Step 1:

[0262] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[0263] Step 2:

[0264] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[0265] Step 3:

[0266] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[0267] Step 4:

[0268] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[0269] Step 5:

[0270] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[0271] Step 6:

[0272] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[0273] Step 7:

[0274] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[0275] Step 8:

[0276] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[0277] Step 9:

[0278] Users can view the inventory rotation plan through the terminal and manually adjust it as needed, for example by changing the order in which new arrivals are placed after older stock.

[0279] Step 10:

[0280] The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. For example, it detects the facial expressions and voice tone when the user picks up a product.

[0281] Step 11:

[0282] The device sends the emotional data to a server, which then stores the collected data in a database and analyzes it.

[0283] Step 12:

[0284] The server uses the emotional data to predict the user's purchasing intent and the popularity of a product. For example, if the user is excited, the server will adjust the supply and demand forecast for that product upward.

[0285] Step 13:

[0286] The server uses the emotional data to optimize inventory replenishment and marketing strategies, for example, by identifying products that users find favorable and implementing promotions centered around those products.

[0287] Step 14:

[0288] The server continuously collects sales, inventory, and sentiment data and updates the system in real time, ensuring that the latest demand forecasts and inventory information are always available.

[0289] Step 15:

[0290] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[0291] This will improve the accuracy and efficiency of inventory management, and also improve customer satisfaction using an emotion engine.

[0292] Example 2

[0293] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0294] Current inventory management systems forecast demand and replenish inventory based on sales and inventory data, but they are unable to take user emotions or purchasing intentions into account. This makes it difficult to accurately forecast demand and appropriately replenish inventory, resulting in a high risk of stockouts and excess inventory. Furthermore, marketing strategies to improve the user experience are not adequately optimized. To solve these problems, there is a need for more accurate demand forecasts and an inventory management system that takes user emotions into account.

[0295] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting sales data, a means for collecting and updating current inventory information, a means for automatically replenishing inventory based on the collected and predicted data, a means for collecting and analyzing user emotion data, and a means for optimizing demand forecasting and marketing strategies based on the emotion data. This improves the accuracy of demand forecasting, reduces the risk of stockouts and excess inventory, and enables product suggestions and marketing strategies to be optimized based on user emotions.

[0296] "Sales data" refers to information such as the name of the product sold in a store or online system, the number of units sold, the date and time of sale, and the sales price.

[0297] "Demand forecasting" is the process of predicting future sales volumes and required inventory levels based on collected sales data.

[0298] "Inventory information" is data such as the quantity and expiration date of currently held products.

[0299] "Automatic inventory replenishment" refers to the automatic replenishment of inventory based on demand forecasts and current inventory information to prevent inventory shortages.

[0300] "Appropriate inventory rotation" means taking into account product expiration dates and managing the inventory so that older inventory is consumed first.

[0301] "Real-time monitoring" means continuously analyzing inventory status and sales information to instantly grasp the latest data.

[0302] "Emotion data" refers to information related to emotions collected from the user's facial expressions, tone of voice, movements, and the like.

[0303] An "emotion engine" is a technology or device that analyzes a user's facial expressions, voice, and movements to collect emotional data.

[0304] A "marketing strategy" is a strategic measure aimed at promoting product sales and improving customer satisfaction.

[0305] This invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. This system improves the accuracy and efficiency of inventory management through sales data collection, demand forecasting, inventory information management, automatic inventory replenishment, appropriate inventory rotation, real-time monitoring, and the use of emotion data.

[0306] Hardware and software used

[0307] 1. Terminal

[0308] Hardware: POS system, barcode scanner, camera, microphone

[0309] Software: Data collection software, facial expression recognition software (e.g., OpenCV), voice analysis software

[0310] 2. Server

[0311] Hardware: High-performance servers (e.g. cloud infrastructure)

[0312] Software: Database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., TensorFlow, PyTorch), visual tools (e.g., Grafana, PowerBI), sentiment analysis algorithms

[0313] Process Overview

[0314] 1. Collect sales data

[0315] The terminal collects sales data in real time from stores and online systems and sends it to a server. The collected sales data includes product name, number of units sold, date and time of sale, and sales price.

[0316] 2. Demand forecast

[0317] The server uses the accumulated sales data to train a generative AI model, which is then used to accurately forecast future demand, including past sales data and seasonality features.

[0318] 3. Inventory management

[0319] The terminal periodically collects current inventory information and sends it to the server, which uses this information to update the inventory database in real time.

[0320] 4. Automatic inventory replenishment

[0321] The server compares demand forecast data with current inventory information to calculate the amount of replenishment required, calculates the appropriate timing and quantity, and automatically sends orders to suppliers.

[0322] 5. Proper inventory rotation

[0323] The server uses expiration information in the inventory database to prioritize product consumption, implementing FIFO (first in, first out) logic to ensure that older inventory is sold first.

[0324] 6. Real-time monitoring

[0325] The server analyzes the continuously collected data and generates reports that are displayed on a dashboard, where users can access up-to-date inventory and sales data via their devices.

[0326] 7. Incorporating an Emotional Engine

[0327] The device's built-in camera and microphone are used to analyze the user's facial expressions, voice tone, and movements, and collect emotional data. This emotional data is sent to a server and used for various analyses.

[0328] 8. Utilizing Emotional Data

[0329] The server analyzes the collected emotional data to assess the user's purchasing intent and interest in specific products, thereby improving the accuracy of inventory replenishment and optimizing product recommendations and marketing strategies based on user emotions.

[0330] Specific examples

[0331] As an example of how the system works in a grocery store, a terminal collects daily sales data from the cash register system (e.g., milk, 100ml, sales date and time, price) and sends that data to a server. The server uses an AI model based on past sales data to predict next month's milk demand (e.g., predicting the amount of milk needed next month to be 200 liters). The terminal also collects daily inventory data (current inventory: 150 liters) and sends it to the server. The server automatically sends an order to the supplier to replenish the missing 50 liters.

[0332] The device also uses a camera and microphone to analyze the user's facial expressions and voice tone to collect emotional data. For example, when a user purchases milk, the device analyzes their facial expressions and voice tone to assess their willingness to purchase, and sends this data to a server. The server analyzes this emotional data to assess the product's popularity and purchasing intent, and then optimizes inventory replenishment and marketing strategies based on that data.

[0333] As a specific example, a prompt such as, "Based on sales data for milk at a grocery store, we would like to predict summer demand and automatically replenish it using an inventory management system. Please tell us the specific steps required and the points that we should consider." could be used.

[0334] The above is a specific embodiment of the present invention.

[0335] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0336] Step 1: Collect sales data

[0337] The terminal collects sales data in real time from stores and online systems. It takes in information from data sources such as POS systems and e-commerce platforms. Specifically, it collects information such as product name, number of units sold, date and time of sale, and sales price. The collected data is stored in JSON format and sent to the server. The input is sales data from each data source, and the output is formatted data sent to the server.

[0338] Step 2: Submit your sales data

[0339] The terminal periodically sends the collected sales data to the server. The HTTPS protocol is used to ensure security when sending data. Specifically, the terminal temporarily stores the collected data and then sends it to the server in batches after a certain period of time has passed. The input is formatted sales data, and the output is the sales data stored on the server.

[0340] Step 3: Save your sales data

[0341] The server saves the received sales data in a database. At this time, it uses a database management system (e.g., MySQL, PostgreSQL) to store the data accurately. The server inserts each data item into the corresponding table according to the data schema. The input is the sales data sent to the server, and the output is the sales data stored in the database.

[0342] Step 4: Training the AI ​​model

[0343] The server uses sales data stored in the database to train a generative AI model (e.g., TensorFlow, PyTorch). The model takes past sales data and features such as seasonal factors as input and outputs a demand forecasting model. Specifically, it runs the training dataset multiple times while optimizing the model's learning parameters. The input is sales data extracted from the database, and the output is a trained demand forecasting model.

[0344] Step 5: Demand forecasting

[0345] The server uses the trained demand forecasting model to predict future demand. Specifically, it makes numerical predictions of next month's sales volume and demand for specific products. The server inputs new sales data into the trained model and outputs the demand forecast results. The input is new sales data, and the output is the predicted product demand.

[0346] Step 6: Gather inventory information

[0347] The terminal periodically collects current inventory information (product name, quantity, expiration date, etc.) and sends that information to the server. Specific operations involve acquiring data using a barcode scanner or inventory management software. The input is the current inventory information, and the output is the inventory data sent to the server.

[0348] Step 7: Save inventory information

[0349] The server stores the received inventory data in a database. The server inserts the inventory data into the corresponding table and updates the database in real time. The input is the inventory data sent to the server, and the output is the inventory information stored in the database.

[0350] Step 8: Automatically replenish inventory

[0351] The server compares demand forecast data with current inventory information to calculate how much replenishment is required. The server calculates the shortage and automatically sends a replenishment order to the supplier. Specifically, it generates an order list and places an order with the supplier via API. The input is demand forecast data and inventory information, and the output is the order data sent to the supplier.

[0352] Step 9: Rotate your inventory appropriately

[0353] The server uses expiration date information in the inventory database to set product consumption priorities. It executes FIFO (first in, first out) logic and issues instructions to sell older stock first. Specifically, it creates a stock rotation plan for each product and sends it to the terminal. The input is inventory information, and the output is rotation instructions to the terminal.

[0354] Step 10: Real-time monitoring

[0355] The server continuously analyzes the collected data and generates reports that are displayed on a dashboard. Users can access up-to-date inventory and sales data using their devices. Specific operations involve using data analysis software to generate graphs and charts using visual tools (e.g., Grafana, PowerBI). The input is the data to be analyzed, and the output is a dashboard that users can access.

[0356] Step 11: Collect emotion data

[0357] Emotional data is collected by analyzing the user's facial expressions, voice tone, and movements using the device's built-in camera and microphone. For example, facial expression recognition software (e.g., OpenCV) is used to analyze the user's facial expressions while browsing products. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[0358] Step 12: Sending Emotion Data

[0359] The device sends the collected emotion data to the server. The HTTPS protocol is used for data transmission, ensuring secure transmission of emotion data. The input is the collected emotion data, and the output is the data sent to the server.

[0360] Step 13: Analyze the emotion data

[0361] The server analyzes the received emotional data and evaluates the user's purchasing intent and interest in the product. The server uses an emotion analysis algorithm to quantitatively evaluate the user's emotions. The input is the transmitted emotional data, and the output is the analysis result.

[0362] Step 14: Optimize your marketing strategy

[0363] The server uses the sentiment data to optimize inventory replenishment and marketing strategies. If there is high interest in a particular product, it will automatically implement measures such as increasing the stock of that product. The input is the analysis results, and the output is an optimized replenishment plan and marketing measures.

[0364] (Application example 2)

[0365] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0366] Current inventory management systems focus on forecasting demand and streamlining inventory replenishment based on sales data and inventory information, but they lack the ability to utilize customer sentiment data. This makes it difficult to understand customer purchasing intent and product popularity in real time and optimize marketing strategies and inventory management.

[0367] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for performing demand forecasting, means for collecting and updating inventory information, means for automatically replenishing inventory, means for managing inventory rotation and taking product expiration dates into consideration, means for monitoring inventory and sales information in real time, means for collecting and analyzing emotion data, and means for optimizing demand forecasting and inventory replenishment based on the emotion data. This enables demand forecasting and real-time inventory management that takes customer emotions into consideration.

[0368] 1. "Sales data" refers to purchase information such as product name, quantity sold, sales date and time, and sales price, and is information collected from stores and online systems.

[0369] 2. "Demand forecasting" is the process of predicting future product demand using AI models based on sales data and market trends.

[0370] 3. "Inventory information" is a general term for data required in an inventory management system, including information such as current inventory quantities, product expiration dates, and storage locations.

[0371] 4. "Automated inventory replenishment" is a system or process that automatically orders products from suppliers before they run out of stock, based on demand forecast data and current inventory information.

[0372] 5. "Inventory rotation" is an inventory management technique that takes into account product expiration dates and adjusts inventory so that older inventory is consumed first.

[0373] 6. "Real-time monitoring" is the process of immediately analyzing collected data to monitor real-time inventory status and sales information.

[0374] 7. "Emotional Data" refers to data used to understand a user's emotional state by analyzing information such as the user's facial expressions, tone of voice, and movements.

[0375] 8. "Sentiment analysis" is the process of using collected emotional data to analyze a user's emotional state and assess purchasing intent and product popularity.

[0376] 9. “Optimization” is the process of adjusting to maximize efficiency or effectiveness under given conditions, and in this case refers to using sentiment data to improve demand forecasting and inventory replenishment.

[0377] This invention combines an emotion recognition engine with an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[0378] The system consists of a terminal that collects sales data, a server that predicts demand based on that sales data, a terminal that collects and updates current inventory information, a server that automatically replenishes inventory based on the collected and predicted data, a server that manages appropriate inventory rotation and takes product expiration dates into account, a terminal that monitors inventory and sales information in real time, a terminal that collects and analyzes emotional data, and a server that optimizes demand prediction and inventory replenishment based on the emotional data.

[0379] Hardware and software used

[0380] 1. Smartphones and smart glasses:

[0381] Camera: Captures the user's facial expressions for emotion recognition.

[0382] Microphone: Records the user's voice for emotion recognition.

[0383] 2. Server:

[0384] Database: Used to store and manage sales and inventory data.

[0385] AI models: Use machine learning libraries (e.g., Scikit-learn) to perform demand forecasting and sentiment analysis.

[0386] 3. Software Libraries:

[0387] OpenCV: An image processing library for facial expression recognition.

[0388] Dlib: Facial landmark detection.

[0389] Scikit-learn: A machine learning library for demand forecasting and sentiment analysis.

[0390] Processing flow

[0391] Device data collection:

[0392] The camera and microphone installed in the smartphone or smart glasses are used to collect the user's facial expressions and voice, and this data is sent to a server in real time.

[0393] Sentiment analysis and purchase intent assessment:

[0394] Emotion data is analyzed using OpenCV and Dlib to understand the user's emotional state, and the AI ​​model then predicts their purchasing intent. For example, if a customer shows excitement in front of a particular product, it predicts increased demand for that product.

[0395] Inventory Management:

[0396] The server uses sales and inventory data to make demand forecasts. By adding the results of sentiment analysis to the demand forecast, it is possible to make demand forecasts that take into account product popularity and purchasing intentions.

[0397] Automatic inventory replenishment:

[0398] The server automatically replenishes goods based on demand forecasts and current inventory information. Specifically, it automatically orders products from suppliers based on demand forecast data before inventory runs out.

[0399] Real-time monitoring:

[0400] Users (store staff) can use smart devices to check inventory status and sales information in real time, which allows for immediate adjustments and promotional campaigns.

[0401] Specific examples

[0402] Milk inventory management:

[0403] Milk sales data is collected in real time and sent to a server. Based on past sales data and market trends, an AI model predicts next month's demand at 200 liters. Knowing that current stock is 150 liters, the AI ​​model automatically orders the missing 50 liters from the supplier. Furthermore, when a customer purchases milk, the smart glasses capture their facial expressions and analyze their excitement, prompting them to order more.

[0404] Prompt Sentence Examples

[0405] "Analyze the facial expressions and voices of users when they purchase milk and predict their purchasing intentions."

[0406] This will enable demand forecasting and inventory management that takes emotional data into account, improving accuracy and efficiency.

[0407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0408] Step 1:

[0409] The device collects the user's facial expressions and voice in real time using the camera and microphone of a smartphone or smart glasses, and generates image and audio files as facial expression and voice data, which are then sent to a server.

[0410] Step 2:

[0411] The server analyzes the received facial expression and audio data. Specifically, it uses OpenCV and Dlib to extract facial landmarks from image files and perform emotion analysis. It also performs tone analysis on audio files to determine the user's emotional state. The input data are facial expression images and audio files, and the output data are labels indicating the emotional state (e.g., "happy," "sad," or "neutral").

[0412] Step 3:

[0413] The server stores the results of the emotion analysis in a database. Detailed emotion data is managed by storing the date and time, user ID, and product information together with the emotional state label. This allows for the accumulation of data necessary for future analysis.

[0414] Step 4:

[0415] The terminal collects sales data from the POS system. The sales data, which includes product name, quantity sold, date and time of sale, and sales price, is periodically sent to the server and received as input data. The output is a record of the updated sales data.

[0416] Step 5:

[0417] The server makes demand forecasts based on accumulated sales data. Past sales data and sentiment data are input into a generative AI model to predict future demand. The forecast results are output as the required quantity of each product for the next month.

