System

Abstract

A system is provided.SOLUTION: A means for periodically collecting sales data, a means for collecting inventory data, a means for acquiring seasonality information and market trend data, a means for performing demand prediction using an AI algorithm based on the collected data, a means for monitoring the inventory level in real time, a means for automatically generating a replenishment instruction when the inventory level falls below a preset threshold, placing an order, and a means for analyzing the turnover rate of the inventory and proposing an efficient rotation.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] This invention aims to prevent stockouts and excess inventory in inventory management of products and raw materials, reduce management workload, and improve accuracy. In particular, in small and medium-sized enterprises, where inventory management relies on the experience and discretion of the person in charge, unstable inventory management is a problem. In addition, there is a demand for automation of a series of inventory management processes, such as improving the accuracy of demand forecasts, understanding inventory status in real time, and efficiently using old inventory. To address this, a system that utilizes artificial intelligence (AI) to automatically replenish inventory and maintain optimal inventory levels is needed. [Means for solving the problem]

[0005] The present invention solves the above problems by the following means.

[0006] A means of collecting sales data on a regular basis;

[0007] a means for collecting inventory data;

[0008] a means for obtaining seasonality information and market trend data;

[0009] A means of forecasting demand using AI algorithms based on collected data;

[0010] a means of monitoring inventory levels in real time;

[0011] means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold;

[0012] A means to analyze inventory turnover and propose efficient rotation;

[0013] A means to classify and notify slow-selling and hot-selling products in real time,

[0014] This system, which includes the above, will improve the efficiency and accuracy of inventory management.

[0015] Furthermore, by performing data preprocessing and including means for removing invalid data and missing values, the accuracy of the data is improved, and the reliability of demand forecasts is enhanced.

[0016] In addition, adding a means for notifying the user that automatic replenishment has been performed and including an interface for the user to confirm this makes it easier for the user to check management. In this way, the problems of out-of-stock and excess inventory can be solved, and customer satisfaction can be improved.

[0017] "Sales data" is information relating to past sales performance, and is data indicating how many of each product were sold within a specific period of time.

[0018] "Inventory data" is information indicating the quantity and status of currently held products, including the inventory status and remaining quantity of products.

[0019] "Seasonal information" is information that indicates demand patterns that vary depending on a particular season or time of year, such as data related to a particular event such as Christmas or summer.

[0020] "Market trend data" is information used to capture overall market trends and changes in demand, and includes data such as consumer preferences and the popularity of new products.

[0021] An "AI algorithm" is a computational method that uses artificial intelligence to analyze data and make predictions, and includes technologies such as machine learning and deep learning.

[0022] "Demand forecasting" is the process of predicting future demand for a product based on past data and market information.

[0023] "Stock level" is an indicator of the quantity of a product in stock at a particular point in time.

[0024] "Real-time" refers to processing and information updates being carried out instantly at the same time as real time.

[0025] A "replenishment instruction" is an instruction to order new products when inventory is low, such as placing an order with a supplier.

[0026] "Purchase Order" refers to the process of ordering the necessary goods or raw materials from suppliers, and specifically includes transactions with suppliers.

[0027] "Inventory turnover" is an indicator of how much inventory is replaced within a specific period of time, and is usually expressed as the ratio of sales to average inventory.

[0028] "Rotation" is the process of efficiently changing the placement and display of inventory, and includes techniques for prioritizing the consumption of older inventory.

[0029] "Sales" refers to the sales status of a product and indicates how quickly a particular product is selling.

[0030] "Notification" is the process of the system informing the user of important information, such as an alert informing that stock is running low.

[0031] An "interface" refers to a screen or operating means through which a system and a user exchange information, allowing the user to give instructions to the system or check data. [Brief explanation of the drawings]

[0032] [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

[0033] 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.

[0034] First, the terms used in the following description will be explained.

[0035] 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).

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] [First embodiment]

[0041] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0042] 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.

[0043] 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).

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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.

[0048] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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."

[0053] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. Specifically, it operates in cooperation with a server, terminals, and users.

[0054] System configuration

[0055] Data collection

[0056] 1. Server

[0057] The server periodically collects sales data from POS systems and online stores.

[0058] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[0059] The server uses external APIs to obtain seasonal information and market trend data.

[0060] 2. Terminal

[0061] The terminal is responsible for transmitting data from the POS system and online store to the server.

[0062] The terminal works in conjunction with an inventory management system and sends inventory data to a server.

[0063] Data analysis and demand forecasting

[0064] 1. Server

[0065] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[0066] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[0067] The server uses the trained model to predict future demand.

[0068] The server displays the prediction results on a dashboard so that users can view them.

