system

Abstract

Provide a system. The present invention includes a means for collecting historical sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; a means for automatically calculating replenishment amounts and placing orders based on the predicted demand; A means of managing the expiration dates of inventory items and prioritizing the sale of items with an approaching expiration date. A means to collect inventory data in real time and monitor sales and stock status, A means to generate and notify real-time alerts for slow-selling or low-stock items; A system including:

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] Many modern companies spend a great deal of time and effort on inventory management. Manual inventory management carries a high risk of stockouts and excess inventory, and errors are inevitable. In particular, product demand forecasting and expiration date management require advanced skills and experience, so efficiency improvements are desirable. Unless these issues are resolved, optimizing inventory management will be difficult, resulting in a decline in business efficiency. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by providing a system including means for collecting past sales data and seasonal data for demand forecasting, means for executing an algorithm for forecasting demand based on the collected data, means for calculating replenishment amounts based on the forecasted demand and automatically placing orders, means for managing the expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates, means for collecting inventory data in real time and monitoring sales and inventory status, and means for generating and notifying warnings in real time about items that are not selling well or are low in stock.

[0006] Specifically, the system first collects past sales data and seasonal data, and uses this to make demand forecasts. Then, based on the predicted demand, it calculates the optimal replenishment amount and automatically places orders with suppliers. It also manages the expiration dates of inventory items and prioritizes the sale of items with an approaching expiration date, minimizing waste. It also collects inventory data in real time and monitors sales and stock levels to detect situations that require timely action. Finally, it generates real-time alerts for items that are not selling well or are low in stock, and notifies store and warehouse employees, encouraging them to take prompt action. In this way, it achieves efficient and optimized inventory management.

[0007] "Demand forecasting" is the process of estimating future demand based on past sales data and seasonal data using statistical or machine learning techniques.

[0008] "Sales data" is a collection of data including information such as the sales quantity and sales amount of products based on past transactions.

[0009] "Seasonal data" refers to data that indicates trends in demand for a product relative to a particular season or time of year.

[0010] An "algorithm" is a set of procedures or computational methods for solving a particular problem.

[0011] "Replenishment quantity" is the quantity of additional product to be ordered or replenished based on forecasted demand and inventory status.

[0012] "Automatic ordering" is a process in which the system automatically calculates replenishment quantities without manual intervention and issues ordering instructions to suppliers.

[0013] "Expiration date" refers to the last date by which the product's quality is guaranteed and by which it must be consumed or sold.

[0014] "Priority sales" is a method of encouraging products with an upcoming expiration date to be sold before other products.

[0015] "Real-time" refers to a state in which data is collected and processed immediately, without delay.

[0016] "Inventory data" is a collection of data including the quantity and status of products currently stored in warehouses or stores.

[0017] An "alert" is a notification or alert that the system generates based on a specific condition (e.g., low inventory, slow sales, etc.).

[0018] "Notifications" are messages generated by the system to inform terminals or employees of warnings or important information. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0041] 1. System Configuration

[0042] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time.

[0043] 2. Data Collection

[0044] The server periodically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, and the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[0045] Example: A store may sell a large number of certain products (e.g., holiday decorations) during the Christmas season. Based on this information, seasonal data is entered into the system.

[0046] 3. Generate a predictive model

[0047] The server analyzes the collected sales and seasonal data and generates a demand forecasting model using statistical analysis and machine learning algorithms. This model is used to predict future demand with high accuracy.

[0048] 4. Automatic replenishment and ordering

[0049] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0050] Example: Predicted Christmas items are automatically ordered before December to avoid shortages.

[0051] 5. Inventory expiration date management

[0052] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0053] Example: If there is food with an expiration date within one month, this information is notified to the store terminal, and employees prioritize putting those foods on the sales floor.

[0054] 6. Real-time inventory tracking

[0055] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0056] Example: If a particular product is about to sell out faster than expected, that information is immediately communicated to the server, which notifies the customer that more needs to be ordered.

[0057] 7. Warnings and Notifications

[0058] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0059] Example: A terminal sends a notice to a customer to offer a discount sale on a slow-selling item, and an employee lowers the price that day.

[0060] In this way, the inventory management system of the present invention enables proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, solving many problems related to inventory management.

[0061] The processing flow will be explained below.

[0062] Step 1: Data collection

[0063] The server automatically collects past sales data and seasonal data from stores and terminals, and aggregates the sales data after closing each day and stores it in a database.

[0064] Step 2: Preprocessing the data

[0065] The server normalizes the collected data and formats it in a format suitable for analysis, for example, by unifying data in different formats and imputing missing values.

[0066] Step 3: Generate a predictive model

[0067] The server creates a demand forecasting model using machine learning algorithms based on normalized sales data and seasonal data, performs statistical analysis, and applies regression analysis and time series analysis.

[0068] Step 4: Run a demand forecast

[0069] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. For example, it calculates demand for one month ahead and stores it in a database.

[0070] Step 5: Calculate the replenishment amount

[0071] The server calculates the optimal replenishment amount based on the predicted demand, taking into account the safety stock amount, calculates the order amount, and formulates a replenishment plan.

[0072] Step 6: Automated Order Processing

[0073] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[0074] Step 7: Inventory expiration management

[0075] The server tracks expiration dates recorded in the inventory database and creates a list of products with expiration dates within one month.

[0076] Step 8: Notification of Priority Sale

[0077] The server notifies the store terminal of the priority sales list, and instructs employees to display products with an approaching expiration date at the front of the shelves.

[0078] Step 9: Real-time inventory monitoring

[0079] The server collects inventory data from stores and warehouses in real time and updates the database as needed. Scanned information from barcode scanners is instantly reflected.

[0080] Step 10: Detect anomalies

[0081] The server detects slow-selling items and items with low stock from the collected real-time inventory data and analyzes the information.

[0082] Step 11: Generate warnings

[0083] The server generates warnings for low stock or slow-selling items based on the configured thresholds and records the warning information in a database.

[0084] Step 12: Sending notifications

[0085] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[0086] Step 13: Take Action

[0087] The terminal receives the notification and the user (employee) takes appropriate action, such as placing new items on the sales floor or checking inventory.

[0088] Step 14: Feedback on results

[0089] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after changing sales areas.

[0090] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory.

[0091] Example 1

[0092] 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."

[0093] Conventional inventory management systems require a lot of manual work in demand forecasting, inventory replenishment, and inventory expiration date management, which can lead to errors and reduced efficiency. Additionally, it is difficult to track inventory in real time, making it difficult to properly manage inventory shortages and excesses.

[0094] 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.

[0095] In this invention, the server includes means for collecting past sales data and seasonal data, means for generating a machine learning model that predicts demand based on the collected data, means for calculating the optimal replenishment amount based on the predicted demand and automatically placing an order, means for tracking the expiration dates of inventory items and notifying employees to prioritize the sale of items with upcoming expiration dates, means for collecting inventory data in real time and monitoring product sales and inventory status, and means for generating real-time alerts for items that are not selling well or are low in stock and notifying them to employee terminals. This automates many manual tasks related to inventory management, enabling efficient and accurate inventory management.

[0096] "Sales Data" refers to all information related to product sales, such as the sales quantity, sales date, and sales price of each product.

[0097] "Seasonal Data" refers to information that indicates fluctuations in demand associated with particular seasons or events.

[0098] "Machine learning model" refers to the algorithm used to forecast demand based on collected data.

[0099] "Replenishment quantity" refers to the quantity of an item required to maintain optimal inventory levels based on forecasted demand.

[0100] "Placing an order" refers to the act of requesting a supplier to supply goods based on the required replenishment quantity of the goods.

[0101] "Expiration date" refers to the period during which the quality of an item in stock is guaranteed, after which the item may deteriorate.

[0102] "Tracking" refers to the act of continuously collecting and tracking data by monitoring the location, condition, and quantity of inventory items.

[0103] "Real-time" refers to processing and data updates occurring in actual time.

[0104] "Terminal" refers to the device that a user (employee) uses to access the system, providing an interface for checking inventory information and notifications.

[0105] An "alert" is a notification generated when an abnormality is detected in inventory management or sales, and includes information to prompt employees to take necessary action.

[0106] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0107] 1. System Configuration

[0108] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings. The terminals provide an interface for employees to check inventory information and alerts in real time. Users check inventory information through the terminals and take necessary actions.

[0109] 2. Data Collection

[0110] The server periodically collects past sales data and seasonality data from each store and terminal. The sales data includes the sales quantity, sale date, and sales price of each product. The seasonality data indicates fluctuations in demand related to specific seasons or events.

[0111] Examples:

[0112] A store sells a large number of certain products (e.g., holiday decorations) during the Christmas season, and this information is registered in the system.

[0113] 3. Generate a predictive model

[0114] The server performs analysis based on the collected sales data and seasonal data, and generates a demand forecasting model using statistical analysis and machine learning algorithms.

[0115] Software used:

[0116] Machine learning libraries (e.g., Tensorflow, scikit-learn)

[0117] 4. Automatic replenishment and ordering

[0118] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0119] Examples:

[0120] Before December arrives, additional orders are automatically placed to ensure there are no shortages of predicted Christmas-related products.

[0121] 5. Inventory expiration date management

[0122] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0123] Examples:

[0124] If there is food with an expiration date within one month, this information is notified to the store terminal, and employees will prioritize putting those foods on the sales floor.

[0125] 6. Real-time inventory tracking

[0126] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0127] Examples:

[0128] If a particular product is likely to sell out sooner than expected, this information is immediately communicated to the server, which will notify the customer of the need to order more.

[0129] 7. Warnings and Notifications

[0130] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0131] Examples:

[0132] Discount sale instructions for slow-selling items are sent to the terminal, and employees lower the prices that day.

[0133] Prompt Sentence Examples

[0134] Here are some example prompts for a generative AI model:

[0135] "Predict next week's demand based on this week's sales data and seasonality data."

[0136] "Please tell me which products on your inventory list have an expiration date within one month."

[0137] "Make a list of products that need to be automatically ordered based on sales data for a specific period."

[0138] In this way, the inventory management system of the invention achieves proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, thereby solving many problems related to inventory management.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1: Data collection

[0141] The server periodically collects past sales data and seasonal data from each store and terminal. As input, it receives sales data extracted from each store's POS system and seasonal data from pre-set calendar events. Specifically, the server automatically saves this data in a database at midnight every night. As output, it generates sales data and seasonal data organized in a database.

[0142] Step 2: Data normalization

[0143] The server normalizes the collected data and formats it in a format suitable for analysis. The input for this step is the sales and seasonality data collected in step 1. The server performs specific operations to unify the data formats and correct inconsistent data. The output is data formatted for analysis.

[0144] Step 3: Generate a predictive model

[0145] The server generates a demand forecasting model based on the normalized data using a machine learning library (e.g., TensorFlow, scikit-learn). The formatted sales data and seasonality data are used as input. Specifically, the server trains the demand forecasting model using statistical analysis and machine learning algorithms. The output is a highly accurate demand forecasting model.

[0146] Step 4: Demand forecast and replenishment calculation

[0147] The server uses the generated forecasting model to forecast future demand. Current sales data and seasonality data are used as input. Specific operations are performed to calculate optimal replenishment amounts based on the demand forecast. The output is data on the required replenishment amounts.

[0148] Step 5: Automated ordering

[0149] The server automatically sends an order instruction to the ERP system based on the calculated replenishment amount. The replenishment amount data and supplier information obtained in step 4 are used as input. Specifically, the server sends the order data to the ERP system via API. The output is an order instruction to the supplier.

[0150] Step 6: Expiration Management

[0151] The server tracks the expiration dates of items in stock and notifies store terminals to prioritize sales of items approaching their expiration date. Stock information and expiration date data are used as input. Specifically, the server lists items that are approaching their expiration date at 10:00 every day and sends a notification to the store terminal. The output is expiration date information that employees can check.

[0152] Step 7: Real-time inventory tracking

[0153] The server monitors inventory data in real time, tracking product sales and stock status. Sales data continuously obtained from the POS system is used as input. Specifically, the server updates the database with the obtained data, reflecting the stock status in real time. The output is always the latest inventory information.

[0154] Step 8: Alert Generation and Notification

[0155] When the server detects anomalies such as inventory levels or poor sales, it generates alerts in real time and notifies employees' devices. Continuously monitored inventory data and threshold settings are used as input. Specifically, the server monitors the configured thresholds, and when an anomaly is detected, it immediately generates an alert and sends a push notification to the device. The output is warning information that employees can check on their devices.

[0156] (Application example 1)

[0157] 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."

[0158] Traditional inventory management systems are unable to respond quickly to fluctuations in demand, making them prone to problems such as stockouts and excess inventory. Furthermore, managing expiration dates for inventory items is often done manually, resulting in inefficiencies. Furthermore, it is difficult for employees to grasp inventory information in real time, which can delay appropriate action. There is a need to solve these problems and improve the efficiency and optimization of store management.

[0159] 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.

[0160] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and notifying alerts in real time about items that are not selling well or are low in stock; and means for store employees to check inventory information in real time using mobile devices and automatically place orders based on demand forecasts created by machine learning models. This enables efficient and reliable demand forecasting and inventory management.

[0161] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[0162] "Past sales data" refers to historical data such as sales quantity, sales date, and sales price of each product.

[0163] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[0164] "Predictive algorithms" refer to mathematical techniques and machine learning models that analyze collected data and forecast future demand.

[0165] "Replenishment amount" is the additional amount of product calculated to maintain appropriate inventory based on predicted demand.

[0166] An "order" is a purchasing instruction given to a supplier to replenish goods or secure inventory.

[0167] "Expiration date management" is a management method that tracks the expiration dates of inventory items and prioritizes the sale of items with upcoming expiration dates.

[0168] "Real-time collection" refers to the process of acquiring inventory and sales data in real time and making it immediately available for use.

[0169] "Sales" is an indicator of how quickly a particular product is being sold.

[0170] "Stock status" is information that indicates the current stock level and stock status.

[0171] "Warnings" are notification messages generated in response to abnormal inventory or sales conditions.

[0172] "Mobile device" refers to a portable electronic device such as a mobile phone or tablet.

[0173] A "machine learning model" is a statistical model that learns patterns and trends based on data and makes future predictions and classifications.

[0174] "Automatic ordering" refers to the process by which a system automatically generates and sends product ordering instructions to a supplier.

[0175] System configuration

[0176] This invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking. The system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time. In terms of specific hardware, the server requires a high-performance database server and computing power capable of running machine learning models, while smartphones and tablets are used as terminals.

[0177] Data collection

[0178] The server periodically collects past sales data and seasonal data from stores and terminals. Sales data includes the sales quantity, sale date, and sales price of each product. Seasonal data includes information indicating fluctuations in demand related to specific seasons and events. For example, it includes data showing that a particular product sells in large quantities during the Christmas season. This process uses API communication technologies such as the requests library.

[0179] Generate predictive models

[0180] The server analyzes the collected sales data and seasonal data to generate a demand forecasting model. This model is generated using statistical analysis and machine learning algorithms. Specifically, it uses linear regression from scikit-learn to predict future demand with high accuracy. When generating the model, the data is normalized and formatted appropriately.

[0181] Automated replenishment and ordering

[0182] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory. For example, additional orders are automatically placed before December to ensure there are no shortages of predicted Christmas-related products.

[0183] Inventory expiration date management

[0184] The server tracks the expiration dates of inventory items and notifies store terminals to prioritize sales of items approaching their expiration date. This expiration date data is sent to the server in real time, and employees are instructed to prioritize those items on the sales floor.

[0185] Real-time inventory tracking

[0186] The server monitors inventory data in real time, tracking product sales and stock status. This allows for timely detection of problems such as shortages or excess inventory. For example, information about a product that is likely to sell out faster than expected is immediately transmitted to the server, and a notification is sent to inform the customer of the need to order more.

[0187] Alerts and Notifications

[0188] When the server detects an abnormality in inventory or poor sales, it generates a real-time warning and notifies the employee's terminal. Employees can then take appropriate measures based on the notification. Instructions for discount sales of poorly selling items are sent to the terminal, and employees can lower the price that day.

[0189] Utilizing mobile devices

[0190] Employees can access inventory information in real time using their mobile devices, and machine learning models automatically place orders based on demand forecasts, enabling faster and more efficient in-store response.

[0191] Examples and prompts

[0192] For example, if a store experiences a sudden drop in its stock of Christmas trees, one scenario could be to detect this drop, use a demand forecasting model to predict future inventory shortages, and automatically place new orders.

[0193] Prompt Sentence Examples

[0194] "Describe a system that automatically places orders based on real-time inventory status and demand forecasts for specific items in a store. For example, include a scenario in which a sudden drop in Christmas tree inventory is detected, a demand forecasting model is used to predict future shortages, and a new order is automatically placed."

[0195] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0196] Step 1:

[0197] The server collects past sales data and seasonal data through API. The server uses the requests library to retrieve data from the specified API and stores the retrieved data in an internal database. Through this process, sales data and seasonal data are collected on the server. The input is raw data retrieved from the API, and the output is organized data stored in the internal database.

[0198] Step 2:

[0199] The server normalizes the collected data and formats it into a format suitable for analysis. The server organizes the data, completes missing values, and removes unnecessary data. This process involves data cleansing. The input is raw data, and the output is normalized data.

[0200] Step 3:

[0201] The server generates a demand forecasting model based on the normalized data. The server uses scikit-learn's LinearRegression to train the forecasting model using past sales data and seasonal data. The input is the normalized sales data and seasonal data, and the output is the trained forecasting model.

[0202] Step 4:

[0203] The server uses the generated forecasting model to predict future demand. The server forecasts demand for a set period (e.g., one month in the future) and uses the results as the basis for replenishment calculations. The inputs are the trained forecasting model and the forecast period, and the output is the future demand amount.

[0204] Step 5:

[0205] The server calculates the optimal replenishment amount based on future demand and automatically sends ordering instructions to the supplier. The server compares the predicted demand with the current inventory and orders the shortage. The input is the future demand and the current inventory, and the output is an ordering instruction to the supplier.

[0206] Step 6:

[0207] The server tracks the expiration dates of inventory items and generates notifications to prioritize the sale of items with upcoming expiration dates. The server scans inventory data, generates a list of items that are about to expire, and notifies the store terminal of that information. The input is inventory data, and the output is a list of items with upcoming expiration dates and notifications.

[0208] Step 7:

[0209] The server monitors inventory data in real time, tracking product sales and stock status. The server receives data from stores and terminals in real time and keeps track of the overall inventory status. The input is inventory data that is updated in real time, and the output is the latest inventory status.

[0210] Step 8:

[0211] The server detects abnormal inventory levels or poor sales, generates warnings in real time, and notifies employees' devices. The server detects abnormalities based on pre-set thresholds and sends warnings urging them to take necessary measures. The input is inventory data and sales data, and the output is a warning message.

[0212] Step 9:

[0213] A user uses a mobile device to check inventory information in real time and the status of automatic orders. The user uses a mobile app to monitor inventory status and the status of order instructions in real time. The input is the mobile device interface operations and data sent from the server, and the output is the displayed inventory information and order status.