[0418] Step 6:

[0419] The server collects current inventory information from the terminals and updates the database in real time. Data including stock quantity, product expiration date, storage location, etc. is input, and the latest inventory status is output.

[0420] Step 7:

[0421] The server compares demand forecast data with current inventory information and automatically replenishes items that are out of stock. It calculates the necessary replenishment amount and the optimal order timing, and automatically sends orders to suppliers. The input data is the demand forecast results and inventory information, and the output data is order details.

[0422] Step 8:

[0423] The server manages the appropriate rotation of inventory. Taking into account the expiration date of the inventory, it adjusts the inventory so that the inventory received first is consumed first. This minimizes product waste. The input data is the expiration date information of the inventory, and the output data is the rotation instruction.

[0424] Step 9:

[0425] Users can monitor inventory status and sales information in real time using a terminal, allowing them to immediately grasp sales trends and inventory status. Input data is current inventory and sales information, and output data is a real-time report of these.

[0426] Step 10:

[0427] The server optimizes marketing strategies based on emotion data. Specifically, it stocks more inventory of products that evoke specific emotions and implements promotions that evoke those emotions. The input data is the emotion analysis results, and the output data is an optimized marketing plan.

[0428] These steps will enable demand forecasting and inventory management that takes emotion data into account, improving the accuracy and efficiency of inventory management.

[0429] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0430] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0431] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0432] [Second embodiment]

[0433] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0434] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0435] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0436] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0437] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0438] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0439] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0440] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0441] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0442] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0443] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0444] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0445] The present invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[0446] ---

[0447] The system has the following components:

[0448] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. Sales data includes product names, quantities sold, sales dates and times, sales prices, etc.

[0449] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[0450] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[0451] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[0452] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[0453] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[0454] ---

[0455] Specific examples

[0456] As a concrete example, the operation of the system in a grocery store will be described.

[0457] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[0458] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[0459] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[0460] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[0461] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[0462] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[0463] This improves the accuracy and efficiency of inventory management, reduces resource waste, and increases customer satisfaction.

[0464] The processing flow will be explained below.

[0465] Step 1:

[0466] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[0467] Step 2:

[0468] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[0469] Step 3:

[0470] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[0471] Step 4:

[0472] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[0473] Step 5:

[0474] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[0475] Step 6:

[0476] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[0477] Step 7:

[0478] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[0479] Step 8:

[0480] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[0481] Step 9:

[0482] Users can view the inventory rotation plan through the terminal and manually adjust it if necessary, for example by changing the order in which new arrivals are placed after older stock.

[0483] Step 10:

[0484] The server continuously collects sales and inventory data and updates the system in real time, allowing you to constantly monitor the latest inventory status and sales trends.

[0485] Step 11:

[0486] The server periodically retrains the demand forecasting model based on new data collected, thereby maintaining and further improving the accuracy of the forecasts.

[0487] Step 12:

[0488] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[0489] Through the above processing steps, the system of the present invention can improve the efficiency and accuracy of inventory management, minimize a company's inventory risk, and increase customer satisfaction.

[0490] Example 1

[0491] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0492] With conventional inventory management systems, sales data collection, demand forecasting, and automatic inventory replenishment are often carried out separately, making integrated management difficult. Furthermore, there are issues with overstocking and shortages due to a lack of forecast accuracy and inappropriate replenishment timing. There is also the problem of increased waste due to management methods that ignore product expiration dates.

[0493] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0494] In this invention, the server includes a means for collecting sales data, a means for forecasting demand based on the sales data, and a means for collecting and updating current inventory information. This allows for integrated management of sales data and inventory information, enabling highly accurate demand forecasting and appropriate inventory replenishment.

[0495] "Sales data" refers to information related to sales, such as product name, number of units sold, sales date and time, and sales price.

[0496] "Demand forecasting" is a method of estimating future demand based on past sales data.

[0497] "Inventory information" refers to detailed inventory data such as product quantity, expiration date, and current stock status.

[0498] "Automatic replenishment" is a method of automatically replenishing inventory before it runs out, based on forecast data and current inventory information.

[0499] "Rotation" is a management method that manages the expiration date of inventory and prioritizes the release of products that were received first.

[0500] "Real-time monitoring" is a method of continuously analyzing data to instantly grasp current inventory status and sales information.

[0501] A "barcode reader" is a device that reads barcodes attached to products.

[0502] "RFID" is a technology that uses wireless communication to read and write information about items.

[0503] An "AI model" is an algorithm that uses machine learning technology to analyze large amounts of data and make predictions and classifications.

[0504] "Supplier" refers to a trader or company that supplies goods.

[0505] This invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. This system is mainly composed of three elements: a server, a terminal, and a user.

[0506] Hardware and software used

[0507] Server: Used for data collection, analysis, prediction, and instruction. The server has machine learning libraries such as TensorFlow and PyTorch and database management systems such as MySQL and PostgreSQL installed.

[0508] Terminals: Used to collect and transmit data. These include barcode readers, RFID devices, and point-of-sale systems.

[0509] User devices: Used to check real-time inventory information. Web dashboard and mobile app installed.

[0510] System processing flow

[0511] 1. Collect sales data:

[0512] The terminal collects sales data such as product name, sales quantity, sales date and time, and sales price through a POS system or online system. The collected data is sent to the server in JSON format.

[0513] 2. Demand forecasting:

[0514] The server stores the received sales data in a database. Next, it uses TensorFlow and PyTorch to train an AI model based on past sales data. This trained model is then used to predict future demand.

[0515] 3. Inventory Management:

[0516] The terminal uses a barcode reader or RFID to collect current inventory information, including product quantities and expiration dates, and sends the collected data to a server, which then updates the database in real time.

[0517] 4. Automatic inventory replenishment:

[0518] The server compares the demand forecast data with current inventory information. If there is a shortage of inventory, the server automatically sends an order to the supplier. The order is placed via API.

[0519] 5. Proper inventory rotation:

[0520] The server manages the expiration dates of inventory and prioritizes the delivery of older inventory, thereby minimizing waste.

[0521] 6. Real-time monitoring:

[0522] Users can check inventory status in real time via a web dashboard or mobile app, allowing them to quickly make any necessary adjustments.

[0523] Specific examples

[0524] As a concrete example, the operation of the system in a grocery store will be described.

[0525] 1. Collect sales data:

[0526] The terminal transmits daily sales data (e.g., milk, 100ml, sales date and time, price) collected from the cash register system to the server in real time.

[0527] 2. Demand forecasting:

[0528] The server trains an AI model using TensorFlow based on past sales data. For example, it uses data showing that milk sales increase in the summer to predict demand for 200 liters next month.

[0529] 3. Inventory Management:

[0530] Every day, the terminal uses a barcode reader to collect inventory data and send it to the server, including information such as the current inventory level being 150 liters.

[0531] 4. Automatic inventory replenishment:

[0532] The server compares the demand forecast results with the current inventory and automatically sends an order to the supplier to replenish the missing 50 liters.

[0533] 5. Proper inventory rotation:

[0534] The server manages the expiration date information of milk and prevents it from being discarded after expiration by implementing a first-in, first-out (FIFO) system.

[0535] 6. Real-time monitoring:

[0536] Users can use the mobile app to check milk inventory and sales in real time, allowing them to make additional adjustments or implement promotional campaigns on the fly.

[0537] Prompt Sentence Examples

[0538] "Please outline a program that uses an inventory control system to forecast milk demand and automatically replenish it appropriately."

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1: Collect sales data

[0541] The terminal collects sales data in real time from stores and online systems. Specifically, it uses a POS system or web application to obtain information such as product name, number of units sold, sales date and time, and sales price. This collected data is sent to the server in JSON format. The input data is sales information, and the output data is the sales data sent to the server.

[0542] Step 2: Demand forecast

[0543] The server stores the received sales data in a database. Next, it uses TensorFlow to train an AI model. The input data used for training is past sales data, and the model is used to predict future demand. The output data is the predicted demand figure. For example, based on past data, it predicts that next month's demand for milk will be 200 liters.

[0544] Step 3: Manage inventory information

[0545] The terminal collects inventory information using a barcode reader or RFID. The collected inventory information includes product quantities, expiration dates, etc., and is sent to the server in JSON format. The input data is the inventory information obtained from the barcode reader or RFID, and the output data is the latest inventory information sent to the server. For example, the server will know that the current amount of milk in stock is 150 liters.

[0546] Step 4: Automatically replenish inventory

[0547] The server compares demand forecast data with current inventory information and analyzes it. The input data is the demand forecast value and current inventory information, and as a result of the analysis, it generates order data to make up for any shortages in inventory. For example, if the forecast demand is 200 liters and the current inventory is 150 liters, the server will order the missing 50 liters from the supplier. This order is placed automatically via API.

[0548] Step 5: Rotate your inventory appropriately

[0549] The server manages inventory expiration date information and adjusts the order so that older inventory is shipped first. The input data is inventory expiration date information, and generates the rotation data required to adjust the shipping order. The output data is the adjusted shipping order information. For example, a first-in, first-out (FIFO) order is implemented using an inventory management script.

[0550] Step 6: Real-time monitoring

[0551] The server continuously analyzes data collected from the devices and monitors inventory status in real time. The input data is sales and inventory information sent from the devices, and the server outputs analyzed inventory status data. Users can access this analysis data and check inventory information in real time via a web dashboard or mobile app. For example, users can instantly check milk inventory levels and sales and make any necessary adjustments or promotional activities.

[0552] (Application example 1)

[0553] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0554] Conventional inventory management systems are prone to inventory shortages and excess inventory, making inventory management, particularly in logistics warehouses, time-consuming and labor-intensive. In addition, inaccurate demand forecasts make it difficult to create accurate inventory plans, resulting in lower customer satisfaction and increased management costs. Furthermore, inventory replenishment work is often done manually, resulting in inefficiency. The present invention aims to solve these problems and achieve efficient and accurate inventory management.

[0555] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0556] In this invention, the server includes a means for collecting sales data, a means for forecasting demand, a means for collecting and updating inventory information, a means for automatically replenishing inventory based on the collected and forecasted data, a means for managing appropriate inventory rotation, a means for monitoring inventory and sales information in real time, and a means for automatically replenishing inventory in the logistics warehouse using a robot. This enables efficient inventory management, accurate demand forecasting, and reduced labor through automatic replenishment.

[0557] Definitions of important words

[0558] "Sales data" is information indicating the sales status of a product, and includes details such as the number of units sold, the date and time of sale, the product name, and the sales price.

[0559] "Demand forecasting" is the process of estimating future sales volumes based on past sales data and market trends.

[0560] "Inventory information" is information indicating the quantity and expiration date of products held in a warehouse or store.

[0561] "Auto-replenish" means that the system automatically places an order for more stock before it runs out.

[0562] "Rotation" refers to managing products so that they are consumed in a specific order, and is often used to refer to first-in, first-out (FIFO).

[0563] "Real-time monitoring" means instantly understanding current inventory status and sales information.

[0564] A "robot" is a mechanical device that automatically replenishes inventory in a logistics warehouse according to programmed instructions.

[0565] An "AI model" is a mathematical algorithm or machine learning model that uses artificial intelligence to extract insights from data and make predictions and classifications.

[0566] A "sensor" is a device that detects physical phenomena and converts them into data. Examples include cameras and pressure sensors.

[0567] "Form for carrying out the invention" of the specification

[0568] The present invention is an automatic inventory replenishment system that uses AI to achieve efficient inventory management in logistics centers. This system uses specific hardware and software to collect sales data, forecast demand, manage inventory information, automatically replenish inventory, rotate inventory, and perform real-time monitoring. Specific embodiments for implementing the present invention are described below.

[0569] Hardware Configuration

[0570] The system includes the following hardware:

[0571] 1. Sensors: Detect the amount of inventory on shelves or in warehouses. For example, cameras and pressure sensors are used.

[0572] 2. Robot: A mechanical device that replenishes inventory in a distribution warehouse according to programmed instructions.

[0573] 3. Terminal: A device used for data collection and for administrators to check information in real time. Examples include smartphones and tablets.

[0574] 4. Server: A central device for aggregating data, analyzing it, and running AI models.

[0575] Software Configuration

[0576] The system includes the following software:

[0577] 1. Sales data collection program: Collects data from sensors in real time and sends it to the server.

[0578] 2. AI models: Built using machine learning libraries such as TensorFlow and PyTorch to perform demand forecasting.

[0579] 3. Inventory management program: Collects, updates, and manages inventory data and manages expiration date information.

[0580] 4. Automatic replenishment program: Based on demand forecasts and inventory information, calculates the required inventory level and sends replenishment instructions to the robot.

[0581] 5. Real-time monitoring interface: An application that monitors inventory status and sales information on a smartphone or tablet.

[0582] Processing flow

[0583] The server first receives sales data sent from sensors and terminals. It then trains an AI model based on the collected sales data to make demand forecasts. This forecast takes market trends and seasonal fluctuations into account. The server also collects current inventory information and updates the database in real time. It compares the forecast results with the inventory information, and if there is a shortage of inventory, it automatically calculates the required inventory amount and sends a replenishment instruction to the robot. The robot replenishes the inventory based on the calculated amount. The server also manages inventory expiration dates and maintains appropriate stock rotation. Users can use their terminals to check inventory status and sales information in real time.

[0584] Specific examples

[0585] As a concrete example, consider the case of managing milk inventory in a distribution warehouse. A sensor detects milk inventory and sends the current inventory amount to a server. Based on past sales data, an AI model predicts the demand for milk for next month. For example, let's say that based on past data, the amount of milk needed next month is predicted to be 200 liters. If the current inventory is 150 liters, a robot automatically picks up an additional 50 liters from the warehouse to replenish the missing 50 liters.

[0586] Prompt Sentence Examples

[0587] "Please predict next month's demand based on the following historical sales data:

[0588] Product Name: Dairy Products

[0589] Monthly sales for the past year (liters):

[0590] January: 200, February: 180, March: 250, April: 300, May: 280, June: 350, July: 400, August: 350, September: 320, October: 300, November: 250, December: 220

[0591] Anticipate future demand.

[0592] As a result, a system that can achieve efficient and accurate inventory management is constructed.

[0593] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0594] Processing steps of the system program that realizes the application example

[0595] Step 1:

[0596] Sensors and terminals monitor inventory on shelves and in warehouses in real time and collect inventory information.

[0597] Input: Shelf inventory status (product name, quantity, expiration date, etc.)

[0598] Processing: Collect inventory data from sensors (cameras and pressure sensors) and convert it into JSON format data.

[0599] Output: Inventory data in JSON format

[0600] Step 2:

[0601] The server receives the inventory data sent from the terminal and stores it in a database.

[0602] Input: Inventory data in JSON format

[0603] Processing: Store the received data in the database and update the current inventory information.

[0604] Output: Updated inventory database

[0605] Step 3:

[0606] The server collects sales data and creates a dataset to be input into the AI ​​model.

[0607] Input: Past sales data (product name, number of units sold, sales date and time, sales price, etc.)

[0608] Processing: Organizing and consolidating each sales data to generate a dataset suitable for the AI ​​model.

[0609] Output: Dataset for AI model

[0610] Step 4:

[0611] The server uses an AI model to make demand forecasts.

[0612] Input: Dataset for AI model

[0613] Processing: Run trained AI models using TensorFlow and PyTorch to predict future demand.

[0614] Output: Forecasted demand data

[0615] Step 5:

[0616] The server compares the forecast results with current inventory information and calculates the amount of inventory that is lacking.

[0617] Inputs: Forecasted demand data, current inventory data

[0618] Processing: Calculate the missing inventory by subtracting the current inventory from the forecasted demand.

[0619] Output: Data on shortage quantity

[0620] Step 6:

[0621] The server sends an automatic replenishment instruction to the robot.

[0622] Input: Data on the shortage amount

[0623] Processing: Generates and sends replenishment instructions to the robot, specifically instructions to retrieve the items the robot needs from the warehouse and replenish them.

[0624] Output: Replenishment instructions (instructions to the robot)

[0625] Step 7:

[0626] The robot follows replenishment instructions, retrieves products from the warehouse, and replenishes them on the designated shelves.

[0627] Input: Replenishment instructions

[0628] Processing: The robot moves, picks up the specified product, and places it appropriately on the specified shelf.

[0629] Output: Notification of replenishment completion

[0630] Step 8:

[0631] The server receives the report of the completion of stock replenishment and updates the database.