[0069] Stock level monitoring and automatic replenishment

[0070] 1. Server

[0071] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below set thresholds.

[0072] The server automatically sends the order instructions to the supplier.

[0073] The server notifies the user that the replenishment has occurred.

[0074] 2. Users

[0075] The user can check the progress of the order and replenishment on the terminal.

[0076] Inventory Optimization

[0077] 1. Server

[0078] The server analyzes inventory turnover and suggests efficient rotation.

[0079] The server suggests to the user that older stock be given priority in displaying the items.

[0080] 2. Users

[0081] The user updates the product display based on the server's suggestions.

[0082] Real-time tracking

[0083] 1. Server

[0084] The server monitors all inventory status in real time and reflects the latest information on the dashboard.

[0085] The server classifies popular and unpopular items and notifies the user.

[0086] 2. Users

[0087] Users take measures such as promotions and discounts to combat slow-selling products.

[0088] Specific examples

[0089] Data collection

[0090] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[0091] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[0092] Data analysis and demand forecasting

[0093] The server trains the AI ​​model based on sales data from the past October to predict demand for the next week. The forecast results are displayed on a dashboard for users to check.

[0094] Stock level monitoring and automatic replenishment

[0095] When the beverage inventory falls below 50 units, the server automatically sends an order to the supplier. The user can check the replenishment status and approve it via their terminal.

[0096] Inventory Optimization

[0097] The server analyzes the inventory turnover rate and suggests to the user that they should prioritize the display of beverages that arrived in August. The user updates their product display accordingly.

[0098] Real-time tracking

[0099] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[0100] In this way, the system of the present invention operates in cooperation with the server, terminals, and users to improve the efficiency and accuracy of inventory management.

[0101] The processing flow will be explained below.

[0102] Step 1:

[0103] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[0104] Step 2:

[0105] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[0106] Step 3:

[0107] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[0108] Step 4:

[0109] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[0110] Step 5:

[0111] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[0112] Step 6:

[0113] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[0114] Step 7:

[0115] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[0116] Step 8:

[0117] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[0118] Step 9:

[0119] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[0120] Step 10:

[0121] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[0122] Step 11:

[0123] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[0124] Step 12:

[0125] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[0126] Step 13:

[0127] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[0128] Step 14:

[0129] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[0130] Step 15:

[0131] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[0132] Example 1

[0133] 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."

[0134] In conventional inventory management systems, sales and inventory information was often collected manually, making it difficult to ensure accurate data and timely inventory replenishment. Furthermore, demand forecasting and efficient inventory rotation were not performed, increasing the risk of excess inventory and shortages. Furthermore, measures to address poorly selling products were delayed, making it difficult to grasp information on best-selling products in real time.

[0135] 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.

[0136] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal data and market trend information; means for forecasting demand using an artificial intelligence algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying products with poor sales and products with good sales in real time; means including an interface for users to check order status and replenishment; and terminal means for linking with the inventory management system and transmitting collected inventory information to the server. This enables efficient and accurate inventory management, timely inventory replenishment based on demand forecasts, and understanding of sales status in real time.

[0137] "Sales information" refers to data such as the quantity, price, and transaction time of the goods sold.

[0138] "Inventory information" refers to data such as the quantity, type, and storage location of products currently stored in warehouses or stores.

[0139] "Seasonal Data" refers to data regarding sales trends or fluctuations in demand during a particular season or time of year.

[0140] "Market trend information" refers to data that shows overall market trends and changes in consumer behavior.

[0141] "Artificial intelligence algorithms" refer to computer programs and methods for analyzing data and making predictions and decisions.

[0142] "Demand forecasting" refers to the process of predicting future sales volumes.

[0143] "Inventory Level" refers to the quantity of inventory at a particular location.

[0144] A "threshold" refers to a value that indicates a particular standard or limit.

[0145] "Replenishment orders" refer to orders or instructions to add inventory.

[0146] "Placing an order" refers to the process of requesting the supply of required goods.

[0147] "Inventory turnover" refers to the rate at which inventory is sold within a certain period of time.

[0148] "Rotation" refers to strategies and methods for efficiently rotating inventory.

[0149] "Products with poor sales" refers to products whose sales are below expectations.

[0150] "Good selling products" refer to products whose sales are favorable compared to expectations.

[0151] "Notification" refers to a message or alert that notifies you of a specific event.

[0152] "Interface" refers to the means or screen through which a user interacts with a system.

[0153] "Inventory management system" refers to the general term for software and hardware used to manage and monitor inventory information.

[0154] "Terminal" refers to a device or equipment that can be directly operated by a user.

[0155] This invention is a system that uses artificial intelligence (AI) to analyze sales information and inventory information and automate inventory management. This system mainly involves a server, terminals, and users, and operates in the following steps.