[0214] 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.

[0215] The present invention relates to an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions, and specific embodiments thereof will be described below.

[0216] 1. System Configuration

[0217] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[0218] 2. Data Collection

[0219] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[0220] Furthermore, the emotion engine recognizes the user's emotions and collects emotion data, which is obtained from facial expressions and voices when the user views or purchases a product.

[0221] 3. Preprocessing and Prediction Model Generation

[0222] The server normalizes the collected sales data, seasonal data, and sentiment data and formats it in a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. Statistical analysis is performed, and regression analysis and time series analysis are applied.

[0223] 4. Demand forecasting and replenishment planning

[0224] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. It also takes into account emotional data and predicts that demand for products with positive user sentiment will increase. It calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[0225] 5. Inventory expiration date management and priority sales

[0226] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying those items.

[0227] 6. Real-time inventory tracking and alerts

[0228] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates appropriate warnings. The warnings also take into account the user's emotional data, and for example, warn users to be especially careful about products that generate a lot of negative emotions.

[0229] 7. Notifications and Actions

[0230] The server then sends the generated alerts to the employee's terminal, where the employee can check the notifications and take appropriate action, such as reordering low-stock items or starting a discount sale on slow-selling items.

[0231] Specific examples

[0232] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[0233] In this way, the inventory management system of the present invention realizes appropriate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data.

[0234] The processing flow will be explained below.

[0235] Step 1: Collect sales data

[0236] The server automatically collects past sales data from stores and terminals, and stores the data, such as the sales quantity, sale date, and sales price of each product, in a database after the store closes each day.

[0237] Step 2: Collect seasonal data

[0238] The server collects external seasonal data (e.g., holidays and events) and integrates it with sales data, allowing you to understand fluctuations in demand due to seasons or specific events.

[0239] Step 3: Collecting emotion data

[0240] The emotion engine recognizes emotions from the user's facial expressions and voice and collects that data, for example, analyzing the smile and tone of voice of a user looking at a product.

[0241] Step 4: Data normalization and preprocessing

[0242] The server normalizes the collected sales, seasonality, and sentiment data, unifying data from different formats and making it suitable for analysis.

[0243] Step 5: Generate a demand forecast model

[0244] The server uses the normalized data to perform statistical analysis and generate a demand forecasting model using machine learning algorithms, such as applying regression analysis or time series analysis.

[0245] Step 6: Run a demand forecast

[0246] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Taking sentiment data into consideration, the server predicts that demand for products with a high number of positive responses will increase.

[0247] Step 7: Calculate the replenishment amount

[0248] The server calculates the replenishment amount based on the predicted demand and safety stock amount, determines the order amount, and creates a replenishment plan.

[0249] Step 8: Execute automatic purchase orders

[0250] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[0251] Step 9: Inventory expiration management

[0252] The server tracks expiration dates for inventory items and creates a list of items with expiration dates within one month.

[0253] Step 10: Notification of Priority Sale

[0254] The server notifies the store terminal of the priority sales list and instructs the store staff to display products with an approaching expiration date at the front of the shelves.

[0255] Step 11: Real-time inventory monitoring

[0256] The server collects inventory data from stores and warehouses in real time and updates the database, with barcode scan information instantly reflected.

[0257] Step 12: Detect anomalies

[0258] The server analyzes real-time inventory data to detect slow-selling or low-stock items, and also takes user sentiment data into account.

[0259] Step 13: Generate warnings

[0260] The server generates warnings based on detected anomalies, such as low stock or slow-selling items, and based on sentiment data, flags items with particularly negative reactions.

[0261] Step 14: Notification of warnings

[0262] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[0263] Step 15: Take Action

[0264] The device receives the notification and the user (employee) takes appropriate action, for example, starting a discount sale on a slow-selling item.

[0265] Step 16: Feedback on results

[0266] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after a price reduction.

[0267] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory, while also achieving highly accurate management by utilizing user emotional data.

[0268] Example 2

[0269] 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."

[0270] Conventional inventory management systems lacked the efficiency of demand forecasting and inventory replenishment, making it difficult to track inventory status in real time or to make accurate demand forecasts based on user sentiment.In addition, due to a lack of effective management of inventory expiration dates and insufficient notification of warnings to terminals, problems such as stockouts and excess inventory frequently occurred, making it impossible to achieve efficient inventory management.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes a means for collecting past sales information and seasonal data for demand forecasting, a means for executing an algorithm for forecasting demand based on the collected data, and a means for calculating replenishment amounts and automatically placing orders based on the forecasted demand. This enables highly accurate demand forecasting and inventory management. Furthermore, by adding a means for recognizing and collecting user emotions using an emotion engine and a means for analyzing the emotion data and reflecting it in the demand forecast, even more accurate demand forecasting can be achieved.

[0273] In this invention, the server includes a means for managing the expiration dates of inventory items and prioritizing the sale of items with upcoming expiration dates, a means for collecting inventory data in real time and monitoring sales and inventory status, and a means for generating and notifying warnings in real time for items that are not selling well or are low in stock, thereby improving the accuracy of inventory management and enabling efficient inventory management.

[0274] In this invention, the server includes means for normalizing collected data and converting it into a format suitable for analysis, and means for notifying a terminal of an alert and prompting an employee to take appropriate action, thereby improving the quality of data analysis and enabling employees to take prompt and appropriate inventory management actions.

[0275] "Demand forecasting" is the process of predicting future demand for a product based on past sales information and seasonal data.

[0276] "Sales information" refers to information including data such as the sales quantity, sales date, and sales price of a product.

[0277] "Seasonal data" is information about fluctuations in demand related to specific seasons or events.

[0278] An "algorithm" is a set of calculation procedures for analyzing collected data and forecasting demand.

[0279] The "replenishment amount" is the quantity of the product to be replenished, calculated based on the demand forecast.

[0280] "Placing an order" is the procedure for requesting a supplier to supply goods.

[0281] The "validity period" indicates the period during which the quality of the stocked product can be guaranteed.

[0282] "Priority sales" is a method of preventing waste by selling products that are nearing their expiration date first.

[0283] "Inventory data" is information about the quantity and condition of inventory items.

[0284] "Real-time" means that data is collected and processed immediately.

[0285] "Warning" is information that notifies you in advance of a problem based on real-time monitoring results.

[0286] "Notification" means informing employees of warnings or important information.

[0287] The "emotion engine" is a mechanism that recognizes the user's emotions and collects that data.

[0288] "Emotion data" is information about emotions acquired from the user's facial expressions and voice.

[0289] "Normalization" is a process for adjusting variations in data and making it consistent.

[0290] "Terminal" refers to a computer system or device used by an employee.

[0291] "Appropriate action" refers to the specific response actions that an employee should take after receiving a notification or warning.

[0292] The present invention is an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0293] 1. System Configuration

[0294] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[0295] 2. Data Collection

[0296] The server collects the following data from stores and devices:

[0297] Sales information: the quantity sold, the date of sale, and the price of each product. This is stored in a database.

[0298] Seasonal Data: Information about fluctuations in demand related to specific seasons or events, such as Christmas or New Year sales.

[0299] Emotion data: Emotion data obtained from the user's facial expressions and voice. The emotion engine analyzes this in real time and sends it to the server as positive or negative emotions.

[0300] 3. Data Preprocessing

[0301] The server normalizes the collected data and converts it into a format suitable for analysis, ensuring data consistency and quality. Specifically, it performs the following operations:

[0302] Imputing or removing missing data

[0303] Filtering Unwanted Data

[0304] Data format conversion (e.g., standardization of date data)

[0305] 4. Generate a demand forecast model

[0306] The server generates a demand forecasting model using machine learning algorithms (such as TensorFlow or scikit-learn) based on the normalized data. This process includes the following steps:

[0307] Splitting the training data (training / testing set)

[0308] Feature extraction

[0309] Training and evaluating models (e.g., regression and time series analysis)

[0310] 5. Demand forecasting and replenishment planning

[0311] The server uses the generated demand forecasting model to predict future demand. In particular, it takes into account emotional data, predicting high demand for products with a high level of positive emotion. This prediction result is stored in a database, and an optimal replenishment plan is created. This includes the following factors:

[0312] Calculating replenishment quantities based on forecasted demand

[0313] Determining replenishment timing

[0314] Automatically send purchase orders to suppliers

[0315] 6. Inventory shelf life management

[0316] The server tracks the expiration dates of items in stock and adds items approaching their expiration date to the priority sales list. Specifically, it:

[0317] Analysis of shelf life data

[0318] Generate and update preferred sales lists

[0319] Device notifications

[0320] 7. Real-time inventory tracking

[0321] The server monitors inventory in real time to detect slow-selling or low-stock items, including:

[0322] Real-time inventory updates

[0323] Sales data analysis

[0324] Generate inventory alerts

[0325] 8. Warning notice

[0326] The server then sends the generated alerts to employees' devices. These alerts include warnings about low stock and slow-selling items. The system also incorporates user sentiment data, so that special attention is given to items with particularly negative sentiment.

[0327] 9. Action Execution

[0328] The device displays a notification to the employee, who then takes appropriate action, for example:

[0329] Reordering out-of-stock items

[0330] Prioritize display of products with upcoming expiration dates

[0331] Discount sales on slow-selling products

[0332] Examples and prompts

[0333] For example, if product A is predicted to be in high demand during the Christmas season and the sentiment data indicates that there will be a lot of positive reactions, the server will perform the following actions:

[0334] Automatically place large orders for product A

[0335] Rapidly develop replenishment plans

[0336] Inform stores about inventory status and replenishment plans

[0337] Example prompt for a generative AI model:

[0338] "Please suggest a demand forecast and replenishment plan for specific product A during the Christmas season based on store sales data and user sentiment data."

[0339] As described above, this inventory management system achieves efficient and highly accurate inventory management through a series of processes including data collection, analysis, prediction, notification, and execution.

[0340] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0341] Program processing flow

[0342] Step 1: Data collection

[0343] The server collects sales information, seasonal data, and emotion data from stores and terminals.

[0344] Input: Sales quantity, sales date, sales price of each product, seasonal event related information, and user sentiment data.

[0345] Specific operation: The server accesses the database and downloads sales information and seasonal data. Then, it collects emotion data from the user's facial expressions and voice in real time through the emotion engine.

[0346] Output: The collected data is stored in the data storage on the server.

[0347] Step 2: Data Preprocessing

[0348] The server normalizes the collected data and formats it into a format suitable for analysis.

[0349] Input: Collected sales information, seasonal data, and sentiment data.

[0350] Specific operations: The server completes missing data, filters unnecessary data, and converts date data into a unified format to ensure data consistency.

[0351] Output: A normalized and shaped dataset is generated and passed to the analysis module.

[0352] Step 3: Generate a demand forecast model

[0353] The server generates a demand forecasting model using a machine learning algorithm based on the normalized data.

[0354] Input: Normalized sales information, seasonal data, and sentiment data.

[0355] How it works: The server uses TensorFlow and scikit-learn to split the training data and extract features, then applies regression and time series analysis to train the model and evaluate its accuracy.

[0356] Output: An optimized demand forecast model is created and saved.

[0357] Step 4: Demand forecast

[0358] The server uses the generated demand forecasting model to predict future demand.

[0359] Inputs: Demand forecasting model, latest sales information, seasonal data, and sentiment data.

[0360] How it works: The server inputs the latest data into the model, performs a predictive calculation, and calculates demand. Products with a high level of positive sentiment are predicted to be in high demand.

[0361] Output: The forecasted demand information is stored in a database.

[0362] Step 5: Generate replenishment plan

[0363] The server creates an optimal replenishment plan based on the predicted demand.

[0364] Input: Forecasted demand information.

[0365] Specific operation: The server calculates the replenishment amount, determines the replenishment timing, and generates automatic ordering instructions to the supplier.

[0366] Output: Replenishment plans and purchase orders are generated and sent to suppliers.

[0367] Step 6: Inventory shelf life control

[0368] The server tracks the expiration dates of inventory items and adds items approaching expiration to a priority sales list.

[0369] Input: Inventory item shelf life data.

[0370] Specific operation: The server analyzes the expiration date and detects products that are close to expiring, creates a priority sales list, and notifies the terminal.

[0371] Output: A priority sales list is generated and sent to the store terminal.

[0372] Step 7: Real-time inventory tracking

[0373] The server monitors inventory in real time and detects slow-selling or low-stock items.

[0374] Input: Real-time inventory data, sales data.

[0375] What it does: The server updates inventory data in real time, analyzes sales data, and generates stock alerts as needed.

[0376] Output: Real-time inventory status and alert notifications are generated.

[0377] Step 8: Warning Notification

[0378] The server notifies the employee's terminal of the generated warning.

[0379] Input: The generated warning data.

[0380] Specific operation: The server sends a warning to the user's device and displays a notification, and gives special attention to products with particularly high levels of negative sentiment.

[0381] Output: A warning notification is sent and displayed on the terminal.

[0382] Step 9: Take Action

[0383] The device displays a notification to the employee, who then takes appropriate action.

[0384] Inputs: Alert notifications, real-time inventory data.

[0385] Specific actions: Employees check the notifications on their devices and take measures such as ordering more items that are out of stock, prioritizing the display of items that are about to expire, and offering discounts on items that are not selling well.

[0386] Output: Action information taken by the employee is reflected in the system.

[0387] Specific examples and prompt sentences are as described above.

[0388] (Application example 2)

[0389] 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."

[0390] Conventional inventory management systems have low accuracy in demand forecasting and inventory replenishment, resulting in problems such as stockouts and excess inventory. Furthermore, because demand forecasts are based on factors other than user sentiment, there is a high risk of missing sales opportunities. Furthermore, it is difficult for employees to take appropriate action at the right time, resulting in reduced efficiency in inventory management.

[0391] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0392] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and issuing warnings in real time for items that are selling poorly or have low inventory; means for recognizing user emotions and optimizing demand forecasting and inventory replenishment based on the emotion data; means for preferentially reflecting items with a high degree of positive emotion in a replenishment plan based on the collected emotion data; means for notifying an employee of the inventory status and warnings in real time to the employee's mobile device and instructing the employee to take appropriate action; and a mobile device with an interface function for notifying the employee of the inventory status and necessary actions. This enables demand forecasting and efficient inventory management using user emotion data.

[0393] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[0394] "Sales data" refers to data that includes information such as the sales quantity, sales date, and sales price of each product.

[0395] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[0396] An "algorithm" is a computational method for analyzing collected data and forecasting demand.

[0397] "Replenishment quantity" is the quantity of an item needed to replenish inventory based on forecasted demand.

[0398] "Placing an order" is the act of requesting a supplier to replenish goods.

[0399] "Inventory items" are items stored in stores or warehouses.

[0400] "Expiration date" refers to the date by which the product can be used.

[0401] "Priority sales" means selling products with an approaching expiration date first.

[0402] "Inventory data" is information about the quantity and condition of inventory items.

[0403] "Real-time" means that data and information are updated instantly and immediately reflect the current state.

[0404] A "warning" is an alert that notifies the user when a problem occurs.

[0405] "Notification" is the act of informing employees of important information.

[0406] "User emotion" refers to emotional information obtained from the user's facial expressions and voice when viewing or purchasing a product.

[0407] "Emotion data" is data relating to the user's emotions.

[0408] A "portable device" is a terminal that an employee can carry with them.

[0409] "Interface functions" are functions that allow a user to interact with a device or system.

[0410] The inventory management system of the present invention combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. This system is composed of a server, terminals, users (employees), and an emotion engine.

[0411] 1. System Configuration

[0412] The server has functions for data collection, analysis, forecasting, replenishment calculation, ordering, inventory management, warning notifications, and emotional data analysis. It also collects and analyzes user emotional data recognized by the emotion engine.

[0413] 2. Data Collection

[0414] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sales price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons and events. In addition, the emotion engine obtains emotion data from the user's facial expressions and voice and sends it to the server.

[0415] 3. Preprocessing and Prediction Model Generation

[0416] The server normalizes the collected sales data, seasonal data, and sentiment data, converting them into a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. The algorithms used include linear regression and time series analysis.

[0417] 4. Demand forecasting and replenishment planning

[0418] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, predicting that demand for products with positive user sentiment will increase. Based on this prediction, the server calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[0419] 5. Inventory expiration date management and priority sales

[0420] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying them.

[0421] 6. Real-time inventory tracking and alerts

[0422] The server monitors inventory data in real time, tracking product sales and availability, detecting slow-selling or low-stock items and generating appropriate alerts, taking user sentiment data into account.

[0423] 7. Notifications and Actions

[0424] The server notifies the employee of the generated alerts via their mobile device. The employee can then view the alerts on their mobile device and take appropriate action, such as placing an order for an item that is low in stock or starting a discount sale on an item that is not selling well. The mobile device, equipped with an interface, notifies the employee of the inventory status and required actions in real time.

[0425] Specific examples

[0426] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[0427] Prompt Sentence Examples

[0428] "Based on December sales data, seasonal data for the Christmas season, and positive customer sentiment data, we would like you to forecast demand for specific confectionery products and create an appropriate replenishment plan."

[0429] As described above, the inventory management system of the present invention achieves accurate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data, thereby maximizing sales opportunities and streamlining inventory management.

[0430] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0431] Step 1:

[0432] Data collection

[0433] The server collects sales data, seasonal data, and emotion data. Sales data includes the sales quantity, sale date, and sale price of a product, while seasonal data includes fluctuations in demand related to specific seasons or events. Emotion data is obtained from the user's facial expressions and voice using an emotion engine. These data are sent to the server and stored. The inputs in this step are sales data, seasonal data, and emotion data, and the output is data stored in a unified format.

[0434] Step 2:

[0435] Data Preprocessing

[0436] The server normalizes the collected data and formats it in a format suitable for analysis. It standardizes the data and imputes missing values ​​or removes unnecessary data. It uses data stored in a uniform format as input and obtains preprocessed data as output, suitable for subsequent analysis or model generation.

[0437] Step 3:

[0438] Generate a demand forecast model

[0439] The server uses machine learning algorithms (e.g., linear regression, time series analysis) to create a demand forecasting model based on the preprocessed data. This model uses sales data, seasonal data, and sentiment data as inputs to predict future demand. The generated demand forecasting model is obtained as an output.

[0440] Step 4:

[0441] Demand forecasting

[0442] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, and it predicts that demand for products with positive user sentiment will increase. In this step, the demand forecasting model and forecast period data are used as input, and the predicted demand volume is obtained as output.

[0443] Step 5:

[0444] Replenishment planning and ordering

[0445] The server calculates the optimal replenishment amount based on the predicted demand and automatically sends order instructions to the supplier. It uses the predicted demand amount as input and gets the replenishment plan and order instructions as output.

[0446] Step 6:

[0447] Inventory expiration date management and priority sales

[0448] The server monitors the expiration dates of inventory items and creates a priority sales list for items approaching their expiration date. It notifies the terminal and instructs employees to prioritize the display of these items. It uses inventory data and expiration date data as input and obtains a priority sales list and notification as output.