[0632] Input: Replenishment completion notification

[0633] Action: Update the database as available stock and check the real-time stock status again.

[0634] Output: Updated database, real-time inventory status

[0635] Step 9:

[0636] The terminal can monitor the latest inventory status and sales information in real time.

[0637] Input: Updated database

[0638] Processing: Retrieves the latest inventory and sales information from the database and provides an interface that allows users to visually check it.

[0639] Output: Inventory status and sales information display interface

[0640] Step 10:

[0641] The user uses the terminal to check inventory status and sales information, and issues additional replenishment instructions or implements sales promotion campaigns as necessary.

[0642] Input: Inventory status and sales information

[0643] Action: View information through the interface and plan replenishment and promotional campaigns. For example, alerts for low-stock items and planning campaigns to balance supply and demand.

[0644] Output: User decision support

[0645] Through the above processing steps, the system of the present invention realizes efficient and practical inventory management and automatic replenishment.

[0646] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0647] The present invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[0648] ---

[0649] The system has the following components:

[0650] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. The sales data includes product name, number of units sold, date and time of sale, sales price, etc.

[0651] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[0652] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[0653] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[0654] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[0655] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[0656] 7. Emotion engine: The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. This emotional data is sent to the server and used for inventory management and product recommendations.

[0657] 8. Utilizing Emotional Data: The server can use emotional data to predict user purchasing intent and product popularity, providing additional data for optimizing inventory replenishment and marketing strategies.

[0658] ---

[0659] Specific examples

[0660] As a concrete example, the operation of the system in a grocery store will be described.

[0661] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[0662] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[0663] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[0664] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[0665] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[0666] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[0667] 7. Use of emotion engine: Using the camera and microphone on the device, the system analyzes the user's facial expressions and voice to collect emotional data. For example, analyzing the user's facial expressions and voice tone when purchasing milk can be used to assess the user's willingness to purchase.

[0668] 8. Utilizing Emotional Data: The server analyzes the collected emotional data to assess user interest in specific products. For example, if users express excitement about a product, the server can stock more of that product. It can also adjust marketing efforts and implement promotions that evoke specific emotions.

[0669] This will further improve the accuracy and efficiency of inventory management, and will also improve customer satisfaction based on user emotions.

[0670] The processing flow will be explained below.

[0671] Step 1:

[0672] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[0673] Step 2:

[0674] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[0675] Step 3:

[0676] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[0677] Step 4:

[0678] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[0679] Step 5:

[0680] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[0681] Step 6:

[0682] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[0683] Step 7:

[0684] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[0685] Step 8:

[0686] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[0687] Step 9:

[0688] Users can view the inventory rotation plan through the terminal and manually adjust it as needed, for example by changing the order in which new arrivals are placed after older stock.

[0689] Step 10:

[0690] The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. For example, it detects the facial expressions and voice tone when the user picks up a product.

[0691] Step 11:

[0692] The device sends the emotional data to a server, which then stores the collected data in a database and analyzes it.

[0693] Step 12:

[0694] The server uses the emotional data to predict the user's purchasing intent and the popularity of a product. For example, if the user is excited, the server will adjust the supply and demand forecast for that product upward.

[0695] Step 13:

[0696] The server uses the emotional data to optimize inventory replenishment and marketing strategies, for example, by identifying products that users find favorable and implementing promotions centered around those products.

[0697] Step 14:

[0698] The server continuously collects sales, inventory, and sentiment data and updates the system in real time, ensuring that the latest demand forecasts and inventory information are always available.

[0699] Step 15:

[0700] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[0701] This will improve the accuracy and efficiency of inventory management, and also improve customer satisfaction using an emotion engine.

[0702] Example 2

[0703] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0704] Current inventory management systems forecast demand and replenish inventory based on sales and inventory data, but they are unable to take user emotions or purchasing intentions into account. This makes it difficult to accurately forecast demand and appropriately replenish inventory, resulting in a high risk of stockouts and excess inventory. Furthermore, marketing strategies to improve the user experience are not adequately optimized. To solve these problems, there is a need for more accurate demand forecasts and an inventory management system that takes user emotions into account.

[0705] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting sales data, a means for collecting and updating current inventory information, a means for automatically replenishing inventory based on the collected and predicted data, a means for collecting and analyzing user emotion data, and a means for optimizing demand forecasting and marketing strategies based on the emotion data. This improves the accuracy of demand forecasting, reduces the risk of stockouts and excess inventory, and enables product suggestions and marketing strategies to be optimized based on user emotions.

[0706] "Sales data" refers to information such as the name of the product sold in a store or online system, the number of units sold, the date and time of sale, and the sales price.

[0707] "Demand forecasting" is the process of predicting future sales volumes and required inventory levels based on collected sales data.

[0708] "Inventory information" is data such as the quantity and expiration date of currently held products.

[0709] "Automatic inventory replenishment" refers to the automatic replenishment of inventory based on demand forecasts and current inventory information to prevent inventory shortages.

[0710] "Appropriate inventory rotation" means taking into account product expiration dates and managing the inventory so that older inventory is consumed first.

[0711] "Real-time monitoring" means continuously analyzing inventory status and sales information to instantly grasp the latest data.

[0712] "Emotion data" refers to information related to emotions collected from the user's facial expressions, tone of voice, movements, and the like.

[0713] An "emotion engine" is a technology or device that analyzes a user's facial expressions, voice, and movements to collect emotional data.

[0714] A "marketing strategy" is a strategic measure aimed at promoting product sales and improving customer satisfaction.

[0715] This invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. This system improves the accuracy and efficiency of inventory management through sales data collection, demand forecasting, inventory information management, automatic inventory replenishment, appropriate inventory rotation, real-time monitoring, and the use of emotion data.

[0716] Hardware and software used

[0717] 1. Terminal

[0718] Hardware: POS system, barcode scanner, camera, microphone

[0719] Software: Data collection software, facial expression recognition software (e.g., OpenCV), voice analysis software

[0720] 2. Server

[0721] Hardware: High-performance servers (e.g. cloud infrastructure)

[0722] Software: Database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., TensorFlow, PyTorch), visual tools (e.g., Grafana, PowerBI), sentiment analysis algorithms

[0723] Process Overview

[0724] 1. Collect sales data

[0725] The terminal collects sales data in real time from stores and online systems and sends it to a server. The collected sales data includes product name, number of units sold, date and time of sale, and sales price.

[0726] 2. Demand forecast

[0727] The server uses the accumulated sales data to train a generative AI model, which is then used to accurately forecast future demand, including past sales data and seasonality features.

[0728] 3. Inventory management

[0729] The terminal periodically collects current inventory information and sends it to the server, which uses this information to update the inventory database in real time.

[0730] 4. Automatic inventory replenishment

[0731] The server compares demand forecast data with current inventory information to calculate the amount of replenishment required, calculates the appropriate timing and quantity, and automatically sends orders to suppliers.

[0732] 5. Proper inventory rotation

[0733] The server uses expiration information in the inventory database to prioritize product consumption, implementing FIFO (first in, first out) logic to ensure that older inventory is sold first.

[0734] 6. Real-time monitoring

[0735] The server analyzes the continuously collected data and generates reports that are displayed on a dashboard, where users can access up-to-date inventory and sales data via their devices.

[0736] 7. Incorporating an Emotional Engine

[0737] The device's built-in camera and microphone are used to analyze the user's facial expressions, voice tone, and movements, and collect emotional data. This emotional data is sent to a server and used for various analyses.

[0738] 8. Utilizing Emotional Data

[0739] The server analyzes the collected emotional data to assess the user's purchasing intent and interest in specific products, thereby improving the accuracy of inventory replenishment and optimizing product recommendations and marketing strategies based on user emotions.

[0740] Specific examples

[0741] As an example of how the system works in a grocery store, a terminal collects daily sales data from the cash register system (e.g., milk, 100ml, sales date and time, price) and sends that data to a server. The server uses an AI model based on past sales data to predict next month's milk demand (e.g., predicting the amount of milk needed next month to be 200 liters). The terminal also collects daily inventory data (current inventory: 150 liters) and sends it to the server. The server automatically sends an order to the supplier to replenish the missing 50 liters.

[0742] The device also uses a camera and microphone to analyze the user's facial expressions and voice tone to collect emotional data. For example, when a user purchases milk, the device analyzes their facial expressions and voice tone to assess their willingness to purchase, and sends this data to a server. The server analyzes this emotional data to assess the product's popularity and purchasing intent, and then optimizes inventory replenishment and marketing strategies based on that data.

[0743] As a specific example, a prompt such as, "Based on sales data for milk at a grocery store, we would like to predict summer demand and automatically replenish it using an inventory management system. Please tell us the specific steps required and the points that we should consider." could be used.

[0744] The above is a specific embodiment of the present invention.

[0745] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0746] Step 1: Collect sales data

[0747] The terminal collects sales data in real time from stores and online systems. It takes in information from data sources such as POS systems and e-commerce platforms. Specifically, it collects information such as product name, number of units sold, date and time of sale, and sales price. The collected data is stored in JSON format and sent to the server. The input is sales data from each data source, and the output is formatted data sent to the server.

[0748] Step 2: Submit your sales data

[0749] The terminal periodically sends the collected sales data to the server. The HTTPS protocol is used to ensure security when sending data. Specifically, the terminal temporarily stores the collected data and then sends it to the server in batches after a certain period of time has passed. The input is formatted sales data, and the output is the sales data stored on the server.

[0750] Step 3: Save your sales data

[0751] The server saves the received sales data in a database. At this time, it uses a database management system (e.g., MySQL, PostgreSQL) to store the data accurately. The server inserts each data item into the corresponding table according to the data schema. The input is the sales data sent to the server, and the output is the sales data stored in the database.

[0752] Step 4: Training the AI ​​model

[0753] The server uses sales data stored in the database to train a generative AI model (e.g., TensorFlow, PyTorch). The model takes past sales data and features such as seasonal factors as input and outputs a demand forecasting model. Specifically, it runs the training dataset multiple times while optimizing the model's learning parameters. The input is sales data extracted from the database, and the output is a trained demand forecasting model.

[0754] Step 5: Demand forecasting

[0755] The server uses the trained demand forecasting model to predict future demand. Specifically, it makes numerical predictions of next month's sales volume and demand for specific products. The server inputs new sales data into the trained model and outputs the demand forecast results. The input is new sales data, and the output is the predicted product demand.

[0756] Step 6: Gather inventory information

[0757] The terminal periodically collects current inventory information (product name, quantity, expiration date, etc.) and sends that information to the server. Specific operations involve acquiring data using a barcode scanner or inventory management software. The input is the current inventory information, and the output is the inventory data sent to the server.

[0758] Step 7: Save inventory information

[0759] The server stores the received inventory data in a database. The server inserts the inventory data into the corresponding table and updates the database in real time. The input is the inventory data sent to the server, and the output is the inventory information stored in the database.

[0760] Step 8: Automatically replenish inventory

[0761] The server compares demand forecast data with current inventory information to calculate how much replenishment is required. The server calculates the shortage and automatically sends a replenishment order to the supplier. Specifically, it generates an order list and places an order with the supplier via API. The input is demand forecast data and inventory information, and the output is the order data sent to the supplier.

[0762] Step 9: Rotate your inventory appropriately

[0763] The server uses expiration date information in the inventory database to set product consumption priorities. It executes FIFO (first in, first out) logic and issues instructions to sell older stock first. Specifically, it creates a stock rotation plan for each product and sends it to the terminal. The input is inventory information, and the output is rotation instructions to the terminal.

[0764] Step 10: Real-time monitoring

[0765] The server continuously analyzes the collected data and generates reports that are displayed on a dashboard. Users can access up-to-date inventory and sales data using their devices. Specific operations involve using data analysis software to generate graphs and charts using visual tools (e.g., Grafana, PowerBI). The input is the data to be analyzed, and the output is a dashboard that users can access.

[0766] Step 11: Collect emotion data

[0767] Emotional data is collected by analyzing the user's facial expressions, voice tone, and movements using the device's built-in camera and microphone. For example, facial expression recognition software (e.g., OpenCV) is used to analyze the user's facial expressions while browsing products. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[0768] Step 12: Sending Emotion Data

[0769] The device sends the collected emotion data to the server. The HTTPS protocol is used for data transmission, ensuring secure transmission of emotion data. The input is the collected emotion data, and the output is the data sent to the server.

[0770] Step 13: Analyze the emotion data

[0771] The server analyzes the received emotional data and evaluates the user's purchasing intent and interest in the product. The server uses an emotion analysis algorithm to quantitatively evaluate the user's emotions. The input is the transmitted emotional data, and the output is the analysis result.

[0772] Step 14: Optimize your marketing strategy

[0773] The server uses the sentiment data to optimize inventory replenishment and marketing strategies. If there is high interest in a particular product, it will automatically implement measures such as increasing the stock of that product. The input is the analysis results, and the output is an optimized replenishment plan and marketing measures.

[0774] (Application example 2)

[0775] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0776] Current inventory management systems focus on forecasting demand and streamlining inventory replenishment based on sales data and inventory information, but they lack the ability to utilize customer sentiment data. This makes it difficult to understand customer purchasing intent and product popularity in real time and optimize marketing strategies and inventory management.

[0777] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for performing demand forecasting, means for collecting and updating inventory information, means for automatically replenishing inventory, means for managing inventory rotation and taking product expiration dates into consideration, means for monitoring inventory and sales information in real time, means for collecting and analyzing emotion data, and means for optimizing demand forecasting and inventory replenishment based on the emotion data. This enables demand forecasting and real-time inventory management that takes customer emotions into consideration.

[0778] 1. "Sales data" refers to purchase information such as product name, quantity sold, sales date and time, and sales price, and is information collected from stores and online systems.

[0779] 2. "Demand forecasting" is the process of predicting future product demand using AI models based on sales data and market trends.

[0780] 3. "Inventory information" is a general term for data required in an inventory management system, including information such as current inventory quantities, product expiration dates, and storage locations.

[0781] 4. "Automated inventory replenishment" is a system or process that automatically orders products from suppliers before they run out of stock, based on demand forecast data and current inventory information.

[0782] 5. "Inventory rotation" is an inventory management technique that takes into account product expiration dates and adjusts inventory so that older inventory is consumed first.

[0783] 6. "Real-time monitoring" is the process of immediately analyzing collected data to monitor real-time inventory status and sales information.

[0784] 7. "Emotional Data" refers to data used to understand a user's emotional state by analyzing information such as the user's facial expressions, tone of voice, and movements.

[0785] 8. "Sentiment analysis" is the process of using collected emotional data to analyze a user's emotional state and assess purchasing intent and product popularity.

[0786] 9. “Optimization” is the process of adjusting to maximize efficiency or effectiveness under given conditions, and in this case refers to using sentiment data to improve demand forecasting and inventory replenishment.

[0787] This invention combines an emotion recognition engine with an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[0788] The system consists of a terminal that collects sales data, a server that predicts demand based on that sales data, a terminal that collects and updates current inventory information, a server that automatically replenishes inventory based on the collected and predicted data, a server that manages appropriate inventory rotation and takes product expiration dates into account, a terminal that monitors inventory and sales information in real time, a terminal that collects and analyzes emotional data, and a server that optimizes demand prediction and inventory replenishment based on the emotional data.

[0789] Hardware and software used

[0790] 1. Smartphones and smart glasses:

[0791] Camera: Captures the user's facial expressions for emotion recognition.

[0792] Microphone: Records the user's voice for emotion recognition.

[0793] 2. Server:

[0794] Database: Used to store and manage sales and inventory data.

[0795] AI models: Use machine learning libraries (e.g., Scikit-learn) to perform demand forecasting and sentiment analysis.

[0796] 3. Software Libraries:

[0797] OpenCV: An image processing library for facial expression recognition.

[0798] Dlib: Facial landmark detection.

[0799] Scikit-learn: A machine learning library for demand forecasting and sentiment analysis.

[0800] Processing flow

[0801] Device data collection:

[0802] The camera and microphone installed in the smartphone or smart glasses are used to collect the user's facial expressions and voice, and this data is sent to a server in real time.

[0803] Sentiment analysis and purchase intent assessment:

[0804] Emotion data is analyzed using OpenCV and Dlib to understand the user's emotional state, and the AI ​​model then predicts their purchasing intent. For example, if a customer shows excitement in front of a particular product, it predicts increased demand for that product.