[0156] Hardware and software used

[0157] server

[0158] Hardware used: High-performance server computer

[0159] Software used: database software (e.g., MySQL or PostgreSQL), AI libraries (e.g., TensorFlow or PyTorch), data processing libraries (e.g., pandas)

[0160] Terminal

[0161] Hardware used: POS terminal, inventory management system linked terminal

[0162] Software used: Data transmission program, communication library (e.g., HTTP client)

[0163] User

[0164] Hardware required: A standard PC or tablet device

[0165] Software used: Web browser, dashboard display software

[0166] System Operation

[0167] Server Operation

[0168] The server periodically collects sales information from the POS system and online store. Specifically, it executes an SQL query to retrieve sales information in CSV format every night at midnight. The server also retrieves the latest inventory information from the inventory management system every hour. Furthermore, the server retrieves seasonal data and market trend information through an external API.

[0169] The server cleanses the collected data and removes invalid data and missing values. This process uses a data processing library (e.g., pandas). Next, it uses the cleansed data to train a demand forecasting model using an AI algorithm. For training, it uses AI libraries such as TensorFlow and PyTorch.

[0170] A trained AI model is used to predict future demand. The prediction results are displayed in real time on a dashboard for users to review. The server also monitors inventory levels in real time, automatically generating replenishment instructions and placing orders when they fall below a set threshold. The user is notified when replenishment is complete.

[0171] The server also analyzes inventory turnover and proposes efficient rotation by generating a report recommending the prioritization of older inventory.The server also monitors all inventory status in real time, classifying and notifying products that are selling poorly or well.

[0172] Device behavior

[0173] The terminal periodically sends sales information from the POS system and online store to the server. It also works with the inventory management system to send collected inventory information to the server, allowing the server to always obtain the latest information.

[0174] User operations

[0175] Users can use the dashboard provided by the server to check inventory status and demand forecast results in real time. For items that are not selling well, they can take measures such as promotions and discounts. They can also receive notifications from the server to check order status and replenishment and take appropriate action.

[0176] Specific examples

[0177] Server processing example

[0178] The server runs the SQL query "select from sales where date = current_date()" every night to collect sales information from the POS system, updates the latest inventory information every hour, and runs Python scripts to cleanse the data frame with the pandas library and train the AI ​​model with TensorFlow.

[0179] Terminal processing example

[0180] The terminal uploads sales information to the server at regular intervals, and also shares the latest inventory information with the server.

[0181] User operation example

[0182] Users can view the dashboard to see the results of the next week's demand forecast, get notified about slow-selling items, and implement promotions.

[0183] Prompt Sentence Examples

[0184] "Please introduce this system. Please explain in detail the processing steps of the program that uses AI to analyze sales and inventory information and automate inventory management."

[0185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0186] Step 1:

[0187] The server periodically collects sales information. Specifically, it retrieves the day's sales information in CSV format from the POS system every night at midnight. The input is the POS system's sales information database, and the output is the collected CSV file. The server executes an SQL query to extract data using the command "select from sales where date = current_date()". The retrieved data is saved in a specified directory.

[0188] Step 2:

[0189] The server collects inventory information. Specifically, it retrieves the latest inventory data from the inventory management system every hour. The input is the inventory information database of the inventory management system, and the output is the collected inventory data. The server calls the API via an HTTP request to retrieve the inventory data.

[0190] Step 3:

[0191] The server obtains seasonal data and market trend information. Specifically, it uses an external API to obtain weekly forecasts and market trend information. The input is the season information and market data API, and the output is the obtained seasonal data and market trend information. The server sends a request to the REST API endpoint and receives data in JSON format.

[0192] Step 4:

[0193] The server cleanses the collected data, removing invalid data and missing values. The input is the collected sales information, inventory information, seasonal data, and market trend information, and the output is a cleansed dataset. The server uses Python scripts and the pandas library to arrange the data using methods such as "df.dropna()" and "df[df['sales'] > 0]".

[0194] Step 5:

[0195] The server trains an AI demand forecasting model. Specifically, it uses the cleansed data and an AI algorithm (e.g., TensorFlow or PyTorch) to train the demand forecasting model. The input is the cleansed dataset, and the output is the trained point model. The server runs code such as "model.fit(data, epochs=100)" to train the model.

[0196] Step 6:

[0197] The server uses a trained AI model to forecast demand. Specifically, it predicts future sales figures and displays the results on a dashboard. The input is the trained model and the latest data, and the output is the prediction results. The server uses the method "predictions = model.predict(new_data)" to reflect the results on the dashboard.