[0449] Step 7:

[0450] Real-time inventory tracking and alerts

[0451] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates alerts and notifications in real time. It uses real-time inventory data as input and gets alerts and notifications as output.

[0452] Step 8:

[0453] Sending notifications and taking action

[0454] The server notifies the employee of the generated alert on their mobile device. The employee reviews the alert and takes appropriate action. The inputs are the alert and inventory data, and the output is the notification and the employee's action, which could include ordering more stock if inventory is low or starting a discount sale on a slow-selling item.

[0455] Through the above steps, the inventory management system of the present invention realizes appropriate demand forecasting and inventory management, thereby maximizing sales opportunities and improving the efficiency of inventory management.

[0456] 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.

[0457] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0458] 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.

[0459] [Second embodiment]

[0460] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0461] 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.

[0462] 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).

[0463] 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.

[0464] 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.

[0465] 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).

[0466] 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.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] In the smart glasses 214, 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.

[0471] 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."

[0472] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0473] 1. System Configuration

[0474] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time.

[0475] 2. Data Collection

[0476] The server periodically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, and the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[0477] Example: A store may sell a large number of certain products (e.g., holiday decorations) during the Christmas season. Based on this information, seasonal data is entered into the system.

[0478] 3. Generate a predictive model

[0479] The server analyzes the collected sales and seasonal data and generates a demand forecasting model using statistical analysis and machine learning algorithms. This model is used to predict future demand with high accuracy.

[0480] 4. Automatic replenishment and ordering

[0481] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0482] Example: Predicted Christmas items are automatically ordered before December to avoid shortages.

[0483] 5. Inventory expiration date management

[0484] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0485] Example: If there is food with an expiration date within one month, this information is notified to the store terminal, and employees prioritize putting those foods on the sales floor.

[0486] 6. Real-time inventory tracking

[0487] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0488] Example: If a particular product is about to sell out faster than expected, that information is immediately communicated to the server, which notifies the customer that more needs to be ordered.

[0489] 7. Warnings and Notifications

[0490] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0491] Example: A terminal sends a notice to a customer to offer a discount sale on a slow-selling item, and an employee lowers the price that day.

[0492] In this way, the inventory management system of the present invention enables proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, solving many problems related to inventory management.

[0493] The processing flow will be explained below.

[0494] Step 1: Data collection

[0495] The server automatically collects past sales data and seasonal data from stores and terminals, and aggregates the sales data after closing each day and stores it in a database.

[0496] Step 2: Preprocessing the data

[0497] The server normalizes the collected data and formats it in a format suitable for analysis, for example, by unifying data in different formats and imputing missing values.

[0498] Step 3: Generate a predictive model

[0499] The server creates a demand forecasting model using machine learning algorithms based on normalized sales data and seasonal data, performs statistical analysis, and applies regression analysis and time series analysis.

[0500] Step 4: Run a demand forecast

[0501] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. For example, it calculates demand for one month ahead and stores it in a database.

[0502] Step 5: Calculate the replenishment amount

[0503] The server calculates the optimal replenishment amount based on the predicted demand, taking into account the safety stock amount, calculates the order amount, and formulates a replenishment plan.

[0504] Step 6: Automated Order Processing

[0505] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[0506] Step 7: Inventory expiration management

[0507] The server tracks expiration dates recorded in the inventory database and creates a list of products with expiration dates within one month.

[0508] Step 8: Notification of Priority Sale

[0509] The server notifies the store terminal of the priority sales list, and instructs employees to display products with an approaching expiration date at the front of the shelves.

[0510] Step 9: Real-time inventory monitoring

[0511] The server collects inventory data from stores and warehouses in real time and updates the database as needed. Scanned information from barcode scanners is instantly reflected.

[0512] Step 10: Detect anomalies

[0513] The server detects slow-selling items and items with low stock from the collected real-time inventory data and analyzes the information.

[0514] Step 11: Generate warnings

[0515] The server generates warnings for low stock or slow-selling items based on the configured thresholds and records the warning information in a database.

[0516] Step 12: Sending notifications

[0517] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[0518] Step 13: Take Action

[0519] The terminal receives the notification and the user (employee) takes appropriate action, such as placing new items on the sales floor or checking inventory.

[0520] Step 14: Feedback on results

[0521] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after changing sales areas.

[0522] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory.

[0523] Example 1

[0524] 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."

[0525] Conventional inventory management systems require a lot of manual work in demand forecasting, inventory replenishment, and inventory expiration date management, which can lead to errors and reduced efficiency. Additionally, it is difficult to track inventory in real time, making it difficult to properly manage inventory shortages and excesses.

[0526] 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.

[0527] In this invention, the server includes means for collecting past sales data and seasonal data, means for generating a machine learning model that predicts demand based on the collected data, means for calculating the optimal replenishment amount based on the predicted demand and automatically placing an order, means for tracking the expiration dates of inventory items and notifying employees to prioritize the sale of items with upcoming expiration dates, means for collecting inventory data in real time and monitoring product sales and inventory status, and means for generating real-time alerts for items that are not selling well or are low in stock and notifying them to employee terminals. This automates many manual tasks related to inventory management, enabling efficient and accurate inventory management.

[0528] "Sales Data" refers to all information related to product sales, such as the sales quantity, sales date, and sales price of each product.

[0529] "Seasonal Data" refers to information that indicates fluctuations in demand associated with particular seasons or events.

[0530] "Machine learning model" refers to the algorithm used to forecast demand based on collected data.

[0531] "Replenishment quantity" refers to the quantity of an item required to maintain optimal inventory levels based on forecasted demand.

[0532] "Placing an order" refers to the act of requesting a supplier to supply goods based on the required replenishment quantity of the goods.

[0533] "Expiration date" refers to the period during which the quality of an item in stock is guaranteed, after which the item may deteriorate.

[0534] "Tracking" refers to the act of continuously collecting and tracking data by monitoring the location, condition, and quantity of inventory items.

[0535] "Real-time" refers to processing and data updates occurring in actual time.

[0536] "Terminal" refers to the device that a user (employee) uses to access the system, providing an interface for checking inventory information and notifications.

[0537] An "alert" is a notification generated when an abnormality is detected in inventory management or sales, and includes information to prompt employees to take necessary action.

[0538] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0539] 1. System Configuration

[0540] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings. The terminals provide an interface for employees to check inventory information and alerts in real time. Users check inventory information through the terminals and take necessary actions.

[0541] 2. Data Collection

[0542] The server periodically collects past sales data and seasonality data from each store and terminal. The sales data includes the sales quantity, sale date, and sales price of each product. The seasonality data indicates fluctuations in demand related to specific seasons or events.

[0543] Examples:

[0544] A store sells a large number of certain products (e.g., holiday decorations) during the Christmas season, and this information is registered in the system.

[0545] 3. Generate a predictive model

[0546] The server performs analysis based on the collected sales data and seasonal data, and generates a demand forecasting model using statistical analysis and machine learning algorithms.

[0547] Software used:

[0548] Machine learning libraries (e.g. TensorFlow, scikit-learn)

[0549] 4. Automatic replenishment and ordering

[0550] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0551] Examples:

[0552] Before December arrives, additional orders are automatically placed to ensure there are no shortages of predicted Christmas-related products.

[0553] 5. Inventory expiration date management

[0554] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0555] Examples:

[0556] If there is food with an expiration date within one month, this information is notified to the store terminal, and employees will prioritize putting those foods on the sales floor.

[0557] 6. Real-time inventory tracking

[0558] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0559] Examples:

[0560] If a particular product is likely to sell out sooner than expected, this information is immediately communicated to the server, which will notify the customer of the need to order more.

[0561] 7. Warnings and Notifications

[0562] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0563] Examples:

[0564] Discount sale instructions for slow-selling items are sent to the terminal, and employees lower the prices that day.

[0565] Prompt Sentence Examples

[0566] Here are some example prompts for a generative AI model:

[0567] "Predict next week's demand based on this week's sales data and seasonality data."

[0568] "Please tell me which products on your inventory list have an expiration date within one month."

[0569] "Make a list of products that need to be automatically ordered based on sales data for a specific period."

[0570] In this way, the inventory management system of the invention achieves proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, thereby solving many problems related to inventory management.

[0571] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0572] Step 1: Data collection

[0573] The server periodically collects past sales data and seasonal data from each store and terminal. As input, it receives sales data extracted from each store's POS system and seasonal data from pre-set calendar events. Specifically, the server automatically saves this data in a database at midnight every night. As output, it generates sales data and seasonal data organized in a database.

[0574] Step 2: Data normalization

[0575] The server normalizes the collected data and formats it in a format suitable for analysis. The input for this step is the sales and seasonality data collected in step 1. The server performs specific operations to unify the data formats and correct inconsistent data. The output is data formatted for analysis.

[0576] Step 3: Generate a predictive model

[0577] The server generates a demand forecasting model based on the normalized data using a machine learning library (e.g., TensorFlow, scikit-learn). The formatted sales data and seasonality data are used as input. Specifically, the server trains the demand forecasting model using statistical analysis and machine learning algorithms. The output is a highly accurate demand forecasting model.

[0578] Step 4: Demand forecast and replenishment calculation

[0579] The server uses the generated forecasting model to forecast future demand. Current sales data and seasonality data are used as input. Specific operations are performed to calculate optimal replenishment amounts based on the demand forecast. The output is data on the required replenishment amounts.

[0580] Step 5: Automated ordering

[0581] The server automatically sends an order instruction to the ERP system based on the calculated replenishment amount. The replenishment amount data and supplier information obtained in step 4 are used as input. Specifically, the server sends the order data to the ERP system via API. The output is an order instruction to the supplier.

[0582] Step 6: Expiration Management

[0583] The server tracks the expiration dates of items in stock and notifies store terminals to prioritize sales of items approaching their expiration date. Stock information and expiration date data are used as input. Specifically, the server lists items that are approaching their expiration date at 10:00 every day and sends a notification to the store terminal. The output is expiration date information that employees can check.

[0584] Step 7: Real-time inventory tracking

[0585] The server monitors inventory data in real time, tracking product sales and stock status. Sales data continuously obtained from the POS system is used as input. Specifically, the server updates the database with the obtained data, reflecting the stock status in real time. The output is always the latest inventory information.

[0586] Step 8: Alert Generation and Notification

[0587] When the server detects anomalies such as inventory levels or poor sales, it generates alerts in real time and notifies employees' devices. Continuously monitored inventory data and threshold settings are used as input. Specifically, the server monitors the configured thresholds, and when an anomaly is detected, it immediately generates an alert and sends a push notification to the device. The output is warning information that employees can check on their devices.

[0588] (Application example 1)

[0589] 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."

[0590] Traditional inventory management systems are unable to respond quickly to fluctuations in demand, making them prone to problems such as stockouts and excess inventory. Furthermore, managing expiration dates for inventory items is often done manually, resulting in inefficiencies. Furthermore, it is difficult for employees to grasp inventory information in real time, which can delay appropriate action. There is a need to solve these problems and improve the efficiency and optimization of store management.

[0591] 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.

[0592] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and notifying alerts in real time about items that are not selling well or are low in stock; and means for store employees to check inventory information in real time using mobile devices and automatically place orders based on demand forecasts created by machine learning models. This enables efficient and reliable demand forecasting and inventory management.

[0593] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[0594] "Past sales data" refers to historical data such as sales quantity, sales date, and sales price of each product.

[0595] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[0596] "Predictive algorithms" refer to mathematical techniques and machine learning models that analyze collected data and forecast future demand.

[0597] "Replenishment amount" is the additional amount of product calculated to maintain appropriate inventory based on predicted demand.

[0598] An "order" is a purchasing instruction given to a supplier to replenish goods or secure inventory.

[0599] "Expiration date management" is a management method that tracks the expiration dates of inventory items and prioritizes the sale of items with upcoming expiration dates.

[0600] "Real-time collection" refers to the process of acquiring inventory and sales data in real time and making it immediately available for use.

[0601] "Sales" is an indicator of how quickly a particular product is being sold.

[0602] "Stock status" is information that indicates the current stock level and stock status.

[0603] "Warnings" are notification messages generated in response to abnormal inventory or sales conditions.

[0604] "Mobile device" refers to a portable electronic device such as a mobile phone or tablet.

[0605] A "machine learning model" is a statistical model that learns patterns and trends based on data and makes future predictions and classifications.

[0606] "Automatic ordering" refers to the process by which a system automatically generates and sends product ordering instructions to a supplier.

[0607] System configuration

[0608] This invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking. The system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time. In terms of specific hardware, the server requires a high-performance database server and computing power capable of running machine learning models, while smartphones and tablets are used as terminals.

[0609] Data collection

[0610] The server periodically collects past sales data and seasonal data from stores and terminals. Sales data includes the sales quantity, sale date, and sales price of each product. Seasonal data includes information indicating fluctuations in demand related to specific seasons and events. For example, it includes data showing that a particular product sells in large quantities during the Christmas season. This process uses API communication technologies such as the requests library.

[0611] Generate predictive models

[0612] The server analyzes the collected sales data and seasonal data to generate a demand forecasting model. This model is generated using statistical analysis and machine learning algorithms. Specifically, it uses linear regression from scikit-learn to predict future demand with high accuracy. When generating the model, the data is normalized and formatted appropriately.

[0613] Automated replenishment and ordering

[0614] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory. For example, additional orders are automatically placed before December to ensure there are no shortages of predicted Christmas-related products.

[0615] Inventory expiration date management

[0616] The server tracks the expiration dates of inventory items and notifies store terminals to prioritize sales of items approaching their expiration date. This expiration date data is sent to the server in real time, and employees are instructed to prioritize those items on the sales floor.

[0617] Real-time inventory tracking

[0618] The server monitors inventory data in real time, tracking product sales and stock status. This allows for timely detection of problems such as shortages or excess inventory. For example, information about a product that is likely to sell out faster than expected is immediately transmitted to the server, and a notification is sent to inform the customer of the need to order more.

[0619] Alerts and Notifications

[0620] When the server detects an abnormality in inventory or poor sales, it generates a real-time warning and notifies the employee's terminal. Employees can then take appropriate measures based on the notification. Instructions for discount sales of poorly selling items are sent to the terminal, and employees can lower the price that day.

[0621] Utilizing mobile devices

[0622] Employees can access inventory information in real time using their mobile devices, and machine learning models automatically place orders based on demand forecasts, enabling faster and more efficient in-store response.

[0623] Examples and prompts

[0624] For example, if a store experiences a sudden drop in its stock of Christmas trees, one scenario could be to detect this drop, use a demand forecasting model to predict future inventory shortages, and automatically place new orders.

[0625] Prompt Sentence Examples

[0626] "Describe a system that automatically places orders based on real-time inventory status and demand forecasts for specific items in a store. For example, include a scenario in which a sudden drop in Christmas tree inventory is detected, a demand forecasting model is used to predict future shortages, and a new order is automatically placed."

[0627] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0628] Step 1:

[0629] The server collects past sales data and seasonal data through API. The server uses the requests library to retrieve data from the specified API and stores the retrieved data in an internal database. Through this process, sales data and seasonal data are collected on the server. The input is raw data retrieved from the API, and the output is organized data stored in the internal database.

[0630] Step 2:

[0631] The server normalizes the collected data and formats it into a format suitable for analysis. The server organizes the data, completes missing values, and removes unnecessary data. This process involves data cleansing. The input is raw data, and the output is normalized data.

[0632] Step 3:

[0633] The server generates a demand forecasting model based on the normalized data. The server uses scikit-learn's LinearRegression to train the forecasting model using past sales data and seasonal data. The input is the normalized sales data and seasonal data, and the output is the trained forecasting model.

[0634] Step 4:

[0635] The server uses the generated forecasting model to predict future demand. The server forecasts demand for a set period (e.g., one month in the future) and uses the results as the basis for replenishment calculations. The inputs are the trained forecasting model and the forecast period, and the output is the future demand amount.

[0636] Step 5:

[0637] The server calculates the optimal replenishment amount based on future demand and automatically sends ordering instructions to the supplier. The server compares the predicted demand with the current inventory and orders the shortage. The input is the future demand and the current inventory, and the output is an ordering instruction to the supplier.

[0638] Step 6:

[0639] The server tracks the expiration dates of inventory items and generates notifications to prioritize the sale of items with upcoming expiration dates. The server scans inventory data, generates a list of items that are about to expire, and notifies the store terminal of that information. The input is inventory data, and the output is a list of items with upcoming expiration dates and notifications.

[0640] Step 7:

[0641] The server monitors inventory data in real time, tracking product sales and stock status. The server receives data from stores and terminals in real time and keeps track of the overall inventory status. The input is inventory data that is updated in real time, and the output is the latest inventory status.

[0642] Step 8:

[0643] The server detects abnormal inventory levels or poor sales, generates warnings in real time, and notifies employees' devices. The server detects abnormalities based on pre-set thresholds and sends warnings urging them to take necessary measures. The input is inventory data and sales data, and the output is a warning message.

[0644] Step 9:

[0645] A user uses a mobile device to check inventory information in real time and the status of automatic orders. The user uses a mobile app to monitor inventory status and the status of order instructions in real time. The input is the mobile device interface operations and data sent from the server, and the output is the displayed inventory information and order status.

[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 relates to an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions, and specific embodiments thereof will be described below.

[0648] 1. System Configuration

[0649] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[0650] 2. Data Collection

[0651] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[0652] Furthermore, the emotion engine recognizes the user's emotions and collects emotion data, which is obtained from facial expressions and voices when the user views or purchases a product.

[0653] 3. Preprocessing and Prediction Model Generation

[0654] The server normalizes the collected sales data, seasonal data, and sentiment data and formats it in a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. Statistical analysis is performed, and regression analysis and time series analysis are applied.

[0655] 4. Demand forecasting and replenishment planning

[0656] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. It also takes into account emotional data and predicts that demand for products with positive user sentiment will increase. It calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[0657] 5. Inventory expiration date management and priority sales

[0658] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying those items.

[0659] 6. Real-time inventory tracking and alerts

[0660] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates appropriate warnings. The warnings also take into account the user's emotional data, and for example, warn users to be especially careful about products that generate a lot of negative emotions.

[0661] 7. Notifications and Actions

[0662] The server then sends the generated alerts to the employee's terminal, where the employee can check the notifications and take appropriate action, such as reordering low-stock items or starting a discount sale on slow-selling items.

[0663] Specific examples

[0664] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[0665] In this way, the inventory management system of the present invention realizes appropriate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data.

[0666] The processing flow will be explained below.

[0667] Step 1: Collect sales data

[0668] The server automatically collects past sales data from stores and terminals, and stores the data, such as the sales quantity, sale date, and sales price of each product, in a database after the store closes each day.

[0669] Step 2: Collect seasonal data

[0670] The server collects external seasonal data (e.g., holidays and events) and integrates it with sales data, allowing you to understand fluctuations in demand due to seasons or specific events.

[0671] Step 3: Collecting emotion data

[0672] The emotion engine recognizes emotions from the user's facial expressions and voice and collects that data, for example, analyzing the smile and tone of voice of a user looking at a product.