[0805] Inventory Management:

[0806] The server uses sales and inventory data to make demand forecasts. By adding the results of sentiment analysis to the demand forecast, it is possible to make demand forecasts that take into account product popularity and purchasing intentions.

[0807] Automatic inventory replenishment:

[0808] The server automatically replenishes goods based on demand forecasts and current inventory information. Specifically, it automatically orders products from suppliers based on demand forecast data before inventory runs out.

[0809] Real-time monitoring:

[0810] Users (store staff) can use smart devices to check inventory status and sales information in real time, which allows for immediate adjustments and promotional campaigns.

[0811] Specific examples

[0812] Milk inventory management:

[0813] Milk sales data is collected in real time and sent to a server. Based on past sales data and market trends, an AI model predicts next month's demand at 200 liters. Knowing that current stock is 150 liters, the AI ​​model automatically orders the missing 50 liters from the supplier. Furthermore, when a customer purchases milk, the smart glasses capture their facial expressions and analyze their excitement, prompting them to order more.

[0814] Prompt Sentence Examples

[0815] "Analyze the facial expressions and voices of users when they purchase milk and predict their purchasing intentions."

[0816] This will enable demand forecasting and inventory management that takes emotional data into account, improving accuracy and efficiency.

[0817] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0818] Step 1:

[0819] The device collects the user's facial expressions and voice in real time using the camera and microphone of a smartphone or smart glasses, and generates image and audio files as facial expression and voice data, which are then sent to a server.

[0820] Step 2:

[0821] The server analyzes the received facial expression and audio data. Specifically, it uses OpenCV and Dlib to extract facial landmarks from image files and perform emotion analysis. It also performs tone analysis on audio files to determine the user's emotional state. The input data are facial expression images and audio files, and the output data are labels indicating the emotional state (e.g., "happy," "sad," or "neutral").

[0822] Step 3:

[0823] The server stores the results of the emotion analysis in a database. Detailed emotion data is managed by storing the date and time, user ID, and product information together with the emotional state label. This allows for the accumulation of data necessary for future analysis.

[0824] Step 4:

[0825] The terminal collects sales data from the POS system. The sales data, which includes product name, quantity sold, date and time of sale, and sales price, is periodically sent to the server and received as input data. The output is a record of the updated sales data.

[0826] Step 5:

[0827] The server makes demand forecasts based on accumulated sales data. Past sales data and sentiment data are input into a generative AI model to predict future demand. The forecast results are output as the required quantity of each product for the next month.

[0828] Step 6:

[0829] The server collects current inventory information from the terminals and updates the database in real time. Data including stock quantity, product expiration date, storage location, etc. is input, and the latest inventory status is output.

[0830] Step 7:

[0831] The server compares demand forecast data with current inventory information and automatically replenishes items that are out of stock. It calculates the necessary replenishment amount and the optimal order timing, and automatically sends orders to suppliers. The input data is the demand forecast results and inventory information, and the output data is order details.

[0832] Step 8:

[0833] The server manages the appropriate rotation of inventory. Taking into account the expiration date of the inventory, it adjusts the inventory so that the inventory received first is consumed first. This minimizes product waste. The input data is the expiration date information of the inventory, and the output data is the rotation instruction.

[0834] Step 9:

[0835] Users can monitor inventory status and sales information in real time using a terminal, allowing them to immediately grasp sales trends and inventory status. Input data is current inventory and sales information, and output data is a real-time report of these.

[0836] Step 10:

[0837] The server optimizes marketing strategies based on emotion data. Specifically, it stocks more inventory of products that evoke specific emotions and implements promotions that evoke those emotions. The input data is the emotion analysis results, and the output data is an optimized marketing plan.

[0838] These steps will enable demand forecasting and inventory management that takes emotion data into account, improving the accuracy and efficiency of inventory management.

[0839] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0840] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0841] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0842] [Third embodiment]

[0843] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0844] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0845] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0846] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0847] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0848] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0849] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0850] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0851] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0852] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0853] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0854] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0855] The present invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[0856] ---

[0857] The system has the following components:

[0858] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. Sales data includes product names, quantities sold, sales dates and times, sales prices, etc.

[0859] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[0860] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[0861] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[0862] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[0863] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[0864] ---

[0865] Specific examples

[0866] As a concrete example, the operation of the system in a grocery store will be described.

[0867] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[0868] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[0869] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[0870] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[0871] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[0872] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[0873] This improves the accuracy and efficiency of inventory management, reduces resource waste, and increases customer satisfaction.

[0874] The processing flow will be explained below.

[0875] Step 1:

[0876] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[0877] Step 2:

[0878] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[0879] Step 3:

[0880] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[0881] Step 4:

[0882] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[0883] Step 5:

[0884] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[0885] Step 6:

[0886] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[0887] Step 7:

[0888] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[0889] Step 8:

[0890] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[0891] Step 9:

[0892] Users can view the inventory rotation plan through the terminal and manually adjust it if necessary, for example by changing the order in which new arrivals are placed after older stock.

[0893] Step 10:

[0894] The server continuously collects sales and inventory data and updates the system in real time, allowing you to constantly monitor the latest inventory status and sales trends.

[0895] Step 11:

[0896] The server periodically retrains the demand forecasting model based on new data collected, thereby maintaining and further improving the accuracy of the forecasts.

[0897] Step 12:

[0898] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[0899] Through the above processing steps, the system of the present invention can improve the efficiency and accuracy of inventory management, minimize a company's inventory risk, and increase customer satisfaction.

[0900] Example 1

[0901] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0902] With conventional inventory management systems, sales data collection, demand forecasting, and automatic inventory replenishment are often carried out separately, making integrated management difficult. Furthermore, there are issues with overstocking and shortages due to a lack of forecast accuracy and inappropriate replenishment timing. There is also the problem of increased waste due to management methods that ignore product expiration dates.

[0903] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0904] In this invention, the server includes a means for collecting sales data, a means for forecasting demand based on the sales data, and a means for collecting and updating current inventory information. This allows for integrated management of sales data and inventory information, enabling highly accurate demand forecasting and appropriate inventory replenishment.

[0905] "Sales data" refers to information related to sales, such as product name, number of units sold, sales date and time, and sales price.

[0906] "Demand forecasting" is a method of estimating future demand based on past sales data.

[0907] "Inventory information" refers to detailed inventory data such as product quantity, expiration date, and current stock status.

[0908] "Automatic replenishment" is a method of automatically replenishing inventory before it runs out, based on forecast data and current inventory information.

[0909] "Rotation" is a management method that manages the expiration date of inventory and prioritizes the release of products that were received first.

[0910] "Real-time monitoring" is a method of continuously analyzing data to instantly grasp current inventory status and sales information.

[0911] A "barcode reader" is a device that reads barcodes attached to products.

[0912] "RFID" is a technology that uses wireless communication to read and write information about items.

[0913] An "AI model" is an algorithm that uses machine learning technology to analyze large amounts of data and make predictions and classifications.

[0914] "Supplier" refers to a trader or company that supplies goods.

[0915] This invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. This system is mainly composed of three elements: a server, a terminal, and a user.

[0916] Hardware and software used

[0917] Server: Used for data collection, analysis, prediction, and instruction. The server has machine learning libraries such as TensorFlow and PyTorch and database management systems such as MySQL and PostgreSQL installed.

[0918] Terminals: Used to collect and transmit data. These include barcode readers, RFID devices, and point-of-sale systems.

[0919] User devices: Used to check real-time inventory information. Web dashboard and mobile app installed.

[0920] System processing flow

[0921] 1. Collect sales data:

[0922] The terminal collects sales data such as product name, sales quantity, sales date and time, and sales price through a POS system or online system. The collected data is sent to the server in JSON format.

[0923] 2. Demand forecasting:

[0924] The server stores the received sales data in a database. Next, it uses TensorFlow and PyTorch to train an AI model based on past sales data. This trained model is then used to predict future demand.

[0925] 3. Inventory Management:

[0926] The terminal uses a barcode reader or RFID to collect current inventory information, including product quantities and expiration dates, and sends the collected data to a server, which then updates the database in real time.

[0927] 4. Automatic inventory replenishment:

[0928] The server compares the demand forecast data with current inventory information. If there is a shortage of inventory, the server automatically sends an order to the supplier. The order is placed via API.

[0929] 5. Proper inventory rotation:

[0930] The server manages the expiration dates of inventory and prioritizes the delivery of older inventory, thereby minimizing waste.

[0931] 6. Real-time monitoring:

[0932] Users can check inventory status in real time via a web dashboard or mobile app, allowing them to quickly make any necessary adjustments.

[0933] Specific examples

[0934] As a concrete example, the operation of the system in a grocery store will be described.

[0935] 1. Collect sales data:

[0936] The terminal transmits daily sales data (e.g., milk, 100ml, sales date and time, price) collected from the cash register system to the server in real time.

[0937] 2. Demand forecasting:

[0938] The server trains an AI model using TensorFlow based on past sales data. For example, it uses data showing that milk sales increase in the summer to predict demand for 200 liters next month.

[0939] 3. Inventory Management:

[0940] Every day, the terminal uses a barcode reader to collect inventory data and send it to the server, including information such as the current inventory level being 150 liters.

[0941] 4. Automatic inventory replenishment:

[0942] The server compares the demand forecast results with the current inventory and automatically sends an order to the supplier to replenish the missing 50 liters.

[0943] 5. Proper inventory rotation:

[0944] The server manages the expiration date information of milk and prevents it from being discarded after expiration by implementing a first-in, first-out (FIFO) system.

[0945] 6. Real-time monitoring:

[0946] Users can use the mobile app to check milk inventory and sales in real time, allowing them to make additional adjustments or implement promotional campaigns on the fly.

[0947] Prompt Sentence Examples

[0948] "Please outline a program that uses an inventory control system to forecast milk demand and automatically replenish it appropriately."

[0949] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0950] Step 1: Collect sales data

[0951] The terminal collects sales data in real time from stores and online systems. Specifically, it uses a POS system or web application to obtain information such as product name, number of units sold, sales date and time, and sales price. This collected data is sent to the server in JSON format. The input data is sales information, and the output data is the sales data sent to the server.

[0952] Step 2: Demand forecast

[0953] The server stores the received sales data in a database. Next, it uses TensorFlow to train an AI model. The input data used for training is past sales data, and the model is used to predict future demand. The output data is the predicted demand figure. For example, based on past data, it predicts that next month's demand for milk will be 200 liters.

[0954] Step 3: Manage inventory information

[0955] The terminal collects inventory information using a barcode reader or RFID. The collected inventory information includes product quantities, expiration dates, etc., and is sent to the server in JSON format. The input data is the inventory information obtained from the barcode reader or RFID, and the output data is the latest inventory information sent to the server. For example, the server will know that the current amount of milk in stock is 150 liters.

[0956] Step 4: Automatically replenish inventory

[0957] The server compares demand forecast data with current inventory information and analyzes it. The input data is the demand forecast value and current inventory information, and as a result of the analysis, it generates order data to make up for any shortages in inventory. For example, if the forecast demand is 200 liters and the current inventory is 150 liters, the server will order the missing 50 liters from the supplier. This order is placed automatically via API.

[0958] Step 5: Rotate your inventory appropriately

[0959] The server manages inventory expiration date information and adjusts the order so that older inventory is shipped first. The input data is inventory expiration date information, and generates the rotation data required to adjust the shipping order. The output data is the adjusted shipping order information. For example, a first-in, first-out (FIFO) order is implemented using an inventory management script.

[0960] Step 6: Real-time monitoring

[0961] The server continuously analyzes data collected from the devices and monitors inventory status in real time. The input data is sales and inventory information sent from the devices, and the server outputs analyzed inventory status data. Users can access this analysis data and check inventory information in real time via a web dashboard or mobile app. For example, users can instantly check milk inventory levels and sales and make any necessary adjustments or promotional activities.

[0962] (Application example 1)

[0963] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0964] Conventional inventory management systems are prone to inventory shortages and excess inventory, making inventory management, particularly in logistics warehouses, time-consuming and labor-intensive. In addition, inaccurate demand forecasts make it difficult to create accurate inventory plans, resulting in lower customer satisfaction and increased management costs. Furthermore, inventory replenishment work is often done manually, resulting in inefficiency. The present invention aims to solve these problems and achieve efficient and accurate inventory management.

[0965] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0966] In this invention, the server includes a means for collecting sales data, a means for forecasting demand, a means for collecting and updating inventory information, a means for automatically replenishing inventory based on the collected and forecasted data, a means for managing appropriate inventory rotation, a means for monitoring inventory and sales information in real time, and a means for automatically replenishing inventory in the logistics warehouse using a robot. This enables efficient inventory management, accurate demand forecasting, and reduced labor through automatic replenishment.

[0967] Definitions of important words

[0968] "Sales data" is information indicating the sales status of a product, and includes details such as the number of units sold, the date and time of sale, the product name, and the sales price.

[0969] "Demand forecasting" is the process of estimating future sales volumes based on past sales data and market trends.

[0970] "Inventory information" is information indicating the quantity and expiration date of products held in a warehouse or store.

[0971] "Auto-replenish" means that the system automatically places an order for more stock before it runs out.

[0972] "Rotation" refers to managing products so that they are consumed in a specific order, and is often used to refer to first-in, first-out (FIFO).

[0973] "Real-time monitoring" means instantly understanding current inventory status and sales information.

[0974] A "robot" is a mechanical device that automatically replenishes inventory in a logistics warehouse according to programmed instructions.

[0975] An "AI model" is a mathematical algorithm or machine learning model that uses artificial intelligence to extract insights from data and make predictions and classifications.

[0976] A "sensor" is a device that detects physical phenomena and converts them into data. Examples include cameras and pressure sensors.

[0977] "Form for carrying out the invention" of the specification

[0978] The present invention is an automatic inventory replenishment system that uses AI to achieve efficient inventory management in logistics centers. This system uses specific hardware and software to collect sales data, forecast demand, manage inventory information, automatically replenish inventory, rotate inventory, and perform real-time monitoring. Specific embodiments for implementing the present invention are described below.

[0979] Hardware Configuration

[0980] The system includes the following hardware:

[0981] 1. Sensors: Detect the amount of inventory on shelves or in warehouses. For example, cameras and pressure sensors are used.

[0982] 2. Robot: A mechanical device that replenishes inventory in a distribution warehouse according to programmed instructions.

[0983] 3. Terminal: A device used for data collection and for administrators to check information in real time. Examples include smartphones and tablets.

[0984] 4. Server: A central device for aggregating data, analyzing it, and running AI models.

[0985] Software Configuration

[0986] The system includes the following software:

[0987] 1. Sales data collection program: Collects data from sensors in real time and sends it to the server.

[0988] 2. AI models: Built using machine learning libraries such as TensorFlow and PyTorch to perform demand forecasting.

[0989] 3. Inventory management program: Collects, updates, and manages inventory data and manages expiration date information.

[0990] 4. Automatic replenishment program: Based on demand forecasts and inventory information, calculates the required inventory level and sends replenishment instructions to the robot.

[0991] 5. Real-time monitoring interface: An application that monitors inventory status and sales information on a smartphone or tablet.

[0992] Processing flow

[0993] The server first receives sales data sent from sensors and terminals. It then trains an AI model based on the collected sales data to make demand forecasts. This forecast takes market trends and seasonal fluctuations into account. The server also collects current inventory information and updates the database in real time. It compares the forecast results with the inventory information, and if there is a shortage of inventory, it automatically calculates the required inventory amount and sends a replenishment instruction to the robot. The robot replenishes the inventory based on the calculated amount. The server also manages inventory expiration dates and maintains appropriate stock rotation. Users can use their terminals to check inventory status and sales information in real time.

[0994] Specific examples

[0995] As a concrete example, consider the case of managing milk inventory in a distribution warehouse. A sensor detects milk inventory and sends the current inventory amount to a server. Based on past sales data, an AI model predicts the demand for milk for next month. For example, let's say that based on past data, the amount of milk needed next month is predicted to be 200 liters. If the current inventory is 150 liters, a robot automatically picks up an additional 50 liters from the warehouse to replenish the missing 50 liters.

[0996] Prompt Sentence Examples

[0997] "Please predict next month's demand based on the following historical sales data:

[0998] Product Name: Dairy Products

[0999] Monthly sales for the past year (liters):

[1000] January: 200, February: 180, March: 250, April: 300, May: 280, June: 350, July: 400, August: 350, September: 320, October: 300, November: 250, December: 220

[1001] Anticipate future demand.