[0198] Step 7:

[0199] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold (e.g., 50 units). The input is a real-time inventory database, and the output is replenishment orders. The server executes logic such as "if inventory < threshold: generate_replenishment_order()".

[0200] Step 8:

[0201] The server sends the order instruction to the supplier. The input is the automatically generated replenishment instruction, and the output is the order request sent to the supplier. Specifically, the order instruction is sent to the supplier via an API request.

[0202] Step 9:

[0203] The user checks for replenishment. Specifically, they receive a notification from the server and check the order status on the dashboard. The input is the notification from the server, and the output is the user's confirmation and response. The user checks the order status and replenishment status on the dashboard and takes the necessary action.

[0204] Step 10:

[0205] The server analyzes inventory turnover and proposes efficient rotation. The input is real-time inventory data, and the output is the turnover analysis results and a proposal report. The server uses a data analysis algorithm to calculate efficient inventory rotation and proposes it to the user.

[0206] Step 11:

[0207] The server grasps sales status in real time, classifies products into those that are selling poorly and those that are selling well, and notifies them. The input is real-time sales data, and the output is the classification results and notifications. The server periodically analyzes the data and notifies the dashboard and users.

[0208] (Application example 1)

[0209] 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."

[0210] In today's brick-and-mortar stores, improving the efficiency and accuracy of inventory management is a key issue. In particular, there is a need to grasp sales and inventory data in real time, forecast demand, and replenish inventory at the appropriate time. It is also necessary to take prompt action to address poorly selling items and propose efficient product display solutions. However, these tasks require a lot of time and effort, and are prone to human error. Furthermore, there is a need for a system that allows store managers and staff to instantly grasp the situation on-site.

[0211] 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.

[0212] In this invention, the server includes: means for periodically collecting sales data; means for collecting inventory data; means for acquiring seasonal information and market trend data; means for forecasting demand using an AI algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; means for checking inventory status in real time using a smart device (smartphone or smart glasses); means for proposing promotions for slow-selling items; and means for proposing replenishment times based on future demand forecasts. This enables the efficiency and accuracy of inventory management in physical stores to be improved.

[0213] "Sales data" refers to data relating to the quantity and amount of purchased goods generated through sales activities at physical stores.

[0214] "Inventory data" refers to data regarding the quantity and types of products currently stored in a physical store.

[0215] "Seasonal information" is information relating to sales trends and demand that fluctuate during specific seasons or periods.

[0216] "Market trend data" is the latest information on overall market trends and consumer purchasing habits.

[0217] An "AI algorithm" is a computational method using artificial intelligence to analyze massive amounts of data, find patterns, and derive next actions or predictions.

[0218] "Demand forecasting" is the process of predicting future sales volumes and demand based on past sales data and market trends.

[0219] "Inventory level" refers to the status of the number of specific items in stock in a store or warehouse.

[0220] A "replenishment instruction" is an instruction to add stock when the stock falls below a certain threshold.

[0221] "Placing an order" is the act of ordering goods from a supplier.

[0222] "Turnover rate" is an indicator that indicates the sales rate of inventory items over a certain period of time.

[0223] "Rotation" is the process of changing the placement and order of inventory items to ensure proper management.

[0224] A "best-selling product" is a product that is currently very popular and is being purchased by many consumers.

[0225] A "slow-selling product" is a product that is not being purchased much by consumers at the moment.

[0226] "Notification" is the act of promptly notifying a user of specific information.

[0227] A "smart device" is a portable electronic device (e.g., a smartphone or smart glasses) that can connect to the Internet and send and receive information.

[0228] "Promotion" refers to advertising and campaign activities to promote sales of slow-selling products.

[0229] The invention is a system that improves the efficiency and accuracy of inventory management in physical stores. This system uses AI to analyze sales data and inventory data and automates inventory management. An embodiment of this system is described below.

[0230] System configuration

[0231] The system consists of three main parts: the server, the terminal, and the user. The specific operation procedure is as follows:

[0232] Data collection

[0233] server

[0234] The server periodically collects sales data from POS systems and online stores, obtains current inventory data from inventory management systems, and uses external APIs to obtain seasonal information and market trend data.

[0235] Terminal

[0236] The terminal is responsible for sending data from the POS system or online store to the server. The terminal is used to link inventory data to the server.

[0237] Data analysis and demand forecasting

[0238] server

[0239] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[0240] Based on the cleansed data, an AI algorithm is used to train a demand forecasting model to predict future demand.

[0241] The prediction results are reflected in the dashboard and can be viewed by users.

[0242] Stock level monitoring and automatic replenishment

[0243] server

[0244] The server monitors inventory levels in real time and automatically generates replenishment instructions and sends order instructions to suppliers when inventory levels fall below a set threshold.