[0673] Step 4: Data normalization and preprocessing

[0674] The server normalizes the collected sales, seasonality, and sentiment data, unifying data from different formats and making it suitable for analysis.

[0675] Step 5: Generate a demand forecast model

[0676] The server uses the normalized data to perform statistical analysis and generate a demand forecasting model using machine learning algorithms, such as applying regression analysis or time series analysis.

[0677] Step 6: Run a demand forecast

[0678] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Taking sentiment data into consideration, the server predicts that demand for products with a high number of positive responses will increase.

[0679] Step 7: Calculate the replenishment amount

[0680] The server calculates the replenishment amount based on the predicted demand and safety stock amount, determines the order amount, and creates a replenishment plan.

[0681] Step 8: Execute automatic purchase orders

[0682] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[0683] Step 9: Inventory expiration management

[0684] The server tracks expiration dates for inventory items and creates a list of items with expiration dates within one month.

[0685] Step 10: Notification of Priority Sale

[0686] The server notifies the store terminal of the priority sales list and instructs the store staff to display products with an approaching expiration date at the front of the shelves.

[0687] Step 11: Real-time inventory monitoring

[0688] The server collects inventory data from stores and warehouses in real time and updates the database, with barcode scan information instantly reflected.

[0689] Step 12: Detect anomalies

[0690] The server analyzes real-time inventory data to detect slow-selling or low-stock items, and also takes user sentiment data into account.

[0691] Step 13: Generate warnings

[0692] The server generates warnings based on detected anomalies, such as low stock or slow-selling items, and based on sentiment data, flags items with particularly negative reactions.

[0693] Step 14: Notification of warnings

[0694] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[0695] Step 15: Take Action

[0696] The device receives the notification and the user (employee) takes appropriate action, for example, starting a discount sale on a slow-selling item.

[0697] Step 16: Feedback on results

[0698] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after a price reduction.

[0699] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory, while also achieving highly accurate management by utilizing user emotional data.

[0700] Example 2

[0701] 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."

[0702] Conventional inventory management systems lacked the efficiency of demand forecasting and inventory replenishment, making it difficult to track inventory status in real time or to make accurate demand forecasts based on user sentiment.In addition, due to a lack of effective management of inventory expiration dates and insufficient notification of warnings to terminals, problems such as stockouts and excess inventory frequently occurred, making it impossible to achieve efficient inventory management.

[0703] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0704] In this invention, the server includes a means for collecting past sales information and seasonal data for demand forecasting, a means for executing an algorithm for forecasting demand based on the collected data, and a means for calculating replenishment amounts and automatically placing orders based on the forecasted demand. This enables highly accurate demand forecasting and inventory management. Furthermore, by adding a means for recognizing and collecting user emotions using an emotion engine and a means for analyzing the emotion data and reflecting it in the demand forecast, even more accurate demand forecasting can be achieved.

[0705] In this invention, the server includes a means for managing the expiration dates of inventory items and prioritizing the sale of items with upcoming expiration dates, a means for collecting inventory data in real time and monitoring sales and inventory status, and a means for generating and notifying warnings in real time for items that are not selling well or are low in stock, thereby improving the accuracy of inventory management and enabling efficient inventory management.

[0706] In this invention, the server includes means for normalizing collected data and converting it into a format suitable for analysis, and means for notifying a terminal of an alert and prompting an employee to take appropriate action, thereby improving the quality of data analysis and enabling employees to take prompt and appropriate inventory management actions.

[0707] "Demand forecasting" is the process of predicting future demand for a product based on past sales information and seasonal data.

[0708] "Sales information" refers to information including data such as the sales quantity, sales date, and sales price of a product.

[0709] "Seasonal data" is information about fluctuations in demand related to specific seasons or events.

[0710] An "algorithm" is a set of calculation procedures for analyzing collected data and forecasting demand.

[0711] The "replenishment amount" is the quantity of the product to be replenished, calculated based on the demand forecast.

[0712] "Placing an order" is the procedure for requesting a supplier to supply goods.

[0713] The "validity period" indicates the period during which the quality of the stocked product can be guaranteed.

[0714] "Priority sales" is a method of preventing waste by selling products that are nearing their expiration date first.

[0715] "Inventory data" is information about the quantity and condition of inventory items.

[0716] "Real-time" means that data is collected and processed immediately.

[0717] "Warning" is information that notifies you in advance of a problem based on real-time monitoring results.

[0718] "Notification" means informing employees of warnings or important information.

[0719] The "emotion engine" is a mechanism that recognizes the user's emotions and collects that data.

[0720] "Emotion data" is information about emotions acquired from the user's facial expressions and voice.

[0721] "Normalization" is a process for adjusting variations in data and making it consistent.

[0722] "Terminal" refers to a computer system or device used by an employee.

[0723] "Appropriate action" refers to the specific response actions that an employee should take after receiving a notification or warning.

[0724] The present invention is an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[0725] 1. System Configuration

[0726] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[0727] 2. Data Collection

[0728] The server collects the following data from stores and devices:

[0729] Sales information: the quantity sold, the date of sale, and the price of each product. This is stored in a database.

[0730] Seasonal Data: Information about fluctuations in demand related to specific seasons or events, such as Christmas or New Year sales.

[0731] Emotion data: Emotion data obtained from the user's facial expressions and voice. The emotion engine analyzes this in real time and sends it to the server as positive or negative emotions.

[0732] 3. Data Preprocessing

[0733] The server normalizes the collected data and converts it into a format suitable for analysis, ensuring data consistency and quality. Specifically, it performs the following operations:

[0734] Imputing or removing missing data

[0735] Filtering Unwanted Data

[0736] Data format conversion (e.g., standardization of date data)

[0737] 4. Generate a demand forecast model

[0738] The server generates a demand forecasting model using machine learning algorithms (such as TensorFlow or scikit-learn) based on the normalized data. This process includes the following steps:

[0739] Splitting the training data (training / testing set)

[0740] Feature extraction

[0741] Training and evaluating models (e.g., regression and time series analysis)

[0742] 5. Demand forecasting and replenishment planning

[0743] The server uses the generated demand forecasting model to predict future demand. In particular, it takes into account emotional data, predicting high demand for products with a high level of positive emotion. This prediction result is stored in a database, and an optimal replenishment plan is created. This includes the following factors:

[0744] Calculating replenishment quantities based on forecasted demand

[0745] Determining replenishment timing

[0746] Automatically send purchase orders to suppliers

[0747] 6. Inventory shelf life management

[0748] The server tracks the expiration dates of items in stock and adds items approaching their expiration date to the priority sales list. Specifically, it:

[0749] Analysis of shelf life data

[0750] Generate and update preferred sales lists

[0751] Device notifications

[0752] 7. Real-time inventory tracking

[0753] The server monitors inventory in real time to detect slow-selling or low-stock items, including:

[0754] Real-time inventory updates

[0755] Sales data analysis

[0756] Generate inventory alerts

[0757] 8. Warning notice

[0758] The server then sends the generated alerts to employees' devices. These alerts include warnings about low stock and slow-selling items. The system also incorporates user sentiment data, so that special attention is given to items with particularly negative sentiment.

[0759] 9. Action Execution

[0760] The device displays a notification to the employee, who then takes appropriate action, for example:

[0761] Reordering out-of-stock items

[0762] Prioritize display of products with upcoming expiration dates

[0763] Discount sales on slow-selling products

[0764] Examples and prompts

[0765] For example, if product A is predicted to be in high demand during the Christmas season and the sentiment data indicates that there will be a lot of positive reactions, the server will perform the following actions:

[0766] Automatically place large orders for product A

[0767] Rapidly develop replenishment plans

[0768] Inform stores about inventory status and replenishment plans

[0769] Example prompt for a generative AI model:

[0770] "Please suggest a demand forecast and replenishment plan for specific product A during the Christmas season based on store sales data and user sentiment data."

[0771] As described above, this inventory management system achieves efficient and highly accurate inventory management through a series of processes including data collection, analysis, prediction, notification, and execution.

[0772] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0773] Program processing flow

[0774] Step 1: Data collection

[0775] The server collects sales information, seasonal data, and emotion data from stores and terminals.

[0776] Input: Sales quantity, sales date, sales price of each product, seasonal event related information, and user sentiment data.

[0777] Specific operation: The server accesses the database and downloads sales information and seasonal data. Then, it collects emotion data from the user's facial expressions and voice in real time through the emotion engine.

[0778] Output: The collected data is stored in the data storage on the server.

[0779] Step 2: Data Preprocessing

[0780] The server normalizes the collected data and formats it into a format suitable for analysis.

[0781] Input: Collected sales information, seasonal data, and sentiment data.

[0782] Specific operations: The server completes missing data, filters unnecessary data, and converts date data into a unified format to ensure data consistency.

[0783] Output: A normalized and shaped dataset is generated and passed to the analysis module.

[0784] Step 3: Generate a demand forecast model

[0785] The server generates a demand forecasting model using a machine learning algorithm based on the normalized data.

[0786] Input: Normalized sales information, seasonal data, and sentiment data.

[0787] How it works: The server uses TensorFlow and scikit-learn to split the training data and extract features, then applies regression and time series analysis to train the model and evaluate its accuracy.

[0788] Output: An optimized demand forecast model is created and saved.

[0789] Step 4: Demand forecast

[0790] The server uses the generated demand forecasting model to predict future demand.

[0791] Inputs: Demand forecasting model, latest sales information, seasonal data, and sentiment data.

[0792] How it works: The server inputs the latest data into the model, performs a predictive calculation, and calculates demand. Products with a high level of positive sentiment are predicted to be in high demand.

[0793] Output: The forecasted demand information is stored in a database.

[0794] Step 5: Generate replenishment plan

[0795] The server creates an optimal replenishment plan based on the predicted demand.

[0796] Input: Forecasted demand information.

[0797] Specific operation: The server calculates the replenishment amount, determines the replenishment timing, and generates automatic ordering instructions to the supplier.

[0798] Output: Replenishment plans and purchase orders are generated and sent to suppliers.

[0799] Step 6: Inventory shelf life control

[0800] The server tracks the expiration dates of inventory items and adds items approaching expiration to a priority sales list.

[0801] Input: Inventory item shelf life data.

[0802] Specific operation: The server analyzes the expiration date and detects products that are close to expiring, creates a priority sales list, and notifies the terminal.

[0803] Output: A priority sales list is generated and sent to the store terminal.

[0804] Step 7: Real-time inventory tracking

[0805] The server monitors inventory in real time and detects slow-selling or low-stock items.

[0806] Input: Real-time inventory data, sales data.

[0807] What it does: The server updates inventory data in real time, analyzes sales data, and generates stock alerts as needed.

[0808] Output: Real-time inventory status and alert notifications are generated.

[0809] Step 8: Warning Notification

[0810] The server notifies the employee's terminal of the generated warning.

[0811] Input: The generated warning data.

[0812] Specific operation: The server sends a warning to the user's device and displays a notification, and gives special attention to products with particularly high levels of negative sentiment.

[0813] Output: A warning notification is sent and displayed on the terminal.

[0814] Step 9: Take Action

[0815] The device displays a notification to the employee, who then takes appropriate action.

[0816] Inputs: Alert notifications, real-time inventory data.

[0817] Specific actions: Employees check the notifications on their devices and take measures such as ordering more items that are out of stock, prioritizing the display of items that are about to expire, and offering discounts on items that are not selling well.

[0818] Output: Action information taken by the employee is reflected in the system.

[0819] Specific examples and prompt sentences are as described above.

[0820] (Application example 2)

[0821] 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."

[0822] Conventional inventory management systems have low accuracy in demand forecasting and inventory replenishment, resulting in problems such as stockouts and excess inventory. Furthermore, because demand forecasts are based on factors other than user sentiment, there is a high risk of missing sales opportunities. Furthermore, it is difficult for employees to take appropriate action at the right time, resulting in reduced efficiency in inventory management.

[0823] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0824] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and issuing warnings in real time for items that are selling poorly or have low inventory; means for recognizing user emotions and optimizing demand forecasting and inventory replenishment based on the emotion data; means for preferentially reflecting items with a high degree of positive emotion in a replenishment plan based on the collected emotion data; means for notifying an employee of the inventory status and warnings in real time to the employee's mobile device and instructing the employee to take appropriate action; and a mobile device with an interface function for notifying the employee of the inventory status and necessary actions. This enables demand forecasting and efficient inventory management using user emotion data.

[0825] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[0826] "Sales data" refers to data that includes information such as the sales quantity, sales date, and sales price of each product.

[0827] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[0828] An "algorithm" is a computational method for analyzing collected data and forecasting demand.

[0829] "Replenishment quantity" is the quantity of an item needed to replenish inventory based on forecasted demand.

[0830] "Placing an order" is the act of requesting a supplier to replenish goods.

[0831] "Inventory items" are items stored in stores or warehouses.

[0832] "Expiration date" refers to the date by which the product can be used.

[0833] "Priority sales" means selling products with an approaching expiration date first.

[0834] "Inventory data" is information about the quantity and condition of inventory items.

[0835] "Real-time" means that data and information are updated instantly and immediately reflect the current state.

[0836] A "warning" is an alert that notifies the user when a problem occurs.

[0837] "Notification" is the act of informing employees of important information.

[0838] "User emotion" refers to emotional information obtained from the user's facial expressions and voice when viewing or purchasing a product.

[0839] "Emotion data" is data relating to the user's emotions.

[0840] A "portable device" is a terminal that an employee can carry with them.

[0841] "Interface functions" are functions that allow a user to interact with a device or system.

[0842] The inventory management system of the present invention combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. This system is composed of a server, terminals, users (employees), and an emotion engine.

[0843] 1. System Configuration

[0844] The server has functions for data collection, analysis, forecasting, replenishment calculation, ordering, inventory management, warning notifications, and emotional data analysis. It also collects and analyzes user emotional data recognized by the emotion engine.

[0845] 2. Data Collection

[0846] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sales price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons and events. In addition, the emotion engine obtains emotion data from the user's facial expressions and voice and sends it to the server.

[0847] 3. Preprocessing and Prediction Model Generation

[0848] The server normalizes the collected sales data, seasonal data, and sentiment data, converting them into a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. The algorithms used include linear regression and time series analysis.

[0849] 4. Demand forecasting and replenishment planning

[0850] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, predicting that demand for products with positive user sentiment will increase. Based on this prediction, the server calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[0851] 5. Inventory expiration date management and priority sales

[0852] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying them.

[0853] 6. Real-time inventory tracking and alerts

[0854] The server monitors inventory data in real time, tracking product sales and availability, detecting slow-selling or low-stock items and generating appropriate alerts, taking user sentiment data into account.

[0855] 7. Notifications and Actions

[0856] The server notifies the employee of the generated alerts via their mobile device. The employee can then view the alerts on their mobile device and take appropriate action, such as placing an order for an item that is low in stock or starting a discount sale on an item that is not selling well. The mobile device, equipped with an interface, notifies the employee of the inventory status and required actions in real time.

[0857] Specific examples

[0858] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[0859] Prompt Sentence Examples

[0860] "Based on December sales data, seasonal data for the Christmas season, and positive customer sentiment data, we would like you to forecast demand for specific confectionery products and create an appropriate replenishment plan."

[0861] As described above, the inventory management system of the present invention achieves accurate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data, thereby maximizing sales opportunities and streamlining inventory management.

[0862] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0863] Step 1:

[0864] Data collection

[0865] The server collects sales data, seasonal data, and emotion data. Sales data includes the sales quantity, sale date, and sale price of a product, while seasonal data includes fluctuations in demand related to specific seasons or events. Emotion data is obtained from the user's facial expressions and voice using an emotion engine. These data are sent to the server and stored. The inputs in this step are sales data, seasonal data, and emotion data, and the output is data stored in a unified format.

[0866] Step 2:

[0867] Data Preprocessing

[0868] The server normalizes the collected data and formats it in a format suitable for analysis. It standardizes the data and imputes missing values ​​or removes unnecessary data. It uses data stored in a uniform format as input and obtains preprocessed data as output, suitable for subsequent analysis or model generation.

[0869] Step 3:

[0870] Generate a demand forecast model

[0871] The server uses machine learning algorithms (e.g., linear regression, time series analysis) to create a demand forecasting model based on the preprocessed data. This model uses sales data, seasonal data, and sentiment data as inputs to predict future demand. The generated demand forecasting model is obtained as an output.

[0872] Step 4:

[0873] Demand forecasting

[0874] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, and it predicts that demand for products with positive user sentiment will increase. In this step, the demand forecasting model and forecast period data are used as input, and the predicted demand volume is obtained as output.

[0875] Step 5:

[0876] Replenishment planning and ordering

[0877] The server calculates the optimal replenishment amount based on the predicted demand and automatically sends order instructions to the supplier. It uses the predicted demand amount as input and gets the replenishment plan and order instructions as output.

[0878] Step 6:

[0879] Inventory expiration date management and priority sales

[0880] The server monitors the expiration dates of inventory items and creates a priority sales list for items approaching their expiration date. It notifies the terminal and instructs employees to prioritize the display of these items. It uses inventory data and expiration date data as input and obtains a priority sales list and notification as output.

[0881] Step 7:

[0882] Real-time inventory tracking and alerts

[0883] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates alerts and notifications in real time. It uses real-time inventory data as input and gets alerts and notifications as output.

[0884] Step 8:

[0885] Sending notifications and taking action

[0886] The server notifies the employee of the generated alert on their mobile device. The employee reviews the alert and takes appropriate action. The inputs are the alert and inventory data, and the output is the notification and the employee's action, which could include ordering more stock if inventory is low or starting a discount sale on a slow-selling item.

[0887] Through the above steps, the inventory management system of the present invention realizes appropriate demand forecasting and inventory management, thereby maximizing sales opportunities and improving the efficiency of inventory management.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] [Third embodiment]

[0892] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0893] 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.

[0894] 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).

[0895] 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.

[0896] 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.

[0897] 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).

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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."

[0904] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0905] 1. System Configuration

[0906] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time.

[0907] 2. Data Collection

[0908] The server periodically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, and the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[0909] Example: A store may sell a large number of certain products (e.g., holiday decorations) during the Christmas season. Based on this information, seasonal data is entered into the system.

[0910] 3. Generate a predictive model

[0911] The server analyzes the collected sales and seasonal data and generates a demand forecasting model using statistical analysis and machine learning algorithms. This model is used to predict future demand with high accuracy.

[0912] 4. Automatic replenishment and ordering

[0913] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0914] Example: Predicted Christmas items are automatically ordered before December to avoid shortages.

[0915] 5. Inventory expiration date management

[0916] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0917] Example: If there is food with an expiration date within one month, this information is notified to the store terminal, and employees prioritize putting those foods on the sales floor.

[0918] 6. Real-time inventory tracking

[0919] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0920] Example: If a particular product is about to sell out faster than expected, that information is immediately communicated to the server, which notifies the customer that more needs to be ordered.

[0921] 7. Warnings and Notifications

[0922] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0923] Example: A terminal sends a notice to a customer to offer a discount sale on a slow-selling item, and an employee lowers the price that day.