[1002] As a result, a system that can achieve efficient and accurate inventory management is constructed.

[1003] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1004] Processing steps of the system program that realizes the application example

[1005] Step 1:

[1006] Sensors and terminals monitor inventory on shelves and in warehouses in real time and collect inventory information.

[1007] Input: Shelf inventory status (product name, quantity, expiration date, etc.)

[1008] Processing: Collect inventory data from sensors (cameras and pressure sensors) and convert it into JSON format data.

[1009] Output: Inventory data in JSON format

[1010] Step 2:

[1011] The server receives the inventory data sent from the terminal and stores it in a database.

[1012] Input: Inventory data in JSON format

[1013] Processing: Store the received data in the database and update the current inventory information.

[1014] Output: Updated inventory database

[1015] Step 3:

[1016] The server collects sales data and creates a dataset to be input into the AI ​​model.

[1017] Input: Past sales data (product name, number of units sold, sales date and time, sales price, etc.)

[1018] Processing: Organizing and consolidating each sales data to generate a dataset suitable for the AI ​​model.

[1019] Output: Dataset for AI model

[1020] Step 4:

[1021] The server uses an AI model to make demand forecasts.

[1022] Input: Dataset for AI model

[1023] Processing: Run trained AI models using TensorFlow and PyTorch to predict future demand.

[1024] Output: Forecasted demand data

[1025] Step 5:

[1026] The server compares the forecast results with current inventory information and calculates the amount of inventory that is lacking.

[1027] Inputs: Forecasted demand data, current inventory data

[1028] Processing: Calculate the missing inventory by subtracting the current inventory from the forecasted demand.

[1029] Output: Data on shortage quantity

[1030] Step 6:

[1031] The server sends an automatic replenishment instruction to the robot.

[1032] Input: Data on the shortage amount

[1033] Processing: Generates and sends replenishment instructions to the robot, specifically instructions to retrieve the items the robot needs from the warehouse and replenish them.

[1034] Output: Replenishment instructions (instructions to the robot)

[1035] Step 7:

[1036] The robot follows replenishment instructions, retrieves products from the warehouse, and replenishes them on the designated shelves.

[1037] Input: Replenishment instructions

[1038] Processing: The robot moves, picks up the specified product, and places it appropriately on the specified shelf.

[1039] Output: Notification of replenishment completion

[1040] Step 8:

[1041] The server receives the report of the completion of stock replenishment and updates the database.

[1042] Input: Replenishment completion notification

[1043] Action: Update the database as available stock and check the real-time stock status again.

[1044] Output: Updated database, real-time inventory status

[1045] Step 9:

[1046] The terminal can monitor the latest inventory status and sales information in real time.

[1047] Input: Updated database

[1048] Processing: Retrieves the latest inventory and sales information from the database and provides an interface that allows users to visually check it.

[1049] Output: Inventory status and sales information display interface

[1050] Step 10:

[1051] The user uses the terminal to check inventory status and sales information, and issues additional replenishment instructions or implements sales promotion campaigns as necessary.

[1052] Input: Inventory status and sales information

[1053] Action: View information through the interface and plan replenishment and promotional campaigns. For example, alerts for low-stock items and planning campaigns to balance supply and demand.

[1054] Output: User decision support

[1055] Through the above processing steps, the system of the present invention realizes efficient and practical inventory management and automatic replenishment.

[1056] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1057] The present invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1058] ---

[1059] The system has the following components:

[1060] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. The sales data includes product name, number of units sold, date and time of sale, sales price, etc.

[1061] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[1062] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[1063] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[1064] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[1065] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[1066] 7. Emotion engine: The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. This emotional data is sent to the server and used for inventory management and product recommendations.

[1067] 8. Utilizing Emotional Data: The server can use emotional data to predict user purchasing intent and product popularity, providing additional data for optimizing inventory replenishment and marketing strategies.

[1068] ---

[1069] Specific examples

[1070] As a concrete example, the operation of the system in a grocery store will be described.

[1071] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[1072] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[1073] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[1074] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[1075] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[1076] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[1077] 7. Use of emotion engine: Using the camera and microphone on the device, the system analyzes the user's facial expressions and voice to collect emotional data. For example, analyzing the user's facial expressions and voice tone when purchasing milk can be used to assess the user's willingness to purchase.

[1078] 8. Utilizing Emotional Data: The server analyzes the collected emotional data to assess user interest in specific products. For example, if users express excitement about a product, the server can stock more of that product. It can also adjust marketing efforts and implement promotions that evoke specific emotions.

[1079] This will further improve the accuracy and efficiency of inventory management, and will also improve customer satisfaction based on user emotions.

[1080] The processing flow will be explained below.

[1081] Step 1:

[1082] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[1083] Step 2:

[1084] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[1085] Step 3:

[1086] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[1087] Step 4:

[1088] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[1089] Step 5:

[1090] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[1091] Step 6:

[1092] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[1093] Step 7:

[1094] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[1095] Step 8:

[1096] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[1097] Step 9:

[1098] Users can view the inventory rotation plan through the terminal and manually adjust it as needed, for example by changing the order in which new arrivals are placed after older stock.

[1099] Step 10:

[1100] The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. For example, it detects the facial expressions and voice tone when the user picks up a product.

[1101] Step 11:

[1102] The device sends the emotional data to a server, which then stores the collected data in a database and analyzes it.

[1103] Step 12:

[1104] The server uses the emotional data to predict the user's purchasing intent and the popularity of a product. For example, if the user is excited, the server will adjust the supply and demand forecast for that product upward.

[1105] Step 13:

[1106] The server uses the emotional data to optimize inventory replenishment and marketing strategies, for example, by identifying products that users find favorable and implementing promotions centered around those products.

[1107] Step 14:

[1108] The server continuously collects sales, inventory, and sentiment data and updates the system in real time, ensuring that the latest demand forecasts and inventory information are always available.

[1109] Step 15:

[1110] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[1111] This will improve the accuracy and efficiency of inventory management, and also improve customer satisfaction using an emotion engine.

[1112] Example 2

[1113] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1114] Current inventory management systems forecast demand and replenish inventory based on sales and inventory data, but they are unable to take user emotions or purchasing intentions into account. This makes it difficult to accurately forecast demand and appropriately replenish inventory, resulting in a high risk of stockouts and excess inventory. Furthermore, marketing strategies to improve the user experience are not adequately optimized. To solve these problems, there is a need for more accurate demand forecasts and an inventory management system that takes user emotions into account.

[1115] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting sales data, a means for collecting and updating current inventory information, a means for automatically replenishing inventory based on the collected and predicted data, a means for collecting and analyzing user emotion data, and a means for optimizing demand forecasting and marketing strategies based on the emotion data. This improves the accuracy of demand forecasting, reduces the risk of stockouts and excess inventory, and enables product suggestions and marketing strategies to be optimized based on user emotions.

[1116] "Sales data" refers to information such as the name of the product sold in a store or online system, the number of units sold, the date and time of sale, and the sales price.

[1117] "Demand forecasting" is the process of predicting future sales volumes and required inventory levels based on collected sales data.

[1118] "Inventory information" is data such as the quantity and expiration date of currently held products.

[1119] "Automatic inventory replenishment" refers to the automatic replenishment of inventory based on demand forecasts and current inventory information to prevent inventory shortages.

[1120] "Appropriate inventory rotation" means taking into account product expiration dates and managing the inventory so that older inventory is consumed first.

[1121] "Real-time monitoring" means continuously analyzing inventory status and sales information to instantly grasp the latest data.

[1122] "Emotion data" refers to information related to emotions collected from the user's facial expressions, tone of voice, movements, and the like.

[1123] An "emotion engine" is a technology or device that analyzes a user's facial expressions, voice, and movements to collect emotional data.

[1124] A "marketing strategy" is a strategic measure aimed at promoting product sales and improving customer satisfaction.

[1125] This invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. This system improves the accuracy and efficiency of inventory management through sales data collection, demand forecasting, inventory information management, automatic inventory replenishment, appropriate inventory rotation, real-time monitoring, and the use of emotion data.

[1126] Hardware and software used

[1127] 1. Terminal

[1128] Hardware: POS system, barcode scanner, camera, microphone

[1129] Software: Data collection software, facial expression recognition software (e.g., OpenCV), voice analysis software

[1130] 2. Server

[1131] Hardware: High-performance servers (e.g. cloud infrastructure)

[1132] Software: Database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., TensorFlow, PyTorch), visual tools (e.g., Grafana, PowerBI), sentiment analysis algorithms

[1133] Process Overview

[1134] 1. Collect sales data

[1135] The terminal collects sales data in real time from stores and online systems and sends it to a server. The collected sales data includes product name, number of units sold, date and time of sale, and sales price.

[1136] 2. Demand forecast

[1137] The server uses the accumulated sales data to train a generative AI model, which is then used to accurately forecast future demand, including past sales data and seasonality features.

[1138] 3. Inventory management

[1139] The terminal periodically collects current inventory information and sends it to the server, which uses this information to update the inventory database in real time.

[1140] 4. Automatic inventory replenishment

[1141] The server compares demand forecast data with current inventory information to calculate the amount of replenishment required, calculates the appropriate timing and quantity, and automatically sends orders to suppliers.

[1142] 5. Proper inventory rotation

[1143] The server uses expiration information in the inventory database to prioritize product consumption, implementing FIFO (first in, first out) logic to ensure that older inventory is sold first.

[1144] 6. Real-time monitoring

[1145] The server analyzes the continuously collected data and generates reports that are displayed on a dashboard, where users can access up-to-date inventory and sales data via their devices.

[1146] 7. Incorporating an Emotional Engine

[1147] The device's built-in camera and microphone are used to analyze the user's facial expressions, voice tone, and movements, and collect emotional data. This emotional data is sent to a server and used for various analyses.

[1148] 8. Utilizing Emotional Data

[1149] The server analyzes the collected emotional data to assess the user's purchasing intent and interest in specific products, thereby improving the accuracy of inventory replenishment and optimizing product recommendations and marketing strategies based on user emotions.

[1150] Specific examples

[1151] As an example of how the system works in a grocery store, a terminal collects daily sales data from the cash register system (e.g., milk, 100ml, sales date and time, price) and sends that data to a server. The server uses an AI model based on past sales data to predict next month's milk demand (e.g., predicting the amount of milk needed next month to be 200 liters). The terminal also collects daily inventory data (current inventory: 150 liters) and sends it to the server. The server automatically sends an order to the supplier to replenish the missing 50 liters.

[1152] The device also uses a camera and microphone to analyze the user's facial expressions and voice tone to collect emotional data. For example, when a user purchases milk, the device analyzes their facial expressions and voice tone to assess their willingness to purchase, and sends this data to a server. The server analyzes this emotional data to assess the product's popularity and purchasing intent, and then optimizes inventory replenishment and marketing strategies based on that data.

[1153] As a specific example, a prompt such as, "Based on sales data for milk at a grocery store, we would like to predict summer demand and automatically replenish it using an inventory management system. Please tell us the specific steps required and the points that we should consider." could be used.

[1154] The above is a specific embodiment of the present invention.

[1155] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1156] Step 1: Collect sales data

[1157] The terminal collects sales data in real time from stores and online systems. It takes in information from data sources such as POS systems and e-commerce platforms. Specifically, it collects information such as product name, number of units sold, date and time of sale, and sales price. The collected data is stored in JSON format and sent to the server. The input is sales data from each data source, and the output is formatted data sent to the server.

[1158] Step 2: Submit your sales data

[1159] The terminal periodically sends the collected sales data to the server. The HTTPS protocol is used to ensure security when sending data. Specifically, the terminal temporarily stores the collected data and then sends it to the server in batches after a certain period of time has passed. The input is formatted sales data, and the output is the sales data stored on the server.

[1160] Step 3: Save your sales data

[1161] The server saves the received sales data in a database. At this time, it uses a database management system (e.g., MySQL, PostgreSQL) to store the data accurately. The server inserts each data item into the corresponding table according to the data schema. The input is the sales data sent to the server, and the output is the sales data stored in the database.

[1162] Step 4: Training the AI ​​model

[1163] The server uses sales data stored in the database to train a generative AI model (e.g., TensorFlow, PyTorch). The model takes past sales data and features such as seasonal factors as input and outputs a demand forecasting model. Specifically, it runs the training dataset multiple times while optimizing the model's learning parameters. The input is sales data extracted from the database, and the output is a trained demand forecasting model.

[1164] Step 5: Demand forecasting

[1165] The server uses the trained demand forecasting model to predict future demand. Specifically, it makes numerical predictions of next month's sales volume and demand for specific products. The server inputs new sales data into the trained model and outputs the demand forecast results. The input is new sales data, and the output is the predicted product demand.

[1166] Step 6: Gather inventory information

[1167] The terminal periodically collects current inventory information (product name, quantity, expiration date, etc.) and sends that information to the server. Specific operations involve acquiring data using a barcode scanner or inventory management software. The input is the current inventory information, and the output is the inventory data sent to the server.

[1168] Step 7: Save inventory information

[1169] The server stores the received inventory data in a database. The server inserts the inventory data into the corresponding table and updates the database in real time. The input is the inventory data sent to the server, and the output is the inventory information stored in the database.

[1170] Step 8: Automatically replenish inventory

[1171] The server compares demand forecast data with current inventory information to calculate how much replenishment is required. The server calculates the shortage and automatically sends a replenishment order to the supplier. Specifically, it generates an order list and places an order with the supplier via API. The input is demand forecast data and inventory information, and the output is the order data sent to the supplier.

[1172] Step 9: Rotate your inventory appropriately

[1173] The server uses expiration date information in the inventory database to set product consumption priorities. It executes FIFO (first in, first out) logic and issues instructions to sell older stock first. Specifically, it creates a stock rotation plan for each product and sends it to the terminal. The input is inventory information, and the output is rotation instructions to the terminal.

[1174] Step 10: Real-time monitoring

[1175] The server continuously analyzes the collected data and generates reports that are displayed on a dashboard. Users can access up-to-date inventory and sales data using their devices. Specific operations involve using data analysis software to generate graphs and charts using visual tools (e.g., Grafana, PowerBI). The input is the data to be analyzed, and the output is a dashboard that users can access.

[1176] Step 11: Collect emotion data

[1177] Emotional data is collected by analyzing the user's facial expressions, voice tone, and movements using the device's built-in camera and microphone. For example, facial expression recognition software (e.g., OpenCV) is used to analyze the user's facial expressions while browsing products. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[1178] Step 12: Sending Emotion Data

[1179] The device sends the collected emotion data to the server. The HTTPS protocol is used for data transmission, ensuring secure transmission of emotion data. The input is the collected emotion data, and the output is the data sent to the server.

[1180] Step 13: Analyze the emotion data

[1181] The server analyzes the received emotional data and evaluates the user's purchasing intent and interest in the product. The server uses an emotion analysis algorithm to quantitatively evaluate the user's emotions. The input is the transmitted emotional data, and the output is the analysis result.

[1182] Step 14: Optimize your marketing strategy

[1183] The server uses the sentiment data to optimize inventory replenishment and marketing strategies. If there is high interest in a particular product, it will automatically implement measures such as increasing the stock of that product. The input is the analysis results, and the output is an optimized replenishment plan and marketing measures.

[1184] (Application example 2)

[1185] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1186] Current inventory management systems focus on forecasting demand and streamlining inventory replenishment based on sales data and inventory information, but they lack the ability to utilize customer sentiment data. This makes it difficult to understand customer purchasing intent and product popularity in real time and optimize marketing strategies and inventory management.

[1187] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for performing demand forecasting, means for collecting and updating inventory information, means for automatically replenishing inventory, means for managing inventory rotation and taking product expiration dates into consideration, means for monitoring inventory and sales information in real time, means for collecting and analyzing emotion data, and means for optimizing demand forecasting and inventory replenishment based on the emotion data. This enables demand forecasting and real-time inventory management that takes customer emotions into consideration.

[1188] 1. "Sales data" refers to purchase information such as product name, quantity sold, sales date and time, and sales price, and is information collected from stores and online systems.

[1189] 2. "Demand forecasting" is the process of predicting future product demand using AI models based on sales data and market trends.

[1190] 3. "Inventory information" is a general term for data required in an inventory management system, including information such as current inventory quantities, product expiration dates, and storage locations.

[1191] 4. "Automated inventory replenishment" is a system or process that automatically orders products from suppliers before they run out of stock, based on demand forecast data and current inventory information.