[0245] When the replenishment is completed, the user is notified.

[0246] User

[0247] Users can check the order progress and replenishment status on the terminal.

[0248] Inventory Optimization

[0249] server

[0250] The server analyzes inventory turnover and suggests efficient rotation.

[0251] The system suggests to the user to prioritize displaying older stock.

[0252] User

[0253] The user updates the product display based on the server's suggestions.

[0254] Real-time tracking and promotions

[0255] server

[0256] The server monitors all inventory status in real time and updates the dashboard with the latest information.

[0257] Categorize best-selling and worst-selling items and notify users.

[0258] User

[0259] Take measures such as promotions and discounts on slow-selling products.

[0260] Example of a system

[0261] This system is realized using specific hardware and software. The hardware used is a server equipped with a high-performance database and an AI computing unit, and smartphones or smart glasses are suitable terminals. The software used is Python Flask or Django for the server, and React Native (smartphones) or ARKit (smart glasses) for the client. TensorFlow and Keras are used for data analysis.

[0262] Specific example explanation

[0263] For example, the server collects the day's sales data from the POS system overnight and updates the current stock status from the inventory management system. Using a smartphone or smart glasses, store staff can check the stock status in real time. Furthermore, an AI model is used to predict demand for the next week based on past sales data, and the results suggest the appropriate time for replenishment.

[0264] Example prompt sentence:

[0265] "Please refer to the sales data for the past three years as of mid-October and forecast demand for next week."

[0266] By inputting these prompts, the AI ​​model performs detailed data analysis and provides specific demand forecasts, thereby improving the efficiency and accuracy of inventory management in physical stores.

[0267] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0268] Step 1:

[0269] The server collects sales data

[0270] Input: Sales data from POS systems and online stores

[0271] Specific operation: The server periodically connects to the POS system or online store to collect sales data, for example, by retrieving data through an API in the middle of the night.

[0272] Output: Collected sales data is stored on the server

[0273] Step 2:

[0274] The server collects inventory data

[0275] Input: Inventory data from inventory management system

[0276] Specific operation: The server connects to the inventory management system to obtain current inventory data, retrieves the data via API, and stores it on the server.

[0277] Output: The latest inventory data is stored on the server.

[0278] Step 3:

[0279] Server retrieves seasonal information and market trend data

[0280] Input: Seasonality and market trend data from external APIs

[0281] What it does: The server sends requests to external APIs to retrieve seasonality and market trend data. This can involve web scraping or API calls.

[0282] Output: The acquired seasonal information and market trend data is stored on the server.

[0283] Step 4:

[0284] The server cleanses the data

[0285] Inputs: Collected sales data, inventory data, seasonality information, market trend data

[0286] Specific operation: The server cleanses the collected data and removes invalid data and missing values. For example, it filters out data with negative values ​​and missing values.

[0287] Output: The cleansed data is passed to the AI ​​algorithm

[0288] Step 5:

[0289] The server uses an AI algorithm to predict demand.

[0290] Input: Cleansed data

[0291] How it works: The server uses the cleansed data to train an AI model to predict future demand, for example, using past sales data to predict sales for the next week.

[0292] Output: Forecasted supply and demand data is generated

[0293] Step 6:

[0294] The server monitors inventory levels in real time.

[0295] Input: Latest inventory data

[0296] What it does: The server monitors inventory levels in real time and immediately issues an alert if they fall below a set threshold.

[0297] Output: Status information on whether stock levels are normal or not

[0298] Step 7:

[0299] The server automatically generates replenishment instructions and places orders.

[0300] Input: Stock level status information

[0301] Specific operation: When the inventory level falls below a threshold, the server automatically generates replenishment instructions and sends order instructions to the supplier.

[0302] Output: Purchase order sent to supplier

[0303] Step 8:

[0304] The server analyzes inventory turnover and suggests efficient rotation.

[0305] Input: Past sales data and inventory data

[0306] Specific operation: The server calculates the inventory turnover rate and suggests an efficient display method, for example, suggesting that old inventory should be displayed at the front and new inventory at the back.

[0307] Output: The user is notified of the rotation suggestion

[0308] Step 9:

[0309] The server proposes a promotion for a slow-selling item

[0310] Input: Real-time sales data

[0311] What it does: The server detects slow-selling products and offers promotions or discounts for them, for example, offering limited-time sales on specific products.

[0312] Output: The user is notified of the promotion offer.

[0313] Step 10:

[0314] Users can check inventory status in real time using their smart devices.

[0315] Input: Stock status data provided by the server

[0316] Specific operation: The user checks the inventory status in real time through the application via a smartphone or smart glasses, for example, by viewing the inventory status on the in-app dashboard.