[0924] In this way, the inventory management system of the present invention enables proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, solving many problems related to inventory management.

[0925] The processing flow will be explained below.

[0926] Step 1: Data collection

[0927] The server automatically collects past sales data and seasonal data from stores and terminals, and aggregates the sales data after closing each day and stores it in a database.

[0928] Step 2: Preprocessing the data

[0929] The server normalizes the collected data and formats it in a format suitable for analysis, for example, by unifying data in different formats and imputing missing values.

[0930] Step 3: Generate a predictive model

[0931] The server creates a demand forecasting model using machine learning algorithms based on normalized sales data and seasonal data, performs statistical analysis, and applies regression analysis and time series analysis.

[0932] Step 4: Run a demand forecast

[0933] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. For example, it calculates demand for one month ahead and stores it in a database.

[0934] Step 5: Calculate the replenishment amount

[0935] The server calculates the optimal replenishment amount based on the predicted demand, taking into account the safety stock amount, calculates the order amount, and formulates a replenishment plan.

[0936] Step 6: Automated Order Processing

[0937] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[0938] Step 7: Inventory expiration management

[0939] The server tracks expiration dates recorded in the inventory database and creates a list of products with expiration dates within one month.

[0940] Step 8: Notification of Priority Sale

[0941] The server notifies the store terminal of the priority sales list, and instructs employees to display products with an approaching expiration date at the front of the shelves.

[0942] Step 9: Real-time inventory monitoring

[0943] The server collects inventory data from stores and warehouses in real time and updates the database as needed. Scanned information from barcode scanners is instantly reflected.

[0944] Step 10: Detect anomalies

[0945] The server detects slow-selling items and items with low stock from the collected real-time inventory data and analyzes the information.

[0946] Step 11: Generate warnings

[0947] The server generates warnings for low stock or slow-selling items based on the configured thresholds and records the warning information in a database.

[0948] Step 12: Sending notifications

[0949] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[0950] Step 13: Take Action

[0951] The terminal receives the notification and the user (employee) takes appropriate action, such as placing new items on the sales floor or checking inventory.

[0952] Step 14: Feedback on results

[0953] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after changing sales areas.

[0954] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory.

[0955] Example 1

[0956] 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."

[0957] Conventional inventory management systems require a lot of manual work in demand forecasting, inventory replenishment, and inventory expiration date management, which can lead to errors and reduced efficiency. Additionally, it is difficult to track inventory in real time, making it difficult to properly manage inventory shortages and excesses.

[0958] 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.

[0959] In this invention, the server includes means for collecting past sales data and seasonal data, means for generating a machine learning model that predicts demand based on the collected data, means for calculating the optimal replenishment amount based on the predicted demand and automatically placing an order, means for tracking the expiration dates of inventory items and notifying employees to prioritize the sale of items with upcoming expiration dates, means for collecting inventory data in real time and monitoring product sales and inventory status, and means for generating real-time alerts for items that are not selling well or are low in stock and notifying them to employee terminals. This automates many manual tasks related to inventory management, enabling efficient and accurate inventory management.

[0960] "Sales Data" refers to all information related to product sales, such as the sales quantity, sales date, and sales price of each product.

[0961] "Seasonal Data" refers to information that indicates fluctuations in demand associated with particular seasons or events.

[0962] "Machine learning model" refers to the algorithm used to forecast demand based on collected data.

[0963] "Replenishment quantity" refers to the quantity of an item required to maintain optimal inventory levels based on forecasted demand.

[0964] "Placing an order" refers to the act of requesting a supplier to supply goods based on the required replenishment quantity of the goods.

[0965] "Expiration date" refers to the period during which the quality of an item in stock is guaranteed, after which the item may deteriorate.

[0966] "Tracking" refers to the act of continuously collecting and tracking data by monitoring the location, condition, and quantity of inventory items.

[0967] "Real-time" refers to processing and data updates occurring in actual time.

[0968] "Terminal" refers to the device that a user (employee) uses to access the system, providing an interface for checking inventory information and notifications.

[0969] An "alert" is a notification generated when an abnormality is detected in inventory management or sales, and includes information to prompt employees to take necessary action.

[0970] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[0971] 1. System Configuration

[0972] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings. The terminals provide an interface for employees to check inventory information and alerts in real time. Users check inventory information through the terminals and take necessary actions.

[0973] 2. Data Collection

[0974] The server periodically collects past sales data and seasonality data from each store and terminal. The sales data includes the sales quantity, sale date, and sales price of each product. The seasonality data indicates fluctuations in demand related to specific seasons or events.

[0975] Examples:

[0976] A store sells a large number of certain products (e.g., holiday decorations) during the Christmas season, and this information is registered in the system.

[0977] 3. Generate a predictive model

[0978] The server performs analysis based on the collected sales data and seasonal data, and generates a demand forecasting model using statistical analysis and machine learning algorithms.

[0979] Software used:

[0980] Machine learning libraries (e.g. TensorFlow, scikit-learn)

[0981] 4. Automatic replenishment and ordering

[0982] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[0983] Examples:

[0984] Before December arrives, additional orders are automatically placed to ensure there are no shortages of predicted Christmas-related products.

[0985] 5. Inventory expiration date management

[0986] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[0987] Examples:

[0988] If there is food with an expiration date within one month, this information is notified to the store terminal, and employees will prioritize putting those foods on the sales floor.

[0989] 6. Real-time inventory tracking

[0990] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[0991] Examples:

[0992] If a particular product is likely to sell out sooner than expected, this information is immediately communicated to the server, which will notify the customer of the need to order more.

[0993] 7. Warnings and Notifications

[0994] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[0995] Examples:

[0996] Discount sale instructions for slow-selling items are sent to the terminal, and employees lower the prices that day.

[0997] Prompt Sentence Examples

[0998] Here are some example prompts for a generative AI model:

[0999] "Predict next week's demand based on this week's sales data and seasonality data."

[1000] "Please tell me which products on your inventory list have an expiration date within one month."

[1001] "Make a list of products that need to be automatically ordered based on sales data for a specific period."

[1002] In this way, the inventory management system of the invention achieves proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, thereby solving many problems related to inventory management.

[1003] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1004] Step 1: Data collection

[1005] The server periodically collects past sales data and seasonal data from each store and terminal. As input, it receives sales data extracted from each store's POS system and seasonal data from pre-set calendar events. Specifically, the server automatically saves this data in a database at midnight every night. As output, it generates sales data and seasonal data organized in a database.

[1006] Step 2: Data normalization

[1007] The server normalizes the collected data and formats it in a format suitable for analysis. The input for this step is the sales and seasonality data collected in step 1. The server performs specific operations to unify the data formats and correct inconsistent data. The output is data formatted for analysis.

[1008] Step 3: Generate a predictive model

[1009] The server generates a demand forecasting model based on the normalized data using a machine learning library (e.g., TensorFlow, scikit-learn). The formatted sales data and seasonality data are used as input. Specifically, the server trains the demand forecasting model using statistical analysis and machine learning algorithms. The output is a highly accurate demand forecasting model.

[1010] Step 4: Demand forecast and replenishment calculation

[1011] The server uses the generated forecasting model to forecast future demand. Current sales data and seasonality data are used as input. Specific operations are performed to calculate optimal replenishment amounts based on the demand forecast. The output is data on the required replenishment amounts.

[1012] Step 5: Automated ordering

[1013] The server automatically sends an order instruction to the ERP system based on the calculated replenishment amount. The replenishment amount data and supplier information obtained in step 4 are used as input. Specifically, the server sends the order data to the ERP system via API. The output is an order instruction to the supplier.

[1014] Step 6: Expiration Management

[1015] The server tracks the expiration dates of items in stock and notifies store terminals to prioritize sales of items approaching their expiration date. Stock information and expiration date data are used as input. Specifically, the server lists items that are approaching their expiration date at 10:00 every day and sends a notification to the store terminal. The output is expiration date information that employees can check.

[1016] Step 7: Real-time inventory tracking

[1017] The server monitors inventory data in real time, tracking product sales and stock status. Sales data continuously obtained from the POS system is used as input. Specifically, the server updates the database with the obtained data, reflecting the stock status in real time. The output is always the latest inventory information.

[1018] Step 8: Alert Generation and Notification

[1019] When the server detects anomalies such as inventory levels or poor sales, it generates alerts in real time and notifies employees' devices. Continuously monitored inventory data and threshold settings are used as input. Specifically, the server monitors the configured thresholds, and when an anomaly is detected, it immediately generates an alert and sends a push notification to the device. The output is warning information that employees can check on their devices.

[1020] (Application example 1)

[1021] 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."

[1022] Traditional inventory management systems are unable to respond quickly to fluctuations in demand, making them prone to problems such as stockouts and excess inventory. Furthermore, managing expiration dates for inventory items is often done manually, resulting in inefficiencies. Furthermore, it is difficult for employees to grasp inventory information in real time, which can delay appropriate action. There is a need to solve these problems and improve the efficiency and optimization of store management.

[1023] 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.

[1024] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and notifying alerts in real time about items that are not selling well or are low in stock; and means for store employees to check inventory information in real time using mobile devices and automatically place orders based on demand forecasts created by machine learning models. This enables efficient and reliable demand forecasting and inventory management.

[1025] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[1026] "Past sales data" refers to historical data such as sales quantity, sales date, and sales price of each product.

[1027] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[1028] "Predictive algorithms" refer to mathematical techniques and machine learning models that analyze collected data and forecast future demand.

[1029] "Replenishment amount" is the additional amount of product calculated to maintain appropriate inventory based on predicted demand.

[1030] An "order" is a purchasing instruction given to a supplier to replenish goods or secure inventory.

[1031] "Expiration date management" is a management method that tracks the expiration dates of inventory items and prioritizes the sale of items with upcoming expiration dates.

[1032] "Real-time collection" refers to the process of acquiring inventory and sales data in real time and making it immediately available for use.

[1033] "Sales" is an indicator of how quickly a particular product is being sold.

[1034] "Stock status" is information that indicates the current stock level and stock status.

[1035] "Warnings" are notification messages generated in response to abnormal inventory or sales conditions.

[1036] "Mobile device" refers to a portable electronic device such as a mobile phone or tablet.

[1037] A "machine learning model" is a statistical model that learns patterns and trends based on data and makes future predictions and classifications.

[1038] "Automatic ordering" refers to the process by which a system automatically generates and sends product ordering instructions to a supplier.

[1039] System configuration

[1040] This invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking. The system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time. In terms of specific hardware, the server requires a high-performance database server and computing power capable of running machine learning models, while smartphones and tablets are used as terminals.

[1041] Data collection

[1042] The server periodically collects past sales data and seasonal data from stores and terminals. Sales data includes the sales quantity, sale date, and sales price of each product. Seasonal data includes information indicating fluctuations in demand related to specific seasons and events. For example, it includes data showing that a particular product sells in large quantities during the Christmas season. This process uses API communication technologies such as the requests library.

[1043] Generate predictive models

[1044] The server analyzes the collected sales data and seasonal data to generate a demand forecasting model. This model is generated using statistical analysis and machine learning algorithms. Specifically, it uses linear regression from scikit-learn to predict future demand with high accuracy. When generating the model, the data is normalized and formatted appropriately.

[1045] Automated replenishment and ordering

[1046] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory. For example, additional orders are automatically placed before December to ensure there are no shortages of predicted Christmas-related products.

[1047] Inventory expiration date management

[1048] The server tracks the expiration dates of inventory items and notifies store terminals to prioritize sales of items approaching their expiration date. This expiration date data is sent to the server in real time, and employees are instructed to prioritize those items on the sales floor.

[1049] Real-time inventory tracking

[1050] The server monitors inventory data in real time, tracking product sales and stock status. This allows for timely detection of problems such as shortages or excess inventory. For example, information about a product that is likely to sell out faster than expected is immediately transmitted to the server, and a notification is sent to inform the customer of the need to order more.

[1051] Alerts and Notifications

[1052] When the server detects an abnormality in inventory or poor sales, it generates a real-time warning and notifies the employee's terminal. Employees can then take appropriate measures based on the notification. Instructions for discount sales of poorly selling items are sent to the terminal, and employees can lower the price that day.

[1053] Utilizing mobile devices

[1054] Employees can access inventory information in real time using their mobile devices, and machine learning models automatically place orders based on demand forecasts, enabling faster and more efficient in-store response.

[1055] Examples and prompts

[1056] For example, if a store experiences a sudden drop in its stock of Christmas trees, one scenario could be to detect this drop, use a demand forecasting model to predict future inventory shortages, and automatically place new orders.

[1057] Prompt Sentence Examples

[1058] "Describe a system that automatically places orders based on real-time inventory status and demand forecasts for specific items in a store. For example, include a scenario in which a sudden drop in Christmas tree inventory is detected, a demand forecasting model is used to predict future shortages, and a new order is automatically placed."

[1059] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1060] Step 1:

[1061] The server collects past sales data and seasonal data through API. The server uses the requests library to retrieve data from the specified API and stores the retrieved data in an internal database. Through this process, sales data and seasonal data are collected on the server. The input is raw data retrieved from the API, and the output is organized data stored in the internal database.

[1062] Step 2:

[1063] The server normalizes the collected data and formats it into a format suitable for analysis. The server organizes the data, completes missing values, and removes unnecessary data. This process involves data cleansing. The input is raw data, and the output is normalized data.

[1064] Step 3:

[1065] The server generates a demand forecasting model based on the normalized data. The server uses scikit-learn's LinearRegression to train the forecasting model using past sales data and seasonal data. The input is the normalized sales data and seasonal data, and the output is the trained forecasting model.

[1066] Step 4:

[1067] The server uses the generated forecasting model to predict future demand. The server forecasts demand for a set period (e.g., one month in the future) and uses the results as the basis for replenishment calculations. The inputs are the trained forecasting model and the forecast period, and the output is the future demand amount.

[1068] Step 5:

[1069] The server calculates the optimal replenishment amount based on future demand and automatically sends ordering instructions to the supplier. The server compares the predicted demand with the current inventory and orders the shortage. The input is the future demand and the current inventory, and the output is an ordering instruction to the supplier.

[1070] Step 6:

[1071] The server tracks the expiration dates of inventory items and generates notifications to prioritize the sale of items with upcoming expiration dates. The server scans inventory data, generates a list of items that are about to expire, and notifies the store terminal of that information. The input is inventory data, and the output is a list of items with upcoming expiration dates and notifications.

[1072] Step 7:

[1073] The server monitors inventory data in real time, tracking product sales and stock status. The server receives data from stores and terminals in real time and keeps track of the overall inventory status. The input is inventory data that is updated in real time, and the output is the latest inventory status.

[1074] Step 8:

[1075] The server detects abnormal inventory levels or poor sales, generates warnings in real time, and notifies employees' devices. The server detects abnormalities based on pre-set thresholds and sends warnings urging them to take necessary measures. The input is inventory data and sales data, and the output is a warning message.

[1076] Step 9:

[1077] A user uses a mobile device to check inventory information in real time and the status of automatic orders. The user uses a mobile app to monitor inventory status and the status of order instructions in real time. The input is the mobile device interface operations and data sent from the server, and the output is the displayed inventory information and order status.

[1078] 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.

[1079] The present invention relates to an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions, and specific embodiments thereof will be described below.

[1080] 1. System Configuration

[1081] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[1082] 2. Data Collection

[1083] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[1084] Furthermore, the emotion engine recognizes the user's emotions and collects emotion data, which is obtained from facial expressions and voices when the user views or purchases a product.

[1085] 3. Preprocessing and Prediction Model Generation

[1086] The server normalizes the collected sales data, seasonal data, and sentiment data and formats it in a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. Statistical analysis is performed, and regression analysis and time series analysis are applied.

[1087] 4. Demand forecasting and replenishment planning

[1088] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. It also takes into account emotional data and predicts that demand for products with positive user sentiment will increase. It calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[1089] 5. Inventory expiration date management and priority sales

[1090] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying those items.

[1091] 6. Real-time inventory tracking and alerts

[1092] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates appropriate warnings. The warnings also take into account the user's emotional data, and for example, warn users to be especially careful about products that generate a lot of negative emotions.

[1093] 7. Notifications and Actions

[1094] The server then sends the generated alerts to the employee's terminal, where the employee can check the notifications and take appropriate action, such as reordering low-stock items or starting a discount sale on slow-selling items.

[1095] Specific examples

[1096] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[1097] In this way, the inventory management system of the present invention realizes appropriate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data.

[1098] The processing flow will be explained below.

[1099] Step 1: Collect sales data

[1100] The server automatically collects past sales data from stores and terminals, and stores the data, such as the sales quantity, sale date, and sales price of each product, in a database after the store closes each day.

[1101] Step 2: Collect seasonal data

[1102] The server collects external seasonal data (e.g., holidays and events) and integrates it with sales data, allowing you to understand fluctuations in demand due to seasons or specific events.

[1103] Step 3: Collecting emotion data

[1104] The emotion engine recognizes emotions from the user's facial expressions and voice and collects that data, for example, analyzing the smile and tone of voice of a user looking at a product.

[1105] Step 4: Data normalization and preprocessing

[1106] The server normalizes the collected sales, seasonality, and sentiment data, unifying data from different formats and making it suitable for analysis.

[1107] Step 5: Generate a demand forecast model

[1108] The server uses the normalized data to perform statistical analysis and generate a demand forecasting model using machine learning algorithms, such as applying regression analysis or time series analysis.

[1109] Step 6: Run a demand forecast

[1110] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Taking sentiment data into consideration, the server predicts that demand for products with a high number of positive responses will increase.

[1111] Step 7: Calculate the replenishment amount

[1112] The server calculates the replenishment amount based on the predicted demand and safety stock amount, determines the order amount, and creates a replenishment plan.

[1113] Step 8: Execute automatic purchase orders

[1114] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[1115] Step 9: Inventory expiration management

[1116] The server tracks expiration dates for inventory items and creates a list of items with expiration dates within one month.

[1117] Step 10: Notification of Priority Sale

[1118] The server notifies the store terminal of the priority sales list and instructs the store staff to display products with an approaching expiration date at the front of the shelves.

[1119] Step 11: Real-time inventory monitoring

[1120] The server collects inventory data from stores and warehouses in real time and updates the database, with barcode scan information instantly reflected.

[1121] Step 12: Detect anomalies

[1122] The server analyzes real-time inventory data to detect slow-selling or low-stock items, and also takes user sentiment data into account.

[1123] Step 13: Generate warnings

[1124] The server generates warnings based on detected anomalies, such as low stock or slow-selling items, and based on sentiment data, flags items with particularly negative reactions.

[1125] Step 14: Notification of warnings

[1126] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[1127] Step 15: Take Action

[1128] The device receives the notification and the user (employee) takes appropriate action, for example, starting a discount sale on a slow-selling item.

[1129] Step 16: Feedback on results

[1130] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after a price reduction.

[1131] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory, while also achieving highly accurate management by utilizing user emotional data.

[1132] Example 2

[1133] 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."