[1192] 5. "Inventory rotation" is an inventory management technique that takes into account product expiration dates and adjusts inventory so that older inventory is consumed first.

[1193] 6. "Real-time monitoring" is the process of immediately analyzing collected data to monitor real-time inventory status and sales information.

[1194] 7. "Emotional Data" refers to data used to understand a user's emotional state by analyzing information such as the user's facial expressions, tone of voice, and movements.

[1195] 8. "Sentiment analysis" is the process of using collected emotional data to analyze a user's emotional state and assess purchasing intent and product popularity.

[1196] 9. “Optimization” is the process of adjusting to maximize efficiency or effectiveness under given conditions, and in this case refers to using sentiment data to improve demand forecasting and inventory replenishment.

[1197] This invention combines an emotion recognition engine with an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[1198] The system consists of a terminal that collects sales data, a server that predicts demand based on that sales data, a terminal that collects and updates current inventory information, a server that automatically replenishes inventory based on the collected and predicted data, a server that manages appropriate inventory rotation and takes product expiration dates into account, a terminal that monitors inventory and sales information in real time, a terminal that collects and analyzes emotional data, and a server that optimizes demand prediction and inventory replenishment based on the emotional data.

[1199] Hardware and software used

[1200] 1. Smartphones and smart glasses:

[1201] Camera: Captures the user's facial expressions for emotion recognition.

[1202] Microphone: Records the user's voice for emotion recognition.

[1203] 2. Server:

[1204] Database: Used to store and manage sales and inventory data.

[1205] AI models: Use machine learning libraries (e.g., Scikit-learn) to perform demand forecasting and sentiment analysis.

[1206] 3. Software Libraries:

[1207] OpenCV: An image processing library for facial expression recognition.

[1208] Dlib: Facial landmark detection.

[1209] Scikit-learn: A machine learning library for demand forecasting and sentiment analysis.

[1210] Processing flow

[1211] Device data collection:

[1212] The camera and microphone installed in the smartphone or smart glasses are used to collect the user's facial expressions and voice, and this data is sent to a server in real time.

[1213] Sentiment analysis and purchase intent assessment:

[1214] Emotion data is analyzed using OpenCV and Dlib to understand the user's emotional state, and the AI ​​model then predicts their purchasing intent. For example, if a customer shows excitement in front of a particular product, it predicts increased demand for that product.

[1215] Inventory Management:

[1216] The server uses sales and inventory data to make demand forecasts. By adding the results of sentiment analysis to the demand forecast, it is possible to make demand forecasts that take into account product popularity and purchasing intentions.

[1217] Automatic inventory replenishment:

[1218] The server automatically replenishes goods based on demand forecasts and current inventory information. Specifically, it automatically orders products from suppliers based on demand forecast data before inventory runs out.

[1219] Real-time monitoring:

[1220] Users (store staff) can use smart devices to check inventory status and sales information in real time, which allows for immediate adjustments and promotional campaigns.

[1221] Specific examples

[1222] Milk inventory management:

[1223] Milk sales data is collected in real time and sent to a server. Based on past sales data and market trends, an AI model predicts next month's demand at 200 liters. Knowing that current stock is 150 liters, the AI ​​model automatically orders the missing 50 liters from the supplier. Furthermore, when a customer purchases milk, the smart glasses capture their facial expressions and analyze their excitement, prompting them to order more.

[1224] Prompt Sentence Examples

[1225] "Analyze the facial expressions and voices of users when they purchase milk and predict their purchasing intentions."

[1226] This will enable demand forecasting and inventory management that takes emotional data into account, improving accuracy and efficiency.

[1227] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1228] Step 1:

[1229] The device collects the user's facial expressions and voice in real time using the camera and microphone of a smartphone or smart glasses, and generates image and audio files as facial expression and voice data, which are then sent to a server.

[1230] Step 2:

[1231] The server analyzes the received facial expression and audio data. Specifically, it uses OpenCV and Dlib to extract facial landmarks from image files and perform emotion analysis. It also performs tone analysis on audio files to determine the user's emotional state. The input data are facial expression images and audio files, and the output data are labels indicating the emotional state (e.g., "happy," "sad," or "neutral").

[1232] Step 3:

[1233] The server stores the results of the emotion analysis in a database. Detailed emotion data is managed by storing the date and time, user ID, and product information together with the emotional state label. This allows for the accumulation of data necessary for future analysis.

[1234] Step 4:

[1235] The terminal collects sales data from the POS system. The sales data, which includes product name, quantity sold, date and time of sale, and sales price, is periodically sent to the server and received as input data. The output is a record of the updated sales data.

[1236] Step 5:

[1237] The server makes demand forecasts based on accumulated sales data. Past sales data and sentiment data are input into a generative AI model to predict future demand. The forecast results are output as the required quantity of each product for the next month.

[1238] Step 6:

[1239] The server collects current inventory information from the terminals and updates the database in real time. Data including stock quantity, product expiration date, storage location, etc. is input, and the latest inventory status is output.

[1240] Step 7:

[1241] The server compares demand forecast data with current inventory information and automatically replenishes items that are out of stock. It calculates the necessary replenishment amount and the optimal order timing, and automatically sends orders to suppliers. The input data is the demand forecast results and inventory information, and the output data is order details.

[1242] Step 8:

[1243] The server manages the appropriate rotation of inventory. Taking into account the expiration date of the inventory, it adjusts the inventory so that the inventory received first is consumed first. This minimizes product waste. The input data is the expiration date information of the inventory, and the output data is the rotation instruction.

[1244] Step 9:

[1245] Users can monitor inventory status and sales information in real time using a terminal, allowing them to immediately grasp sales trends and inventory status. Input data is current inventory and sales information, and output data is a real-time report of these.

[1246] Step 10:

[1247] The server optimizes marketing strategies based on emotion data. Specifically, it stocks more inventory of products that evoke specific emotions and implements promotions that evoke those emotions. The input data is the emotion analysis results, and the output data is an optimized marketing plan.

[1248] These steps will enable demand forecasting and inventory management that takes emotion data into account, improving the accuracy and efficiency of inventory management.

[1249] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1250] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1251] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1252] [Fourth embodiment]

[1253] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1254] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1255] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1256] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1257] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1258] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1259] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1260] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1261] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1262] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1263] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1264] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1265] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1266] The present invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[1267] ---

[1268] The system has the following components:

[1269] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. Sales data includes product names, quantities sold, sales dates and times, sales prices, etc.

[1270] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[1271] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[1272] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[1273] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[1274] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[1275] ---

[1276] Specific examples

[1277] As a concrete example, the operation of the system in a grocery store will be described.

[1278] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[1279] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[1280] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[1281] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[1282] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[1283] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[1284] This improves the accuracy and efficiency of inventory management, reduces resource waste, and increases customer satisfaction.

[1285] The processing flow will be explained below.

[1286] Step 1:

[1287] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[1288] Step 2:

[1289] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[1290] Step 3:

[1291] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[1292] Step 4:

[1293] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[1294] Step 5:

[1295] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[1296] Step 6:

[1297] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[1298] Step 7:

[1299] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[1300] Step 8:

[1301] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[1302] Step 9:

[1303] Users can view the inventory rotation plan through the terminal and manually adjust it if necessary, for example by changing the order in which new arrivals are placed after older stock.

[1304] Step 10:

[1305] The server continuously collects sales and inventory data and updates the system in real time, allowing you to constantly monitor the latest inventory status and sales trends.

[1306] Step 11:

[1307] The server periodically retrains the demand forecasting model based on new data collected, thereby maintaining and further improving the accuracy of the forecasts.

[1308] Step 12:

[1309] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[1310] Through the above processing steps, the system of the present invention can improve the efficiency and accuracy of inventory management, minimize a company's inventory risk, and increase customer satisfaction.

[1311] Example 1

[1312] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1313] With conventional inventory management systems, sales data collection, demand forecasting, and automatic inventory replenishment are often carried out separately, making integrated management difficult. Furthermore, there are issues with overstocking and shortages due to a lack of forecast accuracy and inappropriate replenishment timing. There is also the problem of increased waste due to management methods that ignore product expiration dates.

[1314] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1315] In this invention, the server includes a means for collecting sales data, a means for forecasting demand based on the sales data, and a means for collecting and updating current inventory information. This allows for integrated management of sales data and inventory information, enabling highly accurate demand forecasting and appropriate inventory replenishment.

[1316] "Sales data" refers to information related to sales, such as product name, number of units sold, sales date and time, and sales price.

[1317] "Demand forecasting" is a method of estimating future demand based on past sales data.

[1318] "Inventory information" refers to detailed inventory data such as product quantity, expiration date, and current stock status.

[1319] "Automatic replenishment" is a method of automatically replenishing inventory before it runs out, based on forecast data and current inventory information.

[1320] "Rotation" is a management method that manages the expiration date of inventory and prioritizes the release of products that were received first.

[1321] "Real-time monitoring" is a method of continuously analyzing data to instantly grasp current inventory status and sales information.

[1322] A "barcode reader" is a device that reads barcodes attached to products.

[1323] "RFID" is a technology that uses wireless communication to read and write information about items.

[1324] An "AI model" is an algorithm that uses machine learning technology to analyze large amounts of data and make predictions and classifications.

[1325] "Supplier" refers to a trader or company that supplies goods.

[1326] This invention is an automatic inventory replenishment system that uses AI to efficiently manage inventory. This system is mainly composed of three elements: a server, a terminal, and a user.

[1327] Hardware and software used

[1328] Server: Used for data collection, analysis, prediction, and instruction. The server has machine learning libraries such as TensorFlow and PyTorch and database management systems such as MySQL and PostgreSQL installed.

[1329] Terminals: Used to collect and transmit data. These include barcode readers, RFID devices, and point-of-sale systems.

[1330] User devices: Used to check real-time inventory information. Web dashboard and mobile app installed.

[1331] System processing flow

[1332] 1. Collect sales data:

[1333] The terminal collects sales data such as product name, sales quantity, sales date and time, and sales price through a POS system or online system. The collected data is sent to the server in JSON format.

[1334] 2. Demand forecasting:

[1335] The server stores the received sales data in a database. Next, it uses TensorFlow and PyTorch to train an AI model based on past sales data. This trained model is then used to predict future demand.

[1336] 3. Inventory Management:

[1337] The terminal uses a barcode reader or RFID to collect current inventory information, including product quantities and expiration dates, and sends the collected data to a server, which then updates the database in real time.

[1338] 4. Automatic inventory replenishment:

[1339] The server compares the demand forecast data with current inventory information. If there is a shortage of inventory, the server automatically sends an order to the supplier. The order is placed via API.

[1340] 5. Proper inventory rotation:

[1341] The server manages the expiration dates of inventory and prioritizes the delivery of older inventory, thereby minimizing waste.

[1342] 6. Real-time monitoring:

[1343] Users can check inventory status in real time via a web dashboard or mobile app, allowing them to quickly make any necessary adjustments.

[1344] Specific examples

[1345] As a concrete example, the operation of the system in a grocery store will be described.

[1346] 1. Collect sales data:

[1347] The terminal transmits daily sales data (e.g., milk, 100ml, sales date and time, price) collected from the cash register system to the server in real time.

[1348] 2. Demand forecasting:

[1349] The server trains an AI model using TensorFlow based on past sales data. For example, it uses data showing that milk sales increase in the summer to predict demand for 200 liters next month.

[1350] 3. Inventory Management:

[1351] Every day, the terminal uses a barcode reader to collect inventory data and send it to the server, including information such as the current inventory level being 150 liters.

[1352] 4. Automatic inventory replenishment:

[1353] The server compares the demand forecast results with the current inventory and automatically sends an order to the supplier to replenish the missing 50 liters.

[1354] 5. Proper inventory rotation:

[1355] The server manages the expiration date information of milk and prevents it from being discarded after expiration by implementing a first-in, first-out (FIFO) system.

[1356] 6. Real-time monitoring:

[1357] Users can use the mobile app to check milk inventory and sales in real time, allowing them to make additional adjustments or implement promotional campaigns on the fly.

[1358] Prompt Sentence Examples

[1359] "Please outline a program that uses an inventory control system to forecast milk demand and automatically replenish it appropriately."

[1360] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1361] Step 1: Collect sales data

[1362] The terminal collects sales data in real time from stores and online systems. Specifically, it uses a POS system or web application to obtain information such as product name, number of units sold, sales date and time, and sales price. This collected data is sent to the server in JSON format. The input data is sales information, and the output data is the sales data sent to the server.

[1363] Step 2: Demand forecast

[1364] The server stores the received sales data in a database. Next, it uses TensorFlow to train an AI model. The input data used for training is past sales data, and the model is used to predict future demand. The output data is the predicted demand figure. For example, based on past data, it predicts that next month's demand for milk will be 200 liters.

[1365] Step 3: Manage inventory information

[1366] The terminal collects inventory information using a barcode reader or RFID. The collected inventory information includes product quantities, expiration dates, etc., and is sent to the server in JSON format. The input data is the inventory information obtained from the barcode reader or RFID, and the output data is the latest inventory information sent to the server. For example, the server will know that the current amount of milk in stock is 150 liters.

[1367] Step 4: Automatically replenish inventory

[1368] The server compares demand forecast data with current inventory information and analyzes it. The input data is the demand forecast value and current inventory information, and as a result of the analysis, it generates order data to make up for any shortages in inventory. For example, if the forecast demand is 200 liters and the current inventory is 150 liters, the server will order the missing 50 liters from the supplier. This order is placed automatically via API.

[1369] Step 5: Rotate your inventory appropriately

[1370] The server manages inventory expiration date information and adjusts the order so that older inventory is shipped first. The input data is inventory expiration date information, and generates the rotation data required to adjust the shipping order. The output data is the adjusted shipping order information. For example, a first-in, first-out (FIFO) order is implemented using an inventory management script.

[1371] Step 6: Real-time monitoring

[1372] The server continuously analyzes data collected from the devices and monitors inventory status in real time. The input data is sales and inventory information sent from the devices, and the server outputs analyzed inventory status data. Users can access this analysis data and check inventory information in real time via a web dashboard or mobile app. For example, users can instantly check milk inventory levels and sales and make any necessary adjustments or promotional activities.

[1373] (Application example 1)

[1374] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1375] Conventional inventory management systems are prone to inventory shortages and excess inventory, making inventory management, particularly in logistics warehouses, time-consuming and labor-intensive. In addition, inaccurate demand forecasts make it difficult to create accurate inventory plans, resulting in lower customer satisfaction and increased management costs. Furthermore, inventory replenishment work is often done manually, resulting in inefficiency. The present invention aims to solve these problems and achieve efficient and accurate inventory management.

[1376] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1377] In this invention, the server includes a means for collecting sales data, a means for forecasting demand, a means for collecting and updating inventory information, a means for automatically replenishing inventory based on the collected and forecasted data, a means for managing appropriate inventory rotation, a means for monitoring inventory and sales information in real time, and a means for automatically replenishing inventory in the logistics warehouse using a robot. This enables efficient inventory management, accurate demand forecasting, and reduced labor through automatic replenishment.

[1378] Definitions of important words

[1379] "Sales data" is information indicating the sales status of a product, and includes details such as the number of units sold, the date and time of sale, the product name, and the sales price.

[1380] "Demand forecasting" is the process of estimating future sales volumes based on past sales data and market trends.

[1381] "Inventory information" is information indicating the quantity and expiration date of products held in a warehouse or store.

[1382] "Auto-replenish" means that the system automatically places an order for more stock before it runs out.

[1383] "Rotation" refers to managing products so that they are consumed in a specific order, and is often used to refer to first-in, first-out (FIFO).

[1384] "Real-time monitoring" means instantly understanding current inventory status and sales information.

[1385] A "robot" is a mechanical device that automatically replenishes inventory in a logistics warehouse according to programmed instructions.

[1386] An "AI model" is a mathematical algorithm or machine learning model that uses artificial intelligence to extract insights from data and make predictions and classifications.

[1387] A "sensor" is a device that detects physical phenomena and converts them into data. Examples include cameras and pressure sensors.

[1388] "Form for carrying out the invention" of the specification

[1389] The present invention is an automatic inventory replenishment system that uses AI to achieve efficient inventory management in logistics centers. This system uses specific hardware and software to collect sales data, forecast demand, manage inventory information, automatically replenish inventory, rotate inventory, and perform real-time monitoring. Specific embodiments for implementing the present invention are described below.