[0317] Output: Action guidelines based on the inventory status identified by the user

[0318] 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.

[0319] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. In addition, by combining this with an emotion engine that recognizes user emotions, it realizes more user-friendly inventory management.

[0320] System configuration

[0321] Data collection

[0322] 1. Server

[0323] The server periodically collects sales data from POS systems and online stores, and stores the collected data in a database on the server.

[0324] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[0325] The server uses external APIs to obtain seasonal information and market trend data.

[0326] 2. Terminal

[0327] The terminal sends sales data from the POS system or online store to the server. The data is sent to the server in real time as each transaction occurs.

[0328] The terminal connects to the inventory management system and sends inventory data to the server.

[0329] Data analysis and demand forecasting

[0330] 1. Server

[0331] The server cleanses the collected data, removing any invalid data or missing values.

[0332] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[0333] Use the trained model to predict future demand and display the forecast results in a dashboard.

[0334] Stock level monitoring and automatic replenishment

[0335] 1. Server

[0336] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold.

[0337] The server automatically sends the order instructions to the supplier.

[0338] The server notifies the user that the replenishment has occurred.

[0339] 2. Users

[0340] Users can check the order progress and replenishment status on the terminal.

[0341] Inventory Optimization

[0342] 1. Server

[0343] The server analyzes inventory turnover and suggests efficient rotation.

[0344] The server suggests to the user that older stock be given priority in displaying the items.

[0345] 2. Users

[0346] The user updates the product display based on the server's suggestions.

[0347] Real-time tracking

[0348] 1. Server

[0349] The server monitors inventory status in real time and displays the latest information on the dashboard.

[0350] The server classifies popular and unpopular items and notifies the user.

[0351] 2. Users

[0352] Users take measures such as promotions and discounts to combat slow-selling products.

[0353] Emotion engine integration

[0354] 1. Emotion Engine

[0355] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine collects emotional data through facial recognition and voice analysis.

[0356] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[0357] The server adjusts inventory management methods based on the user's emotional state and optimizes notifications and suggestions to reduce stress for the user.

[0358] 2. Users

[0359] Users receive notifications and suggestions based on emotion recognition from the server and provide feedback on inventory management as needed.

[0360] Specific examples

[0361] Data collection

[0362] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[0363] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[0364] Data analysis and demand forecasting

[0365] The server trains the AI ​​model based on past sales data to predict demand for the next week, and the forecast results are displayed on a dashboard for users to view.

[0366] Stock level monitoring and automatic replenishment

[0367] When beverage inventory falls below a specified threshold, the server automatically sends an order to the supplier, and the user can check the replenishment status and approve it via their terminal.

[0368] Inventory Optimization

[0369] The server analyzes the inventory turnover rate and suggests to the user to prioritize the display of older inventory. The user updates the product display based on the suggestions.

[0370] Real-time tracking

[0371] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[0372] Emotion engine integration

[0373] The server recognizes the user's emotions and adjusts the frequency of notifications or displays positive messages if the user is feeling stressed.

[0374] Users take appropriate inventory management actions based on feedback from the emotion engine to maintain efficient operations.

[0375] In this way, the system of the present invention links the server, terminals, and users, and further integrates the emotion engine, thereby improving the efficiency and accuracy of inventory management and reducing the burden on users.

[0376] The processing flow will be explained below.

[0377] Step 1:

[0378] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[0379] Step 2:

[0380] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[0381] Step 3:

[0382] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[0383] Step 4:

[0384] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[0385] Step 5:

[0386] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[0387] Step 6:

[0388] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[0389] Step 7:

[0390] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[0391] Step 8:

[0392] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[0393] Step 9:

[0394] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[0395] Step 10:

[0396] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[0397] Step 11:

[0398] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[0399] Step 12:

[0400] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[0401] Step 13:

[0402] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[0403] Step 14:

[0404] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[0405] Step 15:

[0406] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[0407] Step 16:

[0408] The server collects emotional data using an emotion engine that recognizes the user's emotions. Specifically, it obtains the user's emotional state in real time through facial recognition and voice analysis.

[0409] Step 17:

[0410] The server analyzes the collected emotional data in real time to understand the user's current emotional state, for example, detecting if the user is feeling stressed.

[0411] Step 18:

[0412] The server adjusts inventory management methods based on the user's emotional state, for example, reducing the frequency of notifications and displaying positive messages if the user is feeling stressed.

[0413] Step 19:

[0414] The user receives notifications and suggestions based on emotion recognition from the server, and provides feedback on inventory management as needed. By accepting responses based on emotions, the user can manage inventory while reducing stress.