[1134] Conventional inventory management systems lacked the efficiency of demand forecasting and inventory replenishment, making it difficult to track inventory status in real time or to make accurate demand forecasts based on user sentiment.In addition, due to a lack of effective management of inventory expiration dates and insufficient notification of warnings to terminals, problems such as stockouts and excess inventory frequently occurred, making it impossible to achieve efficient inventory management.

[1135] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1136] In this invention, the server includes a means for collecting past sales information and seasonal data for demand forecasting, a means for executing an algorithm for forecasting demand based on the collected data, and a means for calculating replenishment amounts and automatically placing orders based on the forecasted demand. This enables highly accurate demand forecasting and inventory management. Furthermore, by adding a means for recognizing and collecting user emotions using an emotion engine and a means for analyzing the emotion data and reflecting it in the demand forecast, even more accurate demand forecasting can be achieved.

[1137] In this invention, the server includes a means for managing the expiration dates of inventory items and prioritizing the sale of items with upcoming expiration dates, a means for collecting inventory data in real time and monitoring sales and inventory status, and a means for generating and notifying warnings in real time for items that are not selling well or are low in stock, thereby improving the accuracy of inventory management and enabling efficient inventory management.

[1138] In this invention, the server includes means for normalizing collected data and converting it into a format suitable for analysis, and means for notifying a terminal of an alert and prompting an employee to take appropriate action, thereby improving the quality of data analysis and enabling employees to take prompt and appropriate inventory management actions.

[1139] "Demand forecasting" is the process of predicting future demand for a product based on past sales information and seasonal data.

[1140] "Sales information" refers to information including data such as the sales quantity, sales date, and sales price of a product.

[1141] "Seasonal data" is information about fluctuations in demand related to specific seasons or events.

[1142] An "algorithm" is a set of calculation procedures for analyzing collected data and forecasting demand.

[1143] The "replenishment amount" is the quantity of the product to be replenished, calculated based on the demand forecast.

[1144] "Placing an order" is the procedure for requesting a supplier to supply goods.

[1145] The "validity period" indicates the period during which the quality of the stocked product can be guaranteed.

[1146] "Priority sales" is a method of preventing waste by selling products that are nearing their expiration date first.

[1147] "Inventory data" is information about the quantity and condition of inventory items.

[1148] "Real-time" means that data is collected and processed immediately.

[1149] "Warning" is information that notifies you in advance of a problem based on real-time monitoring results.

[1150] "Notification" means informing employees of warnings or important information.

[1151] The "emotion engine" is a mechanism that recognizes the user's emotions and collects that data.

[1152] "Emotion data" is information about emotions acquired from the user's facial expressions and voice.

[1153] "Normalization" is a process for adjusting variations in data and making it consistent.

[1154] "Terminal" refers to a computer system or device used by an employee.

[1155] "Appropriate action" refers to the specific response actions that an employee should take after receiving a notification or warning.

[1156] The present invention is an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1157] 1. System Configuration

[1158] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[1159] 2. Data Collection

[1160] The server collects the following data from stores and devices:

[1161] Sales information: the quantity sold, the date of sale, and the price of each product. This is stored in a database.

[1162] Seasonal Data: Information about fluctuations in demand related to specific seasons or events, such as Christmas or New Year sales.

[1163] Emotion data: Emotion data obtained from the user's facial expressions and voice. The emotion engine analyzes this in real time and sends it to the server as positive or negative emotions.

[1164] 3. Data Preprocessing

[1165] The server normalizes the collected data and converts it into a format suitable for analysis, ensuring data consistency and quality. Specifically, it performs the following operations:

[1166] Imputing or removing missing data

[1167] Filtering Unwanted Data

[1168] Data format conversion (e.g., standardization of date data)

[1169] 4. Generate a demand forecast model

[1170] The server generates a demand forecasting model using machine learning algorithms (such as TensorFlow or scikit-learn) based on the normalized data. This process includes the following steps:

[1171] Splitting the training data (training / testing set)

[1172] Feature extraction

[1173] Training and evaluating models (e.g., regression and time series analysis)

[1174] 5. Demand forecasting and replenishment planning

[1175] The server uses the generated demand forecasting model to predict future demand. In particular, it takes into account emotional data, predicting high demand for products with a high level of positive emotion. This prediction result is stored in a database, and an optimal replenishment plan is created. This includes the following factors:

[1176] Calculating replenishment quantities based on forecasted demand

[1177] Determining replenishment timing

[1178] Automatically send purchase orders to suppliers

[1179] 6. Inventory shelf life management

[1180] The server tracks the expiration dates of items in stock and adds items approaching their expiration date to the priority sales list. Specifically, it:

[1181] Analysis of shelf life data

[1182] Generate and update preferred sales lists

[1183] Device notifications

[1184] 7. Real-time inventory tracking

[1185] The server monitors inventory in real time to detect slow-selling or low-stock items, including:

[1186] Real-time inventory updates

[1187] Sales data analysis

[1188] Generate inventory alerts

[1189] 8. Warning notice

[1190] The server then sends the generated alerts to employees' devices. These alerts include warnings about low stock and slow-selling items. The system also incorporates user sentiment data, so that special attention is given to items with particularly negative sentiment.

[1191] 9. Action Execution

[1192] The device displays a notification to the employee, who then takes appropriate action, for example:

[1193] Reordering out-of-stock items

[1194] Prioritize display of products with upcoming expiration dates

[1195] Discount sales on slow-selling products

[1196] Examples and prompts

[1197] For example, if product A is predicted to be in high demand during the Christmas season and the sentiment data indicates that there will be a lot of positive reactions, the server will perform the following actions:

[1198] Automatically place large orders for product A

[1199] Rapidly develop replenishment plans

[1200] Inform stores about inventory status and replenishment plans

[1201] Example prompt for a generative AI model:

[1202] "Please suggest a demand forecast and replenishment plan for specific product A during the Christmas season based on store sales data and user sentiment data."

[1203] As described above, this inventory management system achieves efficient and highly accurate inventory management through a series of processes including data collection, analysis, prediction, notification, and execution.

[1204] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1205] Program processing flow

[1206] Step 1: Data collection

[1207] The server collects sales information, seasonal data, and emotion data from stores and terminals.

[1208] Input: Sales quantity, sales date, sales price of each product, seasonal event related information, and user sentiment data.

[1209] Specific operation: The server accesses the database and downloads sales information and seasonal data. Then, it collects emotion data from the user's facial expressions and voice in real time through the emotion engine.

[1210] Output: The collected data is stored in the data storage on the server.

[1211] Step 2: Data Preprocessing

[1212] The server normalizes the collected data and formats it into a format suitable for analysis.

[1213] Input: Collected sales information, seasonal data, and sentiment data.

[1214] Specific operations: The server completes missing data, filters unnecessary data, and converts date data into a unified format to ensure data consistency.

[1215] Output: A normalized and shaped dataset is generated and passed to the analysis module.

[1216] Step 3: Generate a demand forecast model

[1217] The server generates a demand forecasting model using a machine learning algorithm based on the normalized data.

[1218] Input: Normalized sales information, seasonal data, and sentiment data.

[1219] How it works: The server uses TensorFlow and scikit-learn to split the training data and extract features, then applies regression and time series analysis to train the model and evaluate its accuracy.

[1220] Output: An optimized demand forecast model is created and saved.

[1221] Step 4: Demand forecast

[1222] The server uses the generated demand forecasting model to predict future demand.

[1223] Inputs: Demand forecasting model, latest sales information, seasonal data, and sentiment data.

[1224] How it works: The server inputs the latest data into the model, performs a predictive calculation, and calculates demand. Products with a high level of positive sentiment are predicted to be in high demand.

[1225] Output: The forecasted demand information is stored in a database.

[1226] Step 5: Generate replenishment plan

[1227] The server creates an optimal replenishment plan based on the predicted demand.

[1228] Input: Forecasted demand information.

[1229] Specific operation: The server calculates the replenishment amount, determines the replenishment timing, and generates automatic ordering instructions to the supplier.

[1230] Output: Replenishment plans and purchase orders are generated and sent to suppliers.

[1231] Step 6: Inventory shelf life control

[1232] The server tracks the expiration dates of inventory items and adds items approaching expiration to a priority sales list.

[1233] Input: Inventory item shelf life data.

[1234] Specific operation: The server analyzes the expiration date and detects products that are close to expiring, creates a priority sales list, and notifies the terminal.

[1235] Output: A priority sales list is generated and sent to the store terminal.

[1236] Step 7: Real-time inventory tracking

[1237] The server monitors inventory in real time and detects slow-selling or low-stock items.

[1238] Input: Real-time inventory data, sales data.

[1239] What it does: The server updates inventory data in real time, analyzes sales data, and generates stock alerts as needed.

[1240] Output: Real-time inventory status and alert notifications are generated.

[1241] Step 8: Warning Notification

[1242] The server notifies the employee's terminal of the generated warning.

[1243] Input: The generated warning data.

[1244] Specific operation: The server sends a warning to the user's device and displays a notification, and gives special attention to products with particularly high levels of negative sentiment.

[1245] Output: A warning notification is sent and displayed on the terminal.

[1246] Step 9: Take Action

[1247] The device displays a notification to the employee, who then takes appropriate action.

[1248] Inputs: Alert notifications, real-time inventory data.

[1249] Specific actions: Employees check the notifications on their devices and take measures such as ordering more items that are out of stock, prioritizing the display of items that are about to expire, and offering discounts on items that are not selling well.

[1250] Output: Action information taken by the employee is reflected in the system.

[1251] Specific examples and prompt sentences are as described above.

[1252] (Application example 2)

[1253] 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."

[1254] Conventional inventory management systems have low accuracy in demand forecasting and inventory replenishment, resulting in problems such as stockouts and excess inventory. Furthermore, because demand forecasts are based on factors other than user sentiment, there is a high risk of missing sales opportunities. Furthermore, it is difficult for employees to take appropriate action at the right time, resulting in reduced efficiency in inventory management.

[1255] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1256] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and issuing warnings in real time for items that are selling poorly or have low inventory; means for recognizing user emotions and optimizing demand forecasting and inventory replenishment based on the emotion data; means for preferentially reflecting items with a high degree of positive emotion in a replenishment plan based on the collected emotion data; means for notifying an employee of the inventory status and warnings in real time to the employee's mobile device and instructing the employee to take appropriate action; and a mobile device with an interface function for notifying the employee of the inventory status and necessary actions. This enables demand forecasting and efficient inventory management using user emotion data.

[1257] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[1258] "Sales data" refers to data that includes information such as the sales quantity, sales date, and sales price of each product.

[1259] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[1260] An "algorithm" is a computational method for analyzing collected data and forecasting demand.

[1261] "Replenishment quantity" is the quantity of an item needed to replenish inventory based on forecasted demand.

[1262] "Placing an order" is the act of requesting a supplier to replenish goods.

[1263] "Inventory items" are items stored in stores or warehouses.

[1264] "Expiration date" refers to the date by which the product can be used.

[1265] "Priority sales" means selling products with an approaching expiration date first.

[1266] "Inventory data" is information about the quantity and condition of inventory items.

[1267] "Real-time" means that data and information are updated instantly and immediately reflect the current state.

[1268] A "warning" is an alert that notifies the user when a problem occurs.

[1269] "Notification" is the act of informing employees of important information.

[1270] "User emotion" refers to emotional information obtained from the user's facial expressions and voice when viewing or purchasing a product.

[1271] "Emotion data" is data relating to the user's emotions.

[1272] A "portable device" is a terminal that an employee can carry with them.

[1273] "Interface functions" are functions that allow a user to interact with a device or system.

[1274] The inventory management system of the present invention combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. This system is composed of a server, terminals, users (employees), and an emotion engine.

[1275] 1. System Configuration

[1276] The server has functions for data collection, analysis, forecasting, replenishment calculation, ordering, inventory management, warning notifications, and emotional data analysis. It also collects and analyzes user emotional data recognized by the emotion engine.

[1277] 2. Data Collection

[1278] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sales price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons and events. In addition, the emotion engine obtains emotion data from the user's facial expressions and voice and sends it to the server.

[1279] 3. Preprocessing and Prediction Model Generation

[1280] The server normalizes the collected sales data, seasonal data, and sentiment data, converting them into a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. The algorithms used include linear regression and time series analysis.

[1281] 4. Demand forecasting and replenishment planning

[1282] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, predicting that demand for products with positive user sentiment will increase. Based on this prediction, the server calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[1283] 5. Inventory expiration date management and priority sales

[1284] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying them.

[1285] 6. Real-time inventory tracking and alerts

[1286] The server monitors inventory data in real time, tracking product sales and availability, detecting slow-selling or low-stock items and generating appropriate alerts, taking user sentiment data into account.

[1287] 7. Notifications and Actions

[1288] The server notifies the employee of the generated alerts via their mobile device. The employee can then view the alerts on their mobile device and take appropriate action, such as placing an order for an item that is low in stock or starting a discount sale on an item that is not selling well. The mobile device, equipped with an interface, notifies the employee of the inventory status and required actions in real time.

[1289] Specific examples

[1290] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[1291] Prompt Sentence Examples

[1292] "Based on December sales data, seasonal data for the Christmas season, and positive customer sentiment data, we would like you to forecast demand for specific confectionery products and create an appropriate replenishment plan."

[1293] As described above, the inventory management system of the present invention achieves accurate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data, thereby maximizing sales opportunities and streamlining inventory management.

[1294] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1295] Step 1:

[1296] Data collection

[1297] The server collects sales data, seasonal data, and emotion data. Sales data includes the sales quantity, sale date, and sale price of a product, while seasonal data includes fluctuations in demand related to specific seasons or events. Emotion data is obtained from the user's facial expressions and voice using an emotion engine. These data are sent to the server and stored. The inputs in this step are sales data, seasonal data, and emotion data, and the output is data stored in a unified format.

[1298] Step 2:

[1299] Data Preprocessing

[1300] The server normalizes the collected data and formats it in a format suitable for analysis. It standardizes the data and imputes missing values ​​or removes unnecessary data. It uses data stored in a uniform format as input and obtains preprocessed data as output, suitable for subsequent analysis or model generation.

[1301] Step 3:

[1302] Generate a demand forecast model

[1303] The server uses machine learning algorithms (e.g., linear regression, time series analysis) to create a demand forecasting model based on the preprocessed data. This model uses sales data, seasonal data, and sentiment data as inputs to predict future demand. The generated demand forecasting model is obtained as an output.

[1304] Step 4:

[1305] Demand forecasting

[1306] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, and it predicts that demand for products with positive user sentiment will increase. In this step, the demand forecasting model and forecast period data are used as input, and the predicted demand volume is obtained as output.

[1307] Step 5:

[1308] Replenishment planning and ordering

[1309] The server calculates the optimal replenishment amount based on the predicted demand and automatically sends order instructions to the supplier. It uses the predicted demand amount as input and gets the replenishment plan and order instructions as output.

[1310] Step 6:

[1311] Inventory expiration date management and priority sales

[1312] The server monitors the expiration dates of inventory items and creates a priority sales list for items approaching their expiration date. It notifies the terminal and instructs employees to prioritize the display of these items. It uses inventory data and expiration date data as input and obtains a priority sales list and notification as output.

[1313] Step 7:

[1314] Real-time inventory tracking and alerts

[1315] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates alerts and notifications in real time. It uses real-time inventory data as input and gets alerts and notifications as output.

[1316] Step 8:

[1317] Sending notifications and taking action

[1318] The server notifies the employee of the generated alert on their mobile device. The employee reviews the alert and takes appropriate action. The inputs are the alert and inventory data, and the output is the notification and the employee's action, which could include ordering more stock if inventory is low or starting a discount sale on a slow-selling item.

[1319] Through the above steps, the inventory management system of the present invention realizes appropriate demand forecasting and inventory management, thereby maximizing sales opportunities and improving the efficiency of inventory management.

[1320] 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.

[1321] 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.

[1322] 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.

[1323] [Fourth embodiment]

[1324] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1325] 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.

[1326] 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).

[1327] 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.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] 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.

[1336] 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."

[1337] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[1338] 1. System Configuration

[1339] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time.

[1340] 2. Data Collection

[1341] The server periodically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, and the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[1342] Example: A store may sell a large number of certain products (e.g., holiday decorations) during the Christmas season. Based on this information, seasonal data is entered into the system.

[1343] 3. Generate a predictive model

[1344] The server analyzes the collected sales and seasonal data and generates a demand forecasting model using statistical analysis and machine learning algorithms. This model is used to predict future demand with high accuracy.

[1345] 4. Automatic replenishment and ordering

[1346] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[1347] Example: Predicted Christmas items are automatically ordered before December to avoid shortages.

[1348] 5. Inventory expiration date management

[1349] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[1350] Example: If there is food with an expiration date within one month, this information is notified to the store terminal, and employees prioritize putting those foods on the sales floor.

[1351] 6. Real-time inventory tracking

[1352] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[1353] Example: If a particular product is about to sell out faster than expected, that information is immediately communicated to the server, which notifies the customer that more needs to be ordered.

[1354] 7. Warnings and Notifications

[1355] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[1356] Example: A terminal sends a notice to a customer to offer a discount sale on a slow-selling item, and an employee lowers the price that day.

[1357] In this way, the inventory management system of the present invention enables proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, solving many problems related to inventory management.

[1358] The processing flow will be explained below.

[1359] Step 1: Data collection

[1360] The server automatically collects past sales data and seasonal data from stores and terminals, and aggregates the sales data after closing each day and stores it in a database.

[1361] Step 2: Preprocessing the data

[1362] The server normalizes the collected data and formats it in a format suitable for analysis, for example, by unifying data in different formats and imputing missing values.

[1363] Step 3: Generate a predictive model

[1364] The server creates a demand forecasting model using machine learning algorithms based on normalized sales data and seasonal data, performs statistical analysis, and applies regression analysis and time series analysis.

[1365] Step 4: Run a demand forecast

[1366] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. For example, it calculates demand for one month ahead and stores it in a database.

[1367] Step 5: Calculate the replenishment amount

[1368] The server calculates the optimal replenishment amount based on the predicted demand, taking into account the safety stock amount, calculates the order amount, and formulates a replenishment plan.

[1369] Step 6: Automated Order Processing

[1370] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[1371] Step 7: Inventory expiration management

[1372] The server tracks expiration dates recorded in the inventory database and creates a list of products with expiration dates within one month.

[1373] Step 8: Notification of Priority Sale

[1374] The server notifies the store terminal of the priority sales list, and instructs employees to display products with an approaching expiration date at the front of the shelves.

[1375] Step 9: Real-time inventory monitoring

[1376] The server collects inventory data from stores and warehouses in real time and updates the database as needed. Scanned information from barcode scanners is instantly reflected.

[1377] Step 10: Detect anomalies

[1378] The server detects slow-selling items and items with low stock from the collected real-time inventory data and analyzes the information.

[1379] Step 11: Generate warnings

[1380] The server generates warnings for low stock or slow-selling items based on the configured thresholds and records the warning information in a database.

[1381] Step 12: Sending notifications

[1382] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[1383] Step 13: Take Action

[1384] The terminal receives the notification and the user (employee) takes appropriate action, such as placing new items on the sales floor or checking inventory.