[1390] Hardware Configuration

[1391] The system includes the following hardware:

[1392] 1. Sensors: Detect the amount of inventory on shelves or in warehouses. For example, cameras and pressure sensors are used.

[1393] 2. Robot: A mechanical device that replenishes inventory in a distribution warehouse according to programmed instructions.

[1394] 3. Terminal: A device used for data collection and for administrators to check information in real time. Examples include smartphones and tablets.

[1395] 4. Server: A central device for aggregating data, analyzing it, and running AI models.

[1396] Software Configuration

[1397] The system includes the following software:

[1398] 1. Sales data collection program: Collects data from sensors in real time and sends it to the server.

[1399] 2. AI models: Built using machine learning libraries such as TensorFlow and PyTorch to perform demand forecasting.

[1400] 3. Inventory management program: Collects, updates, and manages inventory data and manages expiration date information.

[1401] 4. Automatic replenishment program: Based on demand forecasts and inventory information, calculates the required inventory level and sends replenishment instructions to the robot.

[1402] 5. Real-time monitoring interface: An application that monitors inventory status and sales information on a smartphone or tablet.

[1403] Processing flow

[1404] The server first receives sales data sent from sensors and terminals. It then trains an AI model based on the collected sales data to make demand forecasts. This forecast takes market trends and seasonal fluctuations into account. The server also collects current inventory information and updates the database in real time. It compares the forecast results with the inventory information, and if there is a shortage of inventory, it automatically calculates the required inventory amount and sends a replenishment instruction to the robot. The robot replenishes the inventory based on the calculated amount. The server also manages inventory expiration dates and maintains appropriate stock rotation. Users can use their terminals to check inventory status and sales information in real time.

[1405] Specific examples

[1406] As a concrete example, consider the case of managing milk inventory in a distribution warehouse. A sensor detects milk inventory and sends the current inventory amount to a server. Based on past sales data, an AI model predicts the demand for milk for next month. For example, let's say that based on past data, the amount of milk needed next month is predicted to be 200 liters. If the current inventory is 150 liters, a robot automatically picks up an additional 50 liters from the warehouse to replenish the missing 50 liters.

[1407] Prompt Sentence Examples

[1408] "Please predict next month's demand based on the following historical sales data:

[1409] Product Name: Dairy Products

[1410] Monthly sales for the past year (liters):

[1411] January: 200, February: 180, March: 250, April: 300, May: 280, June: 350, July: 400, August: 350, September: 320, October: 300, November: 250, December: 220

[1412] Anticipate future demand.

[1413] As a result, a system that can achieve efficient and accurate inventory management is constructed.

[1414] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1415] Processing steps of the system program that realizes the application example

[1416] Step 1:

[1417] Sensors and terminals monitor inventory on shelves and in warehouses in real time and collect inventory information.

[1418] Input: Shelf inventory status (product name, quantity, expiration date, etc.)

[1419] Processing: Collect inventory data from sensors (cameras and pressure sensors) and convert it into JSON format data.

[1420] Output: Inventory data in JSON format

[1421] Step 2:

[1422] The server receives the inventory data sent from the terminal and stores it in a database.

[1423] Input: Inventory data in JSON format

[1424] Processing: Store the received data in the database and update the current inventory information.

[1425] Output: Updated inventory database

[1426] Step 3:

[1427] The server collects sales data and creates a dataset to be input into the AI ​​model.

[1428] Input: Past sales data (product name, number of units sold, sales date and time, sales price, etc.)

[1429] Processing: Organizing and consolidating each sales data to generate a dataset suitable for the AI ​​model.

[1430] Output: Dataset for AI model

[1431] Step 4:

[1432] The server uses an AI model to make demand forecasts.

[1433] Input: Dataset for AI model

[1434] Processing: Run trained AI models using TensorFlow and PyTorch to predict future demand.

[1435] Output: Forecasted demand data

[1436] Step 5:

[1437] The server compares the forecast results with current inventory information and calculates the amount of inventory that is lacking.

[1438] Inputs: Forecasted demand data, current inventory data

[1439] Processing: Calculate the missing inventory by subtracting the current inventory from the forecasted demand.

[1440] Output: Data on shortage quantity

[1441] Step 6:

[1442] The server sends an automatic replenishment instruction to the robot.

[1443] Input: Data on the shortage amount

[1444] Processing: Generates and sends replenishment instructions to the robot, specifically instructions to retrieve the items the robot needs from the warehouse and replenish them.

[1445] Output: Replenishment instructions (instructions to the robot)

[1446] Step 7:

[1447] The robot follows replenishment instructions, retrieves products from the warehouse, and replenishes them on the designated shelves.

[1448] Input: Replenishment instructions

[1449] Processing: The robot moves, picks up the specified product, and places it appropriately on the specified shelf.

[1450] Output: Notification of replenishment completion

[1451] Step 8:

[1452] The server receives the report of the completion of stock replenishment and updates the database.

[1453] Input: Replenishment completion notification

[1454] Action: Update the database as available stock and check the real-time stock status again.

[1455] Output: Updated database, real-time inventory status

[1456] Step 9:

[1457] The terminal can monitor the latest inventory status and sales information in real time.

[1458] Input: Updated database

[1459] Processing: Retrieves the latest inventory and sales information from the database and provides an interface that allows users to visually check it.

[1460] Output: Inventory status and sales information display interface

[1461] Step 10:

[1462] The user uses the terminal to check inventory status and sales information, and issues additional replenishment instructions or implements sales promotion campaigns as necessary.

[1463] Input: Inventory status and sales information

[1464] Action: View information through the interface and plan replenishment and promotional campaigns. For example, alerts for low-stock items and planning campaigns to balance supply and demand.

[1465] Output: User decision support

[1466] Through the above processing steps, the system of the present invention realizes efficient and practical inventory management and automatic replenishment.

[1467] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1468] The present invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. Specific embodiments of this system are described below.

[1469] ---

[1470] The system has the following components:

[1471] 1. Sales data collection: The terminal collects sales data in real time from stores and online systems and sends it to the server. The sales data includes product name, number of units sold, date and time of sale, sales price, etc.

[1472] 2. Demand forecasting: The server uses accumulated sales data to train an AI model. Using the trained model, the server accurately predicts future demand. For example, the server calculates how much of each product will be needed based on seasonal fluctuations and market trends.

[1473] 3. Inventory Management: The terminal periodically collects current inventory information and sends it to the server, which then updates the inventory database in real time. This information includes important information such as product quantities and expiration dates.

[1474] 4. Automatic inventory replenishment: The server analyzes demand forecast data against current inventory information and automatically replenishes inventory before it runs out. The server calculates the appropriate timing and quantity, and automatically sends an order to the supplier.

[1475] 5. Proper stock rotation: The server manages the expiration dates of stock and creates a rotation plan, so that the products that arrived first are consumed first. For example, in the case of groceries, it practices First In First Out (FIFO).

[1476] 6. Real-time monitoring: The server analyzes the data collected continuously and monitors the inventory status in real time. Users can access the latest inventory information at any time using their devices and check product sales and stock status.

[1477] 7. Emotion engine: The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. This emotional data is sent to the server and used for inventory management and product recommendations.

[1478] 8. Utilizing Emotional Data: The server can use emotional data to predict user purchasing intent and product popularity, providing additional data for optimizing inventory replenishment and marketing strategies.

[1479] ---

[1480] Specific examples

[1481] As a concrete example, the operation of the system in a grocery store will be described.

[1482] 1. Collection of sales data: The terminal collects daily sales data (e.g., milk, 100ml, sales date and time, price) from the cash register system in real time and sends the data to the server.

[1483] 2. Demand forecasting: The server uses an AI model to forecast the demand for milk for the next month based on past sales data (e.g., milk sales increase in the summer). For example, based on past data, it predicts that the amount of milk needed next month will be 200 liters.

[1484] 3. Inventory management: The terminal collects daily inventory data and sends it to the server. The server updates the database based on the current inventory amount, and determines that there is currently 150 liters left in stock.

[1485] 4. Automatic inventory replenishment: The server compares the demand forecast (200 liters) with the current inventory information (150 liters) and automatically sends an order to the supplier to replenish the missing 50 liters.

[1486] 5. Proper stock rotation: The server manages the expiration date information of milk and adjusts the sales so that older stock is sold first, thereby preventing expired stock from being wasted.

[1487] 6. Real-time monitoring: Users can check the real-time milk inventory status and sales status on their devices. Based on this information, users can immediately make additional adjustments or carry out promotional campaigns.

[1488] 7. Use of emotion engine: Using the camera and microphone on the device, the system analyzes the user's facial expressions and voice to collect emotional data. For example, analyzing the user's facial expressions and voice tone when purchasing milk can be used to assess the user's willingness to purchase.

[1489] 8. Utilizing Emotional Data: The server analyzes the collected emotional data to assess user interest in specific products. For example, if users express excitement about a product, the server can stock more of that product. It can also adjust marketing efforts and implement promotions that evoke specific emotions.

[1490] This will further improve the accuracy and efficiency of inventory management, and will also improve customer satisfaction based on user emotions.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] The terminal collects sales data in real time from stores and online systems. The sales data includes product names, quantities sold, sales dates and times, sales prices, etc. This data is periodically sent to the server.

[1494] Step 2:

[1495] The server stores the received sales data in a database and performs preprocessing on the data, which includes imputing missing values ​​and detecting and correcting outliers.

[1496] Step 3:

[1497] The server trains a demand forecasting model based on the preprocessed sales data using machine learning algorithms (e.g., LSTM and ARIMA) that take into account seasonal fluctuations and market trends.

[1498] Step 4:

[1499] The server uses the trained model to predict demand for the next month or week, which is then stored in a database and sent to a dashboard for visualization.

[1500] Step 5:

[1501] The terminal periodically checks the store's current inventory information and sends it to the server, which stores the received inventory data in a database and updates it in real time.

[1502] Step 6:

[1503] Users can access real-time inventory information from their devices and check stock fluctuations. Users can also manually update inventory information.

[1504] Step 7:

[1505] The server compares current inventory data with demand forecast data to create a list of products that need replenishment, calculates the optimal replenishment timing and quantity, and automatically sends orders to suppliers.

[1506] Step 8:

[1507] The server manages the appropriate rotation of inventory, taking into account product expiration dates, and in particular prioritizes the sale of products whose expiration dates are approaching.

[1508] Step 9:

[1509] Users can view the inventory rotation plan through the terminal and manually adjust it as needed, for example by changing the order in which new arrivals are placed after older stock.

[1510] Step 10:

[1511] The emotion engine installed in the device analyzes the user's facial expressions, voice tone, and movements to collect emotional data. For example, it detects the facial expressions and voice tone when the user picks up a product.

[1512] Step 11:

[1513] The device sends the emotional data to a server, which then stores the collected data in a database and analyzes it.

[1514] Step 12:

[1515] The server uses the emotional data to predict the user's purchasing intent and the popularity of a product. For example, if the user is excited, the server will adjust the supply and demand forecast for that product upward.

[1516] Step 13:

[1517] The server uses the emotional data to optimize inventory replenishment and marketing strategies, for example, by identifying products that users find favorable and implementing promotions centered around those products.

[1518] Step 14:

[1519] The server continuously collects sales, inventory, and sentiment data and updates the system in real time, ensuring that the latest demand forecasts and inventory information are always available.

[1520] Step 15:

[1521] Users can monitor system performance and provide feedback as needed, which is used to tune the system.

[1522] This will improve the accuracy and efficiency of inventory management, and also improve customer satisfaction using an emotion engine.

[1523] Example 2

[1524] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1525] Current inventory management systems forecast demand and replenish inventory based on sales and inventory data, but they are unable to take user emotions or purchasing intentions into account. This makes it difficult to accurately forecast demand and appropriately replenish inventory, resulting in a high risk of stockouts and excess inventory. Furthermore, marketing strategies to improve the user experience are not adequately optimized. To solve these problems, there is a need for more accurate demand forecasts and an inventory management system that takes user emotions into account.

[1526] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for collecting sales data, a means for collecting and updating current inventory information, a means for automatically replenishing inventory based on the collected and predicted data, a means for collecting and analyzing user emotion data, and a means for optimizing demand forecasting and marketing strategies based on the emotion data. This improves the accuracy of demand forecasting, reduces the risk of stockouts and excess inventory, and enables product suggestions and marketing strategies to be optimized based on user emotions.

[1527] "Sales data" refers to information such as the name of the product sold in a store or online system, the number of units sold, the date and time of sale, and the sales price.

[1528] "Demand forecasting" is the process of predicting future sales volumes and required inventory levels based on collected sales data.

[1529] "Inventory information" is data such as the quantity and expiration date of currently held products.

[1530] "Automatic inventory replenishment" refers to the automatic replenishment of inventory based on demand forecasts and current inventory information to prevent inventory shortages.

[1531] "Appropriate inventory rotation" means taking into account product expiration dates and managing the inventory so that older inventory is consumed first.

[1532] "Real-time monitoring" means continuously analyzing inventory status and sales information to instantly grasp the latest data.

[1533] "Emotion data" refers to information related to emotions collected from the user's facial expressions, tone of voice, movements, and the like.

[1534] An "emotion engine" is a technology or device that analyzes a user's facial expressions, voice, and movements to collect emotional data.

[1535] A "marketing strategy" is a strategic measure aimed at promoting product sales and improving customer satisfaction.

[1536] This invention combines an AI-based automatic inventory replenishment system for efficient inventory management with an emotion engine that recognizes user emotions. This system improves the accuracy and efficiency of inventory management through sales data collection, demand forecasting, inventory information management, automatic inventory replenishment, appropriate inventory rotation, real-time monitoring, and the use of emotion data.

[1537] Hardware and software used

[1538] 1. Terminal

[1539] Hardware: POS system, barcode scanner, camera, microphone

[1540] Software: Data collection software, facial expression recognition software (e.g., OpenCV), voice analysis software

[1541] 2. Server

[1542] Hardware: High-performance servers (e.g. cloud infrastructure)

[1543] Software: Database management systems (e.g., MySQL, PostgreSQL), generative AI models (e.g., TensorFlow, PyTorch), visual tools (e.g., Grafana, PowerBI), sentiment analysis algorithms

[1544] Process Overview

[1545] 1. Collect sales data

[1546] The terminal collects sales data in real time from stores and online systems and sends it to a server. The collected sales data includes product name, number of units sold, date and time of sale, and sales price.

[1547] 2. Demand forecast

[1548] The server uses the accumulated sales data to train a generative AI model, which is then used to accurately forecast future demand, including past sales data and seasonality features.

[1549] 3. Inventory management

[1550] The terminal periodically collects current inventory information and sends it to the server, which uses this information to update the inventory database in real time.

[1551] 4. Automatic inventory replenishment

[1552] The server compares demand forecast data with current inventory information to calculate the amount of replenishment required, calculates the appropriate timing and quantity, and automatically sends orders to suppliers.

[1553] 5. Proper inventory rotation

[1554] The server uses expiration information in the inventory database to prioritize product consumption, implementing FIFO (first in, first out) logic to ensure that older inventory is sold first.

[1555] 6. Real-time monitoring

[1556] The server analyzes the continuously collected data and generates reports that are displayed on a dashboard, where users can access up-to-date inventory and sales data via their devices.

[1557] 7. Incorporating an Emotional Engine

[1558] The device's built-in camera and microphone are used to analyze the user's facial expressions, voice tone, and movements, and collect emotional data. This emotional data is sent to a server and used for various analyses.

[1559] 8. Utilizing Emotional Data

[1560] The server analyzes the collected emotional data to assess the user's purchasing intent and interest in specific products, thereby improving the accuracy of inventory replenishment and optimizing product recommendations and marketing strategies based on user emotions.

[1561] Specific examples

[1562] As an example of how the system works in a grocery store, a terminal collects daily sales data from the cash register system (e.g., milk, 100ml, sales date and time, price) and sends that data to a server. The server uses an AI model based on past sales data to predict next month's milk demand (e.g., predicting the amount of milk needed next month to be 200 liters). The terminal also collects daily inventory data (current inventory: 150 liters) and sends it to the server. The server automatically sends an order to the supplier to replenish the missing 50 liters.

[1563] The device also uses a camera and microphone to analyze the user's facial expressions and voice tone to collect emotional data. For example, when a user purchases milk, the device analyzes their facial expressions and voice tone to assess their willingness to purchase, and sends this data to a server. The server analyzes this emotional data to assess the product's popularity and purchasing intent, and then optimizes inventory replenishment and marketing strategies based on that data.