[0415] In this way, the system of the present invention allows the server, terminals, and users to work together, and by integrating an emotion engine, it is possible to improve the efficiency and accuracy of inventory management while also reducing the burden on users.

[0416] Example 2

[0417] 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."

[0418] In modern inventory management systems, it is important to effectively manage sales and inventory information in real time and to perform highly accurate demand forecasts. However, in conventional systems, data collection and analysis are often performed manually, resulting in problems with efficiency and accuracy. In addition, inventory management and notifications do not take user emotions into account, which tends to place a heavy burden on users. To solve these issues, a more automated and highly accurate inventory management system is needed.

[0419] 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.

[0420] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal information and market trend information; means for forecasting demand using an AI algorithm based on the collected information; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; and means for recognizing a user's emotional state using an emotion engine and optimizing notifications and suggestions. This automates a series of processes, from collecting sales and inventory information to demand forecasting and optimal notifications and suggestions based on the user's emotions, enabling more efficient and accurate inventory management.

[0421] "Sales information" is data relating to the sales results of products and services, and includes details such as the date and time of the transaction, product name, quantity, and price.

[0422] "Inventory information" is data that indicates the current inventory status, such as the quantity of products stored in warehouses or stores, inventory history, and location information.

[0423] "Seasonal information" is data on consumption trends and sales trends related to specific seasons or events.

[0424] "Market trend information" is data on economic trends, such as the current market supply and demand balance and changes in consumer preferences.

[0425] An "AI algorithm" is a mathematical model or method for analyzing and predicting data using artificial intelligence technology.

[0426] "Demand forecasting" is the process of predicting future sales volumes based on past sales data and external factors.

[0427] "Stock level" is information that indicates how much of a particular product is currently in stock.

[0428] A "replenishment instruction" is an instruction to replenish new products when inventory is low.

[0429] "Placing an order" is the process of ordering goods from a supplier or source.

[0430] "Inventory turnover" is an indicator that shows how much merchandise is being brought in and out of stock over a certain period of time.

[0431] "Rotation" is a method of efficiently managing inventory by replacing it chronologically.

[0432] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[0433] "Notification" refers to notifications or notices sent from the system to the user.

[0434] A "suggestion" is a recommendation of an action or improvement method for the system to take to the user.

[0435] This invention is a system that collects sales information and inventory information, forecasts demand based on the information, and automates inventory management. Furthermore, by combining it with an emotion engine that recognizes user emotions, it has the advantage of reducing the burden on users.

[0436] System configuration

[0437] Data collection

[0438] server

[0439] The server periodically collects sales information from POS systems and online stores, makes API calls using a scripting language such as Python, retrieves the data, and stores it in a database.

[0440] The server collects inventory information in real time from the inventory management system, retrieves the data using HTTP requests, and stores it in a database.

[0441] The server also periodically retrieves seasonal and market trend information using external APIs, including, for example, weather forecast APIs and market trend APIs.

[0442] Terminal

[0443] The terminal transmits sales information to the server in real time each time a transaction occurs in a POS system or online store.

[0444] The terminals work in conjunction with an inventory management system and send inventory information to the server, which ensures that the latest inventory status is always reflected.

[0445] Data analysis and demand forecasting

[0446] server

[0447] The server cleanses the collected data, using the Python Pandas library to remove invalid data and missing values.

[0448] The server uses AI algorithms to train demand forecasting models based on the cleansed data, using machine learning libraries such as TensorFlow and Scikit-learn.

[0449] The trained model is used to predict future demand and the results are displayed in a dashboard, which users can view through a browser-based dashboard.

[0450] Stock level monitoring and automatic replenishment

[0451] server

[0452] The server monitors inventory levels in real time and automatically generates replenishment orders if they fall below a set threshold.

[0453] The server then places orders with suppliers based on the generated replenishment instructions. Orders are placed via email or a dedicated API.

[0454] The server notifies the user that the refill is complete.

[0455] User

[0456] Users can check the progress of their orders and check replenishment status through a dedicated interface, and are notified immediately when replenishment is complete.

[0457] Inventory Optimization

[0458] server

[0459] The server analyzes inventory turnover and suggests efficient rotation, for example, suggesting to the user to prioritize displaying older inventory.

[0460] Computer programs find ways to avoid inventory delays and backlogs and rotate products efficiently.

[0461] User

[0462] The user updates the product display based on the server's suggestions.

[0463] Real-time tracking

[0464] server

[0465] The server monitors all inventory status in real time, and the latest information is reflected on the dashboard.

[0466] The server classifies popular and unpopular items and notifies the user.

[0467] User

[0468] Users take measures such as promotions and discounts to combat slow-selling products.