[1385] Step 14: Feedback on results

[1386] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after changing sales areas.

[1387] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory.

[1388] Example 1

[1389] 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."

[1390] Conventional inventory management systems require a lot of manual work in demand forecasting, inventory replenishment, and inventory expiration date management, which can lead to errors and reduced efficiency. Additionally, it is difficult to track inventory in real time, making it difficult to properly manage inventory shortages and excesses.

[1391] 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.

[1392] In this invention, the server includes means for collecting past sales data and seasonal data, means for generating a machine learning model that predicts demand based on the collected data, means for calculating the optimal replenishment amount based on the predicted demand and automatically placing an order, means for tracking the expiration dates of inventory items and notifying employees to prioritize the sale of items with upcoming expiration dates, means for collecting inventory data in real time and monitoring product sales and inventory status, and means for generating real-time alerts for items that are not selling well or are low in stock and notifying them to employee terminals. This automates many manual tasks related to inventory management, enabling efficient and accurate inventory management.

[1393] "Sales Data" refers to all information related to product sales, such as the sales quantity, sales date, and sales price of each product.

[1394] "Seasonal Data" refers to information that indicates fluctuations in demand associated with particular seasons or events.

[1395] "Machine learning model" refers to the algorithm used to forecast demand based on collected data.

[1396] "Replenishment quantity" refers to the quantity of an item required to maintain optimal inventory levels based on forecasted demand.

[1397] "Placing an order" refers to the act of requesting a supplier to supply goods based on the required replenishment quantity of the goods.

[1398] "Expiration date" refers to the period during which the quality of an item in stock is guaranteed, after which the item may deteriorate.

[1399] "Tracking" refers to the act of continuously collecting and tracking data by monitoring the location, condition, and quantity of inventory items.

[1400] "Real-time" refers to processing and data updates occurring in actual time.

[1401] "Terminal" refers to the device that a user (employee) uses to access the system, providing an interface for checking inventory information and notifications.

[1402] An "alert" is a notification generated when an abnormality is detected in inventory management or sales, and includes information to prompt employees to take necessary action.

[1403] The present invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking, and specific embodiments thereof will be described below.

[1404] 1. System Configuration

[1405] This inventory management system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings. The terminals provide an interface for employees to check inventory information and alerts in real time. Users check inventory information through the terminals and take necessary actions.

[1406] 2. Data Collection

[1407] The server periodically collects past sales data and seasonality data from each store and terminal. The sales data includes the sales quantity, sale date, and sales price of each product. The seasonality data indicates fluctuations in demand related to specific seasons or events.

[1408] Examples:

[1409] A store sells a large number of certain products (e.g., holiday decorations) during the Christmas season, and this information is registered in the system.

[1410] 3. Generate a predictive model

[1411] The server performs analysis based on the collected sales data and seasonal data, and generates a demand forecasting model using statistical analysis and machine learning algorithms.

[1412] Software used:

[1413] Machine learning libraries (e.g. TensorFlow, scikit-learn)

[1414] 4. Automatic replenishment and ordering

[1415] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory.

[1416] Examples:

[1417] Before December arrives, additional orders are automatically placed to ensure there are no shortages of predicted Christmas-related products.

[1418] 5. Inventory expiration date management

[1419] The server tracks the expiration dates of products in stock and notifies the store terminal to prioritize the sale of products whose expiration dates are approaching.

[1420] Examples:

[1421] If there is food with an expiration date within one month, this information is notified to the store terminal, and employees will prioritize putting those foods on the sales floor.

[1422] 6. Real-time inventory tracking

[1423] The server monitors inventory data in real time, tracking product sales and availability, allowing for timely detection of problems such as shortages or excess inventory.

[1424] Examples:

[1425] If a particular product is likely to sell out sooner than expected, this information is immediately communicated to the server, which will notify the customer of the need to order more.

[1426] 7. Warnings and Notifications

[1427] When the server detects an abnormality, such as a lack of inventory or poor sales, it generates a real-time warning and sends it to the employee's device, allowing the employee to take appropriate measures based on the notification.

[1428] Examples:

[1429] Discount sale instructions for slow-selling items are sent to the terminal, and employees lower the prices that day.

[1430] Prompt Sentence Examples

[1431] Here are some example prompts for a generative AI model:

[1432] "Predict next week's demand based on this week's sales data and seasonality data."

[1433] "Please tell me which products on your inventory list have an expiration date within one month."

[1434] "Make a list of products that need to be automatically ordered based on sales data for a specific period."

[1435] In this way, the inventory management system of the invention achieves proper forecasting of demand, efficient replenishment of inventory, inventory optimization, and real-time inventory monitoring, thereby solving many problems related to inventory management.

[1436] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1437] Step 1: Data collection

[1438] The server periodically collects past sales data and seasonal data from each store and terminal. As input, it receives sales data extracted from each store's POS system and seasonal data from pre-set calendar events. Specifically, the server automatically saves this data in a database at midnight every night. As output, it generates sales data and seasonal data organized in a database.

[1439] Step 2: Data normalization

[1440] The server normalizes the collected data and formats it in a format suitable for analysis. The input for this step is the sales and seasonality data collected in step 1. The server performs specific operations to unify the data formats and correct inconsistent data. The output is data formatted for analysis.

[1441] Step 3: Generate a predictive model

[1442] The server generates a demand forecasting model based on the normalized data using a machine learning library (e.g., TensorFlow, scikit-learn). The formatted sales data and seasonality data are used as input. Specifically, the server trains the demand forecasting model using statistical analysis and machine learning algorithms. The output is a highly accurate demand forecasting model.

[1443] Step 4: Demand forecast and replenishment calculation

[1444] The server uses the generated forecasting model to forecast future demand. Current sales data and seasonality data are used as input. Specific operations are performed to calculate optimal replenishment amounts based on the demand forecast. The output is data on the required replenishment amounts.

[1445] Step 5: Automated ordering

[1446] The server automatically sends an order instruction to the ERP system based on the calculated replenishment amount. The replenishment amount data and supplier information obtained in step 4 are used as input. Specifically, the server sends the order data to the ERP system via API. The output is an order instruction to the supplier.

[1447] Step 6: Expiration Management

[1448] The server tracks the expiration dates of items in stock and notifies store terminals to prioritize sales of items approaching their expiration date. Stock information and expiration date data are used as input. Specifically, the server lists items that are approaching their expiration date at 10:00 every day and sends a notification to the store terminal. The output is expiration date information that employees can check.

[1449] Step 7: Real-time inventory tracking

[1450] The server monitors inventory data in real time, tracking product sales and stock status. Sales data continuously obtained from the POS system is used as input. Specifically, the server updates the database with the obtained data, reflecting the stock status in real time. The output is always the latest inventory information.

[1451] Step 8: Alert Generation and Notification

[1452] When the server detects anomalies such as inventory levels or poor sales, it generates alerts in real time and notifies employees' devices. Continuously monitored inventory data and threshold settings are used as input. Specifically, the server monitors the configured thresholds, and when an anomaly is detected, it immediately generates an alert and sends a push notification to the device. The output is warning information that employees can check on their devices.

[1453] (Application example 1)

[1454] 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."

[1455] Traditional inventory management systems are unable to respond quickly to fluctuations in demand, making them prone to problems such as stockouts and excess inventory. Furthermore, managing expiration dates for inventory items is often done manually, resulting in inefficiencies. Furthermore, it is difficult for employees to grasp inventory information in real time, which can delay appropriate action. There is a need to solve these problems and improve the efficiency and optimization of store management.

[1456] 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.

[1457] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and notifying alerts in real time about items that are not selling well or are low in stock; and means for store employees to check inventory information in real time using mobile devices and automatically place orders based on demand forecasts created by machine learning models. This enables efficient and reliable demand forecasting and inventory management.

[1458] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[1459] "Past sales data" refers to historical data such as sales quantity, sales date, and sales price of each product.

[1460] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[1461] "Predictive algorithms" refer to mathematical techniques and machine learning models that analyze collected data and forecast future demand.

[1462] "Replenishment amount" is the additional amount of product calculated to maintain appropriate inventory based on predicted demand.

[1463] An "order" is a purchasing instruction given to a supplier to replenish goods or secure inventory.

[1464] "Expiration date management" is a management method that tracks the expiration dates of inventory items and prioritizes the sale of items with upcoming expiration dates.

[1465] "Real-time collection" refers to the process of acquiring inventory and sales data in real time and making it immediately available for use.

[1466] "Sales" is an indicator of how quickly a particular product is being sold.

[1467] "Stock status" is information that indicates the current stock level and stock status.

[1468] "Warnings" are notification messages generated in response to abnormal inventory or sales conditions.

[1469] "Mobile device" refers to a portable electronic device such as a mobile phone or tablet.

[1470] A "machine learning model" is a statistical model that learns patterns and trends based on data and makes future predictions and classifications.

[1471] "Automatic ordering" refers to the process by which a system automatically generates and sends product ordering instructions to a supplier.

[1472] System configuration

[1473] This invention relates to an inventory management system that performs demand forecasting, automatic inventory replenishment, inventory optimization, and real-time tracking. The system consists of a central server, terminals, and users (employees). The server collects data, analyzes, forecasts, calculates replenishment, places orders, manages inventory, and issues warnings, while the terminals provide an interface for employees to check inventory information and alerts in real time. In terms of specific hardware, the server requires a high-performance database server and computing power capable of running machine learning models, while smartphones and tablets are used as terminals.

[1474] Data collection

[1475] The server periodically collects past sales data and seasonal data from stores and terminals. Sales data includes the sales quantity, sale date, and sales price of each product. Seasonal data includes information indicating fluctuations in demand related to specific seasons and events. For example, it includes data showing that a particular product sells in large quantities during the Christmas season. This process uses API communication technologies such as the requests library.

[1476] Generate predictive models

[1477] The server analyzes the collected sales data and seasonal data to generate a demand forecasting model. This model is generated using statistical analysis and machine learning algorithms. Specifically, it uses linear regression from scikit-learn to predict future demand with high accuracy. When generating the model, the data is normalized and formatted appropriately.

[1478] Automated replenishment and ordering

[1479] The server calculates the optimal replenishment amount based on predicted demand and automatically sends ordering instructions to suppliers, preventing stockouts and excess inventory. For example, additional orders are automatically placed before December to ensure there are no shortages of predicted Christmas-related products.

[1480] Inventory expiration date management

[1481] The server tracks the expiration dates of inventory items and notifies store terminals to prioritize sales of items approaching their expiration date. This expiration date data is sent to the server in real time, and employees are instructed to prioritize those items on the sales floor.

[1482] Real-time inventory tracking

[1483] The server monitors inventory data in real time, tracking product sales and stock status. This allows for timely detection of problems such as shortages or excess inventory. For example, information about a product that is likely to sell out faster than expected is immediately transmitted to the server, and a notification is sent to inform the customer of the need to order more.

[1484] Alerts and Notifications

[1485] When the server detects an abnormality in inventory or poor sales, it generates a real-time warning and notifies the employee's terminal. Employees can then take appropriate measures based on the notification. Instructions for discount sales of poorly selling items are sent to the terminal, and employees can lower the price that day.

[1486] Utilizing mobile devices

[1487] Employees can access inventory information in real time using their mobile devices, and machine learning models automatically place orders based on demand forecasts, enabling faster and more efficient in-store response.

[1488] Examples and prompts

[1489] For example, if a store experiences a sudden drop in its stock of Christmas trees, one scenario could be to detect this drop, use a demand forecasting model to predict future inventory shortages, and automatically place new orders.

[1490] Prompt Sentence Examples

[1491] "Describe a system that automatically places orders based on real-time inventory status and demand forecasts for specific items in a store. For example, include a scenario in which a sudden drop in Christmas tree inventory is detected, a demand forecasting model is used to predict future shortages, and a new order is automatically placed."

[1492] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1493] Step 1:

[1494] The server collects past sales data and seasonal data through API. The server uses the requests library to retrieve data from the specified API and stores the retrieved data in an internal database. Through this process, sales data and seasonal data are collected on the server. The input is raw data retrieved from the API, and the output is organized data stored in the internal database.

[1495] Step 2:

[1496] The server normalizes the collected data and formats it into a format suitable for analysis. The server organizes the data, completes missing values, and removes unnecessary data. This process involves data cleansing. The input is raw data, and the output is normalized data.

[1497] Step 3:

[1498] The server generates a demand forecasting model based on the normalized data. The server uses scikit-learn's LinearRegression to train the forecasting model using past sales data and seasonal data. The input is the normalized sales data and seasonal data, and the output is the trained forecasting model.

[1499] Step 4:

[1500] The server uses the generated forecasting model to predict future demand. The server forecasts demand for a set period (e.g., one month in the future) and uses the results as the basis for replenishment calculations. The inputs are the trained forecasting model and the forecast period, and the output is the future demand amount.

[1501] Step 5:

[1502] The server calculates the optimal replenishment amount based on future demand and automatically sends ordering instructions to the supplier. The server compares the predicted demand with the current inventory and orders the shortage. The input is the future demand and the current inventory, and the output is an ordering instruction to the supplier.

[1503] Step 6:

[1504] The server tracks the expiration dates of inventory items and generates notifications to prioritize the sale of items with upcoming expiration dates. The server scans inventory data, generates a list of items that are about to expire, and notifies the store terminal of that information. The input is inventory data, and the output is a list of items with upcoming expiration dates and notifications.

[1505] Step 7:

[1506] The server monitors inventory data in real time, tracking product sales and stock status. The server receives data from stores and terminals in real time and keeps track of the overall inventory status. The input is inventory data that is updated in real time, and the output is the latest inventory status.

[1507] Step 8:

[1508] The server detects abnormal inventory levels or poor sales, generates warnings in real time, and notifies employees' devices. The server detects abnormalities based on pre-set thresholds and sends warnings urging them to take necessary measures. The input is inventory data and sales data, and the output is a warning message.

[1509] Step 9:

[1510] A user uses a mobile device to check inventory information in real time and the status of automatic orders. The user uses a mobile app to monitor inventory status and the status of order instructions in real time. The input is the mobile device interface operations and data sent from the server, and the output is the displayed inventory information and order status.

[1511] 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.

[1512] The present invention relates to an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions, and specific embodiments thereof will be described below.

[1513] 1. System Configuration

[1514] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[1515] 2. Data Collection

[1516] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sale price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons or events.

[1517] Furthermore, the emotion engine recognizes the user's emotions and collects emotion data, which is obtained from facial expressions and voices when the user views or purchases a product.

[1518] 3. Preprocessing and Prediction Model Generation

[1519] The server normalizes the collected sales data, seasonal data, and sentiment data and formats it in a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. Statistical analysis is performed, and regression analysis and time series analysis are applied.

[1520] 4. Demand forecasting and replenishment planning

[1521] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. It also takes into account emotional data and predicts that demand for products with positive user sentiment will increase. It calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[1522] 5. Inventory expiration date management and priority sales

[1523] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying those items.

[1524] 6. Real-time inventory tracking and alerts

[1525] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates appropriate warnings. The warnings also take into account the user's emotional data, and for example, warn users to be especially careful about products that generate a lot of negative emotions.

[1526] 7. Notifications and Actions

[1527] The server then sends the generated alerts to the employee's terminal, where the employee can check the notifications and take appropriate action, such as reordering low-stock items or starting a discount sale on slow-selling items.

[1528] Specific examples

[1529] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[1530] In this way, the inventory management system of the present invention realizes appropriate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data.

[1531] The processing flow will be explained below.

[1532] Step 1: Collect sales data

[1533] The server automatically collects past sales data from stores and terminals, and stores the data, such as the sales quantity, sale date, and sales price of each product, in a database after the store closes each day.

[1534] Step 2: Collect seasonal data

[1535] The server collects external seasonal data (e.g., holidays and events) and integrates it with sales data, allowing you to understand fluctuations in demand due to seasons or specific events.

[1536] Step 3: Collecting emotion data

[1537] The emotion engine recognizes emotions from the user's facial expressions and voice and collects that data, for example, analyzing the smile and tone of voice of a user looking at a product.

[1538] Step 4: Data normalization and preprocessing

[1539] The server normalizes the collected sales, seasonality, and sentiment data, unifying data from different formats and making it suitable for analysis.

[1540] Step 5: Generate a demand forecast model

[1541] The server uses the normalized data to perform statistical analysis and generate a demand forecasting model using machine learning algorithms, such as applying regression analysis or time series analysis.

[1542] Step 6: Run a demand forecast

[1543] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Taking sentiment data into consideration, the server predicts that demand for products with a high number of positive responses will increase.

[1544] Step 7: Calculate the replenishment amount

[1545] The server calculates the replenishment amount based on the predicted demand and safety stock amount, determines the order amount, and creates a replenishment plan.

[1546] Step 8: Execute automatic purchase orders

[1547] The server automatically sends purchase orders to suppliers based on the replenishment plan. Purchase order information is shared through an interface.

[1548] Step 9: Inventory expiration management

[1549] The server tracks expiration dates for inventory items and creates a list of items with expiration dates within one month.

[1550] Step 10: Notification of Priority Sale

[1551] The server notifies the store terminal of the priority sales list and instructs the store staff to display products with an approaching expiration date at the front of the shelves.

[1552] Step 11: Real-time inventory monitoring

[1553] The server collects inventory data from stores and warehouses in real time and updates the database, with barcode scan information instantly reflected.

[1554] Step 12: Detect anomalies

[1555] The server analyzes real-time inventory data to detect slow-selling or low-stock items, and also takes user sentiment data into account.

[1556] Step 13: Generate warnings

[1557] The server generates warnings based on detected anomalies, such as low stock or slow-selling items, and based on sentiment data, flags items with particularly negative reactions.

[1558] Step 14: Notification of warnings

[1559] The server notifies the employee terminal of the generated alert, for example, informing them that a product is running low on stock and that more needs to be ordered.

[1560] Step 15: Take Action

[1561] The device receives the notification and the user (employee) takes appropriate action, for example, starting a discount sale on a slow-selling item.

[1562] Step 16: Feedback on results

[1563] The user (employee) feeds back the results of the actions they have taken into the system, for example, by inputting sales data after a price reduction.

[1564] Through these steps, the inventory management system efficiently and effectively monitors and manages inventory, while also achieving highly accurate management by utilizing user emotional data.

[1565] Example 2

[1566] 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."

[1567] Conventional inventory management systems lacked the efficiency of demand forecasting and inventory replenishment, making it difficult to track inventory status in real time or to make accurate demand forecasts based on user sentiment.In addition, due to a lack of effective management of inventory expiration dates and insufficient notification of warnings to terminals, problems such as stockouts and excess inventory frequently occurred, making it impossible to achieve efficient inventory management.

[1568] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1569] In this invention, the server includes a means for collecting past sales information and seasonal data for demand forecasting, a means for executing an algorithm for forecasting demand based on the collected data, and a means for calculating replenishment amounts and automatically placing orders based on the forecasted demand. This enables highly accurate demand forecasting and inventory management. Furthermore, by adding a means for recognizing and collecting user emotions using an emotion engine and a means for analyzing the emotion data and reflecting it in the demand forecast, even more accurate demand forecasting can be achieved.