[1564] As a specific example, a prompt such as, "Based on sales data for milk at a grocery store, we would like to predict summer demand and automatically replenish it using an inventory management system. Please tell us the specific steps required and the points that we should consider." could be used.

[1565] The above is a specific embodiment of the present invention.

[1566] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1567] Step 1: Collect sales data

[1568] The terminal collects sales data in real time from stores and online systems. It takes in information from data sources such as POS systems and e-commerce platforms. Specifically, it collects information such as product name, number of units sold, date and time of sale, and sales price. The collected data is stored in JSON format and sent to the server. The input is sales data from each data source, and the output is formatted data sent to the server.

[1569] Step 2: Submit your sales data

[1570] The terminal periodically sends the collected sales data to the server. The HTTPS protocol is used to ensure security when sending data. Specifically, the terminal temporarily stores the collected data and then sends it to the server in batches after a certain period of time has passed. The input is formatted sales data, and the output is the sales data stored on the server.

[1571] Step 3: Save your sales data

[1572] The server saves the received sales data in a database. At this time, it uses a database management system (e.g., MySQL, PostgreSQL) to store the data accurately. The server inserts each data item into the corresponding table according to the data schema. The input is the sales data sent to the server, and the output is the sales data stored in the database.

[1573] Step 4: Training the AI ​​model

[1574] The server uses sales data stored in the database to train a generative AI model (e.g., TensorFlow, PyTorch). The model takes past sales data and features such as seasonal factors as input and outputs a demand forecasting model. Specifically, it runs the training dataset multiple times while optimizing the model's learning parameters. The input is sales data extracted from the database, and the output is a trained demand forecasting model.

[1575] Step 5: Demand forecasting

[1576] The server uses the trained demand forecasting model to predict future demand. Specifically, it makes numerical predictions of next month's sales volume and demand for specific products. The server inputs new sales data into the trained model and outputs the demand forecast results. The input is new sales data, and the output is the predicted product demand.

[1577] Step 6: Gather inventory information

[1578] The terminal periodically collects current inventory information (product name, quantity, expiration date, etc.) and sends that information to the server. Specific operations involve acquiring data using a barcode scanner or inventory management software. The input is the current inventory information, and the output is the inventory data sent to the server.

[1579] Step 7: Save inventory information

[1580] The server stores the received inventory data in a database. The server inserts the inventory data into the corresponding table and updates the database in real time. The input is the inventory data sent to the server, and the output is the inventory information stored in the database.

[1581] Step 8: Automatically replenish inventory

[1582] The server compares demand forecast data with current inventory information to calculate how much replenishment is required. The server calculates the shortage and automatically sends a replenishment order to the supplier. Specifically, it generates an order list and places an order with the supplier via API. The input is demand forecast data and inventory information, and the output is the order data sent to the supplier.

[1583] Step 9: Rotate your inventory appropriately

[1584] The server uses expiration date information in the inventory database to set product consumption priorities. It executes FIFO (first in, first out) logic and issues instructions to sell older stock first. Specifically, it creates a stock rotation plan for each product and sends it to the terminal. The input is inventory information, and the output is rotation instructions to the terminal.

[1585] Step 10: Real-time monitoring

[1586] The server continuously analyzes the collected data and generates reports that are displayed on a dashboard. Users can access up-to-date inventory and sales data using their devices. Specific operations involve using data analysis software to generate graphs and charts using visual tools (e.g., Grafana, PowerBI). The input is the data to be analyzed, and the output is a dashboard that users can access.

[1587] Step 11: Collect emotion data

[1588] Emotional data is collected by analyzing the user's facial expressions, voice tone, and movements using the device's built-in camera and microphone. For example, facial expression recognition software (e.g., OpenCV) is used to analyze the user's facial expressions while browsing products. The input is the user's facial and voice data, and the output is the analyzed emotional data.

[1589] Step 12: Sending Emotion Data

[1590] The device sends the collected emotion data to the server. The HTTPS protocol is used for data transmission, ensuring secure transmission of emotion data. The input is the collected emotion data, and the output is the data sent to the server.

[1591] Step 13: Analyze the emotion data

[1592] The server analyzes the received emotional data and evaluates the user's purchasing intent and interest in the product. The server uses an emotion analysis algorithm to quantitatively evaluate the user's emotions. The input is the transmitted emotional data, and the output is the analysis result.

[1593] Step 14: Optimize your marketing strategy

[1594] The server uses the sentiment data to optimize inventory replenishment and marketing strategies. If there is high interest in a particular product, it will automatically implement measures such as increasing the stock of that product. The input is the analysis results, and the output is an optimized replenishment plan and marketing measures.

[1595] (Application example 2)

[1596] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1597] Current inventory management systems focus on forecasting demand and streamlining inventory replenishment based on sales data and inventory information, but they lack the ability to utilize customer sentiment data. This makes it difficult to understand customer purchasing intent and product popularity in real time and optimize marketing strategies and inventory management.

[1598] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting sales data, means for performing demand forecasting, means for collecting and updating inventory information, means for automatically replenishing inventory, means for managing inventory rotation and taking product expiration dates into consideration, means for monitoring inventory and sales information in real time, means for collecting and analyzing emotion data, and means for optimizing demand forecasting and inventory replenishment based on the emotion data. This enables demand forecasting and real-time inventory management that takes customer emotions into consideration.

[1599] 1. "Sales data" refers to purchase information such as product name, quantity sold, sales date and time, and sales price, and is information collected from stores and online systems.

[1600] 2. "Demand forecasting" is the process of predicting future product demand using AI models based on sales data and market trends.

[1601] 3. "Inventory information" is a general term for data required in an inventory management system, including information such as current inventory quantities, product expiration dates, and storage locations.

[1602] 4. "Automated inventory replenishment" is a system or process that automatically orders products from suppliers before they run out of stock, based on demand forecast data and current inventory information.

[1603] 5. "Inventory rotation" is an inventory management technique that takes into account product expiration dates and adjusts inventory so that older inventory is consumed first.

[1604] 6. "Real-time monitoring" is the process of immediately analyzing collected data to monitor real-time inventory status and sales information.

[1605] 7. "Emotional Data" refers to data used to understand a user's emotional state by analyzing information such as the user's facial expressions, tone of voice, and movements.

[1606] 8. "Sentiment analysis" is the process of using collected emotional data to analyze a user's emotional state and assess purchasing intent and product popularity.

[1607] 9. “Optimization” is the process of adjusting to maximize efficiency or effectiveness under given conditions, and in this case refers to using sentiment data to improve demand forecasting and inventory replenishment.

[1608] This invention combines an emotion recognition engine with an automatic inventory replenishment system that uses AI to efficiently manage inventory. Specific embodiments of this system are described below.

[1609] The system consists of a terminal that collects sales data, a server that predicts demand based on that sales data, a terminal that collects and updates current inventory information, a server that automatically replenishes inventory based on the collected and predicted data, a server that manages appropriate inventory rotation and takes product expiration dates into account, a terminal that monitors inventory and sales information in real time, a terminal that collects and analyzes emotional data, and a server that optimizes demand prediction and inventory replenishment based on the emotional data.

[1610] Hardware and software used

[1611] 1. Smartphones and smart glasses:

[1612] Camera: Captures the user's facial expressions for emotion recognition.

[1613] Microphone: Records the user's voice for emotion recognition.

[1614] 2. Server:

[1615] Database: Used to store and manage sales and inventory data.

[1616] AI models: Use machine learning libraries (e.g., Scikit-learn) to perform demand forecasting and sentiment analysis.

[1617] 3. Software Libraries:

[1618] OpenCV: An image processing library for facial expression recognition.

[1619] Dlib: Facial landmark detection.

[1620] Scikit-learn: A machine learning library for demand forecasting and sentiment analysis.

[1621] Processing flow

[1622] Device data collection:

[1623] The camera and microphone installed in the smartphone or smart glasses are used to collect the user's facial expressions and voice, and this data is sent to a server in real time.

[1624] Sentiment analysis and purchase intent assessment:

[1625] Emotion data is analyzed using OpenCV and Dlib to understand the user's emotional state, and the AI ​​model then predicts their purchasing intent. For example, if a customer shows excitement in front of a particular product, it predicts increased demand for that product.

[1626] Inventory Management:

[1627] The server uses sales and inventory data to make demand forecasts. By adding the results of sentiment analysis to the demand forecast, it is possible to make demand forecasts that take into account product popularity and purchasing intentions.

[1628] Automatic inventory replenishment:

[1629] The server automatically replenishes goods based on demand forecasts and current inventory information. Specifically, it automatically orders products from suppliers based on demand forecast data before inventory runs out.

[1630] Real-time monitoring:

[1631] Users (store staff) can use smart devices to check inventory status and sales information in real time, which allows for immediate adjustments and promotional campaigns.

[1632] Specific examples

[1633] Milk inventory management:

[1634] Milk sales data is collected in real time and sent to a server. Based on past sales data and market trends, an AI model predicts next month's demand at 200 liters. Knowing that current stock is 150 liters, the AI ​​model automatically orders the missing 50 liters from the supplier. Furthermore, when a customer purchases milk, the smart glasses capture their facial expressions and analyze their excitement, prompting them to order more.

[1635] Prompt Sentence Examples

[1636] "Analyze the facial expressions and voices of users when they purchase milk and predict their purchasing intentions."

[1637] This will enable demand forecasting and inventory management that takes emotional data into account, improving accuracy and efficiency.

[1638] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1639] Step 1:

[1640] The device collects the user's facial expressions and voice in real time using the camera and microphone of a smartphone or smart glasses, and generates image and audio files as facial expression and voice data, which are then sent to a server.

[1641] Step 2:

[1642] The server analyzes the received facial expression and audio data. Specifically, it uses OpenCV and Dlib to extract facial landmarks from image files and perform emotion analysis. It also performs tone analysis on audio files to determine the user's emotional state. The input data are facial expression images and audio files, and the output data are labels indicating the emotional state (e.g., "happy," "sad," or "neutral").

[1643] Step 3:

[1644] The server stores the results of the emotion analysis in a database. Detailed emotion data is managed by storing the date and time, user ID, and product information together with the emotional state label. This allows for the accumulation of data necessary for future analysis.

[1645] Step 4:

[1646] The terminal collects sales data from the POS system. The sales data, which includes product name, quantity sold, date and time of sale, and sales price, is periodically sent to the server and received as input data. The output is a record of the updated sales data.

[1647] Step 5:

[1648] The server makes demand forecasts based on accumulated sales data. Past sales data and sentiment data are input into a generative AI model to predict future demand. The forecast results are output as the required quantity of each product for the next month.

[1649] Step 6:

[1650] The server collects current inventory information from the terminals and updates the database in real time. Data including stock quantity, product expiration date, storage location, etc. is input, and the latest inventory status is output.

[1651] Step 7:

[1652] The server compares demand forecast data with current inventory information and automatically replenishes items that are out of stock. It calculates the necessary replenishment amount and the optimal order timing, and automatically sends orders to suppliers. The input data is the demand forecast results and inventory information, and the output data is order details.

[1653] Step 8:

[1654] The server manages the appropriate rotation of inventory. Taking into account the expiration date of the inventory, it adjusts the inventory so that the inventory received first is consumed first. This minimizes product waste. The input data is the expiration date information of the inventory, and the output data is the rotation instruction.

[1655] Step 9:

[1656] Users can monitor inventory status and sales information in real time using a terminal, allowing them to immediately grasp sales trends and inventory status. Input data is current inventory and sales information, and output data is a real-time report of these.

[1657] Step 10:

[1658] The server optimizes marketing strategies based on emotion data. Specifically, it stocks more inventory of products that evoke specific emotions and implements promotions that evoke those emotions. The input data is the emotion analysis results, and the output data is an optimized marketing plan.

[1659] These steps will enable demand forecasting and inventory management that takes emotion data into account, improving the accuracy and efficiency of inventory management.

[1660] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1661] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1662] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1663] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1664] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1665] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1666] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1667] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1668] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1669] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1670] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1671] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1672] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1673] 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.

[1674] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1675] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1676] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1677] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1678] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1679] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1680] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1681] The following is further disclosed regarding the above embodiment.

[1682] (Claim 1)

[1683] a means of collecting sales data;

[1684] A means of forecasting demand based on that sales data;

[1685] A means of collecting and updating current inventory information;

[1686] a means for automatically replenishing inventory based on collected and forecasted data;

[1687] A means of managing proper rotation of stock and taking into account product expiry dates;

[1688] A means of monitoring inventory and sales information in real time,

[1689] A system including:

[1690] (Claim 2)

[1691] 2. The system according to claim 1, wherein the demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends.

[1692] (Claim 3)

[1693] 2. The system according to claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount and automatically sends an order to the supplier.

[1694] "Example 1"

[1695] (Claim 1)

[1696] a means of collecting sales data;

[1697] A means of forecasting demand based on that sales data;

[1698] A means of collecting and updating current inventory information;

[1699] a means for automatically replenishing inventory based on collected and forecasted data;

[1700] A means of managing proper rotation of stock and taking into account product expiry dates;

[1701] A means of monitoring inventory and sales information in real time,

[1702] A means of collecting inventory information using barcode readers and RFID,

[1703] A means to train AI models based on historical sales data, and

[1704] A means of automatically sending orders to suppliers;

[1705] A system including:

[1706] (Claim 2)

[1707] 2. The system according to claim 1, wherein the demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends.

[1708] (Claim 3)

[1709] 2. The system according to claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount and automatically sends an order to the supplier.

[1710] "Application Example 1"

[1711] Claims that reflect new inventions

[1712] (Claim 1)

[1713] a means of collecting sales data;

[1714] A means of forecasting demand based on that sales data;

[1715] A means of collecting and updating current inventory information;

[1716] a means for automatically replenishing inventory based on collected and forecasted data;

[1717] A means of managing proper rotation of stock and taking into account product expiry dates;

[1718] A means of monitoring inventory and sales information in real time,

[1719] A means of automatically replenishing inventory in logistics warehouses using robots,

[1720] A system including:

[1721] (Claim 2)

[1722] The system according to claim 1, wherein the demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends, and predicts inventory in the logistics warehouse using an AI model.

[1723] (Claim 3)

[1724] 2. The system of claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount, automatically sends orders to suppliers, and further uses a robot to actually replenish inventory.

[1725] "Example 2: Combining Emotion Engines"

[1726] (Claim 1)

[1727] a means of collecting sales data;

[1728] A means of forecasting demand based on that sales data;

[1729] A means of collecting and updating current inventory information;

[1730] a means for automatically replenishing inventory based on collected and forecasted data;

[1731] A means of managing proper rotation of stock and taking into account product expiry dates;

[1732] A means of monitoring inventory and sales information in real time,

[1733] means for collecting and analyzing user emotion data;

[1734] means for optimizing demand forecasting and marketing strategies based on the emotion data;

[1735] A system including:

[1736] (Claim 2)

[1737] 2. The system according to claim 1, wherein the demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends.

[1738] (Claim 3)

[1739] 2. The system according to claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount and automatically sends an order to the supplier.

[1740] "Application example 2 when combining emotion engines"

[1741] (Claim 1)

[1742] a means of collecting sales data;

[1743] A means of forecasting demand based on that sales data;

[1744] A means of collecting and updating current inventory information;

[1745] a means for automatically replenishing inventory based on collected and forecasted data;

[1746] A means of managing proper rotation of stock and taking into account product expiry dates;

[1747] A means of monitoring inventory and sales information in real time,

[1748] a means for collecting and analyzing emotion data;

[1749] a means for optimizing demand forecasting and inventory replenishment based on sentiment data;

[1750] A system including:

[1751] (Claim 2)

[1752] 2. The system according to claim 1, wherein the demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends.

[1753] (Claim 3)

[1754] 2. The system according to claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount and automatically sends an order to the supplier. [Explanation of symbols]

[1755] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means of collecting sales data; A means of forecasting demand based on that sales data; A means of collecting and updating current inventory information; a means for automatically replenishing inventory based on collected and forecasted data; A means of managing proper rotation of stock and taking into account product expiry dates; A means of monitoring inventory and sales information in real time, A system including:

2. 2. The system according to claim 1, wherein said demand forecasting means makes a demand forecast taking into account seasonal fluctuations and market trends.

3. 2. The system according to claim 1, wherein the automatic inventory replenishment means calculates the optimal replenishment timing and amount and automatically sends an order to the supplier.

Images