[1570] In this invention, the server includes a means for managing the expiration dates of inventory items and prioritizing the sale of items with upcoming expiration dates, a means for collecting inventory data in real time and monitoring sales and inventory status, and a means for generating and notifying warnings in real time for items that are not selling well or are low in stock, thereby improving the accuracy of inventory management and enabling efficient inventory management.

[1571] In this invention, the server includes means for normalizing collected data and converting it into a format suitable for analysis, and means for notifying a terminal of an alert and prompting an employee to take appropriate action, thereby improving the quality of data analysis and enabling employees to take prompt and appropriate inventory management actions.

[1572] "Demand forecasting" is the process of predicting future demand for a product based on past sales information and seasonal data.

[1573] "Sales information" refers to information including data such as the sales quantity, sales date, and sales price of a product.

[1574] "Seasonal data" is information about fluctuations in demand related to specific seasons or events.

[1575] An "algorithm" is a set of calculation procedures for analyzing collected data and forecasting demand.

[1576] The "replenishment amount" is the quantity of the product to be replenished, calculated based on the demand forecast.

[1577] "Placing an order" is the procedure for requesting a supplier to supply goods.

[1578] The "validity period" indicates the period during which the quality of the stocked product can be guaranteed.

[1579] "Priority sales" is a method of preventing waste by selling products that are nearing their expiration date first.

[1580] "Inventory data" is information about the quantity and condition of inventory items.

[1581] "Real-time" means that data is collected and processed immediately.

[1582] "Warning" is information that notifies you in advance of a problem based on real-time monitoring results.

[1583] "Notification" means informing employees of warnings or important information.

[1584] The "emotion engine" is a mechanism that recognizes the user's emotions and collects that data.

[1585] "Emotion data" is information about emotions acquired from the user's facial expressions and voice.

[1586] "Normalization" is a process for adjusting variations in data and making it consistent.

[1587] "Terminal" refers to a computer system or device used by an employee.

[1588] "Appropriate action" refers to the specific response actions that an employee should take after receiving a notification or warning.

[1589] The present invention is an inventory management system that combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. Specific embodiments of the system are described below.

[1590] 1. System Configuration

[1591] This inventory management system consists of a central server, terminals, users (employees), and an emotion engine. The server collects data, analyzes it, makes forecasts, calculates replenishment, places orders, manages inventory, issues warnings, and analyzes emotion data. The terminals provide an interface for employees to check inventory information and alerts in real time, and the emotion engine recognizes user emotions and provides emotion data to the system.

[1592] 2. Data Collection

[1593] The server collects the following data from stores and devices:

[1594] Sales information: the quantity sold, the date of sale, and the price of each product. This is stored in a database.

[1595] Seasonal Data: Information about fluctuations in demand related to specific seasons or events, such as Christmas or New Year sales.

[1596] Emotion data: Emotion data obtained from the user's facial expressions and voice. The emotion engine analyzes this in real time and sends it to the server as positive or negative emotions.

[1597] 3. Data Preprocessing

[1598] The server normalizes the collected data and converts it into a format suitable for analysis, ensuring data consistency and quality. Specifically, it performs the following operations:

[1599] Imputing or removing missing data

[1600] Filtering Unwanted Data

[1601] Data format conversion (e.g., standardization of date data)

[1602] 4. Generate a demand forecast model

[1603] The server generates a demand forecasting model using machine learning algorithms (such as TensorFlow or scikit-learn) based on the normalized data. This process includes the following steps:

[1604] Splitting the training data (training / testing set)

[1605] Feature extraction

[1606] Training and evaluating models (e.g., regression and time series analysis)

[1607] 5. Demand forecasting and replenishment planning

[1608] The server uses the generated demand forecasting model to predict future demand. In particular, it takes into account emotional data, predicting high demand for products with a high level of positive emotion. This prediction result is stored in a database, and an optimal replenishment plan is created. This includes the following factors:

[1609] Calculating replenishment quantities based on forecasted demand

[1610] Determining replenishment timing

[1611] Automatically send purchase orders to suppliers

[1612] 6. Inventory shelf life management

[1613] The server tracks the expiration dates of items in stock and adds items approaching their expiration date to the priority sales list. Specifically, it:

[1614] Analysis of shelf life data

[1615] Generate and update preferred sales lists

[1616] Device notifications

[1617] 7. Real-time inventory tracking

[1618] The server monitors inventory in real time to detect slow-selling or low-stock items, including:

[1619] Real-time inventory updates

[1620] Sales data analysis

[1621] Generate inventory alerts

[1622] 8. Warning notice

[1623] The server then sends the generated alerts to employees' devices. These alerts include warnings about low stock and slow-selling items. The system also incorporates user sentiment data, so that special attention is given to items with particularly negative sentiment.

[1624] 9. Action Execution

[1625] The device displays a notification to the employee, who then takes appropriate action, for example:

[1626] Reordering out-of-stock items

[1627] Prioritize display of products with upcoming expiration dates

[1628] Discount sales on slow-selling products

[1629] Examples and prompts

[1630] For example, if product A is predicted to be in high demand during the Christmas season and the sentiment data indicates that there will be a lot of positive reactions, the server will perform the following actions:

[1631] Automatically place large orders for product A

[1632] Rapidly develop replenishment plans

[1633] Inform stores about inventory status and replenishment plans

[1634] Example prompt for a generative AI model:

[1635] "Please suggest a demand forecast and replenishment plan for specific product A during the Christmas season based on store sales data and user sentiment data."

[1636] As described above, this inventory management system achieves efficient and highly accurate inventory management through a series of processes including data collection, analysis, prediction, notification, and execution.

[1637] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1638] Program processing flow

[1639] Step 1: Data collection

[1640] The server collects sales information, seasonal data, and emotion data from stores and terminals.

[1641] Input: Sales quantity, sales date, sales price of each product, seasonal event related information, and user sentiment data.

[1642] Specific operation: The server accesses the database and downloads sales information and seasonal data. Then, it collects emotion data from the user's facial expressions and voice in real time through the emotion engine.

[1643] Output: The collected data is stored in the data storage on the server.

[1644] Step 2: Data Preprocessing

[1645] The server normalizes the collected data and formats it into a format suitable for analysis.

[1646] Input: Collected sales information, seasonal data, and sentiment data.

[1647] Specific operations: The server completes missing data, filters unnecessary data, and converts date data into a unified format to ensure data consistency.

[1648] Output: A normalized and shaped dataset is generated and passed to the analysis module.

[1649] Step 3: Generate a demand forecast model

[1650] The server generates a demand forecasting model using a machine learning algorithm based on the normalized data.

[1651] Input: Normalized sales information, seasonal data, and sentiment data.

[1652] How it works: The server uses TensorFlow and scikit-learn to split the training data and extract features, then applies regression and time series analysis to train the model and evaluate its accuracy.

[1653] Output: An optimized demand forecast model is created and saved.

[1654] Step 4: Demand forecast

[1655] The server uses the generated demand forecasting model to predict future demand.

[1656] Inputs: Demand forecasting model, latest sales information, seasonal data, and sentiment data.

[1657] How it works: The server inputs the latest data into the model, performs a predictive calculation, and calculates demand. Products with a high level of positive sentiment are predicted to be in high demand.

[1658] Output: The forecasted demand information is stored in a database.

[1659] Step 5: Generate replenishment plan

[1660] The server creates an optimal replenishment plan based on the predicted demand.

[1661] Input: Forecasted demand information.

[1662] Specific operation: The server calculates the replenishment amount, determines the replenishment timing, and generates automatic ordering instructions to the supplier.

[1663] Output: Replenishment plans and purchase orders are generated and sent to suppliers.

[1664] Step 6: Inventory shelf life control

[1665] The server tracks the expiration dates of inventory items and adds items approaching expiration to a priority sales list.

[1666] Input: Inventory item shelf life data.

[1667] Specific operation: The server analyzes the expiration date and detects products that are close to expiring, creates a priority sales list, and notifies the terminal.

[1668] Output: A priority sales list is generated and sent to the store terminal.

[1669] Step 7: Real-time inventory tracking

[1670] The server monitors inventory in real time and detects slow-selling or low-stock items.

[1671] Input: Real-time inventory data, sales data.

[1672] What it does: The server updates inventory data in real time, analyzes sales data, and generates stock alerts as needed.

[1673] Output: Real-time inventory status and alert notifications are generated.

[1674] Step 8: Warning Notification

[1675] The server notifies the employee's terminal of the generated warning.

[1676] Input: The generated warning data.

[1677] Specific operation: The server sends a warning to the user's device and displays a notification, and gives special attention to products with particularly high levels of negative sentiment.

[1678] Output: A warning notification is sent and displayed on the terminal.

[1679] Step 9: Take Action

[1680] The device displays a notification to the employee, who then takes appropriate action.

[1681] Inputs: Alert notifications, real-time inventory data.

[1682] Specific actions: Employees check the notifications on their devices and take measures such as ordering more items that are out of stock, prioritizing the display of items that are about to expire, and offering discounts on items that are not selling well.

[1683] Output: Action information taken by the employee is reflected in the system.

[1684] Specific examples and prompt sentences are as described above.

[1685] (Application example 2)

[1686] 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."

[1687] Conventional inventory management systems have low accuracy in demand forecasting and inventory replenishment, resulting in problems such as stockouts and excess inventory. Furthermore, because demand forecasts are based on factors other than user sentiment, there is a high risk of missing sales opportunities. Furthermore, it is difficult for employees to take appropriate action at the right time, resulting in reduced efficiency in inventory management.

[1688] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1689] In this invention, the server includes: means for collecting past sales data and seasonal data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; means for calculating replenishment amounts and automatically placing orders based on the forecasted demand; means for managing expiration dates of inventory items and prioritizing the sale of items approaching their expiration dates; means for collecting inventory data in real time and monitoring sales and inventory status; means for generating and issuing warnings in real time for items that are selling poorly or have low inventory; means for recognizing user emotions and optimizing demand forecasting and inventory replenishment based on the emotion data; means for preferentially reflecting items with a high degree of positive emotion in a replenishment plan based on the collected emotion data; means for notifying an employee of the inventory status and warnings in real time to the employee's mobile device and instructing the employee to take appropriate action; and a mobile device with an interface function for notifying the employee of the inventory status and necessary actions. This enables demand forecasting and efficient inventory management using user emotion data.

[1690] "Demand forecasting" is the process of predicting future demand based on past sales data and seasonal data.

[1691] "Sales data" refers to data that includes information such as the sales quantity, sales date, and sales price of each product.

[1692] "Seasonal data" is information that indicates fluctuations in demand associated with particular seasons or events.

[1693] An "algorithm" is a computational method for analyzing collected data and forecasting demand.

[1694] "Replenishment quantity" is the quantity of an item needed to replenish inventory based on forecasted demand.

[1695] "Placing an order" is the act of requesting a supplier to replenish goods.

[1696] "Inventory items" are items stored in stores or warehouses.

[1697] "Expiration date" refers to the date by which the product can be used.

[1698] "Priority sales" means selling products with an approaching expiration date first.

[1699] "Inventory data" is information about the quantity and condition of inventory items.

[1700] "Real-time" means that data and information are updated instantly and immediately reflect the current state.

[1701] A "warning" is an alert that notifies the user when a problem occurs.

[1702] "Notification" is the act of informing employees of important information.

[1703] "User emotion" refers to emotional information obtained from the user's facial expressions and voice when viewing or purchasing a product.

[1704] "Emotion data" is data relating to the user's emotions.

[1705] A "portable device" is a terminal that an employee can carry with them.

[1706] "Interface functions" are functions that allow a user to interact with a device or system.

[1707] The inventory management system of the present invention combines demand forecasting, automatic inventory replenishment, inventory optimization, real-time tracking, and an emotion engine that recognizes user emotions. This system is composed of a server, terminals, users (employees), and an emotion engine.

[1708] 1. System Configuration

[1709] The server has functions for data collection, analysis, forecasting, replenishment calculation, ordering, inventory management, warning notifications, and emotional data analysis. It also collects and analyzes user emotional data recognized by the emotion engine.

[1710] 2. Data Collection

[1711] The server automatically collects past sales data and seasonal data from stores and terminals. The sales data includes the sales quantity, sale date, and sales price of each product, while the seasonal data includes information indicating fluctuations in demand related to specific seasons and events. In addition, the emotion engine obtains emotion data from the user's facial expressions and voice and sends it to the server.

[1712] 3. Preprocessing and Prediction Model Generation

[1713] The server normalizes the collected sales data, seasonal data, and sentiment data, converting them into a format suitable for analysis. This allows the data to be stored in a unified format. Based on the normalized data, a demand forecasting model is created using machine learning algorithms. The algorithms used include linear regression and time series analysis.

[1714] 4. Demand forecasting and replenishment planning

[1715] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, predicting that demand for products with positive user sentiment will increase. Based on this prediction, the server calculates the optimal replenishment quantity and automatically sends ordering instructions to suppliers.

[1716] 5. Inventory expiration date management and priority sales

[1717] The server tracks the expiration dates of inventory items, creates a list of items that are approaching their expiration date, and notifies store terminals of items that are approaching their expiration date, instructing employees to prioritize displaying them.

[1718] 6. Real-time inventory tracking and alerts

[1719] The server monitors inventory data in real time, tracking product sales and availability, detecting slow-selling or low-stock items and generating appropriate alerts, taking user sentiment data into account.

[1720] 7. Notifications and Actions

[1721] The server notifies the employee of the generated alerts via their mobile device. The employee can then view the alerts on their mobile device and take appropriate action, such as placing an order for an item that is low in stock or starting a discount sale on an item that is not selling well. The mobile device, equipped with an interface, notifies the employee of the inventory status and required actions in real time.

[1722] Specific examples

[1723] For example, if a store predicts that a particular product will be in high demand during the Christmas season, and user sentiment data indicates that the reaction to that product is very positive, the server can automatically place a large order and quickly develop the necessary replenishment plan to prevent stockouts.

[1724] Prompt Sentence Examples

[1725] "Based on December sales data, seasonal data for the Christmas season, and positive customer sentiment data, we would like you to forecast demand for specific confectionery products and create an appropriate replenishment plan."

[1726] As described above, the inventory management system of the present invention achieves accurate demand forecasting, efficient inventory replenishment, inventory optimization, real-time inventory monitoring, and even more accurate management by utilizing user emotion data, thereby maximizing sales opportunities and streamlining inventory management.

[1727] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1728] Step 1:

[1729] Data collection

[1730] The server collects sales data, seasonal data, and emotion data. Sales data includes the sales quantity, sale date, and sale price of a product, while seasonal data includes fluctuations in demand related to specific seasons or events. Emotion data is obtained from the user's facial expressions and voice using an emotion engine. These data are sent to the server and stored. The inputs in this step are sales data, seasonal data, and emotion data, and the output is data stored in a unified format.

[1731] Step 2:

[1732] Data Preprocessing

[1733] The server normalizes the collected data and formats it in a format suitable for analysis. It standardizes the data and imputes missing values ​​or removes unnecessary data. It uses data stored in a uniform format as input and obtains preprocessed data as output, suitable for subsequent analysis or model generation.

[1734] Step 3:

[1735] Generate a demand forecast model

[1736] The server uses machine learning algorithms (e.g., linear regression, time series analysis) to create a demand forecasting model based on the preprocessed data. This model uses sales data, seasonal data, and sentiment data as inputs to predict future demand. The generated demand forecasting model is obtained as an output.

[1737] Step 4:

[1738] Demand forecasting

[1739] The server uses the generated demand forecasting model to predict demand for the next replenishment planning period. Emotional data is also taken into account, and it predicts that demand for products with positive user sentiment will increase. In this step, the demand forecasting model and forecast period data are used as input, and the predicted demand volume is obtained as output.

[1740] Step 5:

[1741] Replenishment planning and ordering

[1742] The server calculates the optimal replenishment amount based on the predicted demand and automatically sends order instructions to the supplier. It uses the predicted demand amount as input and gets the replenishment plan and order instructions as output.

[1743] Step 6:

[1744] Inventory expiration date management and priority sales

[1745] The server monitors the expiration dates of inventory items and creates a priority sales list for items approaching their expiration date. It notifies the terminal and instructs employees to prioritize the display of these items. It uses inventory data and expiration date data as input and obtains a priority sales list and notification as output.

[1746] Step 7:

[1747] Real-time inventory tracking and alerts

[1748] The server monitors inventory data in real time, tracking product sales and availability. It detects slow-selling or low-stock items and generates alerts and notifications in real time. It uses real-time inventory data as input and gets alerts and notifications as output.

[1749] Step 8:

[1750] Sending notifications and taking action

[1751] The server notifies the employee of the generated alert on their mobile device. The employee reviews the alert and takes appropriate action. The inputs are the alert and inventory data, and the output is the notification and the employee's action, which could include ordering more stock if inventory is low or starting a discount sale on a slow-selling item.

[1752] Through the above steps, the inventory management system of the present invention realizes appropriate demand forecasting and inventory management, thereby maximizing sales opportunities and improving the efficiency of inventory management.

[1753] 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.

[1754] 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.

[1755] 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 robot 414.

[1756] 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.

[1757] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1758] 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.

[1759] 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).

[1760] 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.

[1761] 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."

[1762] 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.

[1763] 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).

[1764] 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.

[1765] 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.

[1766] 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.

[1767] 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.

[1768] 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.

[1769] 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.

[1770] 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.

[1771] 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.

[1772] 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.

[1773] 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.

[1774] The following is further disclosed regarding the above embodiment.

[1775] (Claim 1)

[1776] a means of collecting historical sales and seasonality data for demand forecasting;

[1777] means for executing an algorithm for forecasting demand based on the collected data;

[1778] a means for automatically calculating replenishment amounts and placing orders based on the predicted demand;

[1779] A means of managing the expiration dates of inventory items and prioritizing the sale of items with an approaching expiration date.

[1780] A means to collect inventory data in real time and monitor sales and stock status,

[1781] A means to generate and notify real-time alerts for slow-selling or low-stock items;

[1782] A system including:

[1783] (Claim 2)

[1784] 10. The system of claim 1, further comprising means for normalizing the collected data and shaping it into a form suitable for analysis.

[1785] (Claim 3)

[1786] 10. The system according to claim 1, further comprising means for notifying a terminal in a store or warehouse of the warning and prompti...

Claims

1. a means of collecting historical sales and seasonality data for demand forecasting; means for executing an algorithm for forecasting demand based on the collected data; a means for automatically calculating replenishment amounts and placing orders based on the predicted demand; A means of managing the expiration dates of inventory items and prioritizing the sale of items with an approaching expiration date. A means to collect inventory data in real time and monitor sales and stock status, A means to generate and notify real-time alerts for slow-selling or low-stock items; A system including:

2. 10. The system of claim 1, further comprising means for normalizing the collected data and shaping it into a form suitable for analysis.

3. The system according to claim 1, further comprising means for notifying a terminal in a store or warehouse of the warning and prompting an employee to take appropriate action.

Images