[0469] Emotion engine integration

[0470] Emotion Engine

[0471] The server is equipped with an emotion engine that recognizes the user's emotions and collects emotional information through facial recognition and voice analysis.

[0472] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[0473] The server adjusts the content and frequency of notifications and suggestions based on the user's emotional state. By providing positive messages and timely notifications, the server reduces the user's stress.

[0474] User

[0475] Users receive and utilize the feedback and suggestions provided by the emotion engine to improve the efficiency of their inventory management.

[0476] Specific examples

[0477] A specific example of this is a process in which the server collects the day's sales information from the POS system in the middle of the night and obtains the latest stock status from the inventory management system.The server also trains an AI model based on past sales information to predict demand for the next week, and displays the results on a dashboard so that users can check them.

[0478] Prompt Sentence Examples

[0479] "Please provide an outline of your system for efficiently managing sales and inventory data. Also, explain how you use AI to analyze the collected data and how you build a user-friendly interface using an emotion engine."

[0480] In this way, the system of the present invention aims to improve the efficiency and accuracy of inventory management by linking the server, terminals, and users and further integrating the emotion engine.

[0481] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0482] Step 1:

[0483] Collection of sales information

[0484] The server periodically collects sales information from POS systems and online stores. For example, it uses a Python script to retrieve sales data from an API endpoint. It receives sales data from the API endpoint (transaction date and time, product name, quantity, price, etc.) as input and stores the sales data in a database as output.

[0485] Step 2:

[0486] Collecting inventory information

[0487] The server collects inventory information from the inventory management system in real time. It retrieves the inventory information using HTTP requests and stores it in a database. It receives current inventory information (product ID, quantity, location, etc.) from the inventory management system as input, and updates the database with the latest inventory status as output.

[0488] Step 3:

[0489] Obtaining seasonal and market trend information

[0490] The server uses external APIs to obtain seasonal and market trend information. Specifically, it obtains information from specified API endpoints. It receives seasonal and market trend data (weather information, consumption trends, etc.) as input and stores this data in a database as output.

[0491] Step 4:

[0492] Data Cleansing

[0493] The server cleanses the collected sales, inventory, seasonality, and market trend information. It uses the Python Pandas library to cleanse the data and remove incorrect data and missing values. It takes all the collected data as input and produces a cleansed dataset as output.

[0494] Step 5:

[0495] Training a demand forecasting model

[0496] The server uses AI algorithms to train a demand forecasting model based on the cleansed data. It uses machine learning libraries such as TensorFlow and Scikit-learn. It receives the cleansed dataset as input, selects features from the data, and trains the model. It generates a trained demand forecasting model as output.

[0497] Step 6:

[0498] Demand forecasting

[0499] The server uses the trained model to predict future demand. It provides new sales information and external information as inputs to the model and outputs future demand. The output results are reflected in a dashboard and provided to users in a visualized form.

[0500] Step 7:

[0501] Monitoring inventory levels

[0502] The server monitors inventory levels in real time and generates alerts if they fall below a set threshold. It receives real-time inventory information as input, checks inventory levels, and generates alerts as output, indicating that the conditions for a replenishment order have been met.

[0503] Step 8:

[0504] Generate replenishment orders

[0505] The server automatically generates replenishment orders when inventory levels fall below a set threshold. It receives inventory level alerts as input and creates replenishment orders. It sends the generated replenishment orders to suppliers as output.

[0506] Step 9:

[0507] Ordering from suppliers

[0508] The server places an order with the supplier based on the replenishment instructions. It sends order information via email or a dedicated API. It receives replenishment instructions as input and sends an order to the supplier. It outputs confirmation that the order information has been sent.

[0509] Step 10:

[0510] Inventory Turnover Analysis

[0511] The server analyzes inventory turnover. It combines sales data and inventory data for analysis and proposes efficient rotation. It receives past sales information and inventory information as input and calculates the turnover rate. It generates the inventory turnover analysis results as output and presents them to the user as a proposal.

[0512] Step 11:

[0513] Proposal for efficient rotation

[0514] The server suggests to the user to prioritize stocking older stock based on the results of inventory turnover analysis. It receives the results of the turnover analysis as input, generates a suggestion for efficient rotation, and notifies the user of the suggestion as output.

[0515] Step 12:

[0516] Real-time inventory monitoring

[0517] The server monitors the inventory status in real time and reflects the latest information on the dashboard. It receives real-time inventory data as input, updates the dashboard, and visualizes the latest information as output and provides it to the user.

[0518] Step 13:

[0519] Best-selling product categories

[0520] The server analyzes the sales data and classifies popular and unpopular products. It uses the sales data as input and applies machine learning algorithms to perform the classification. It then returns the classification results to the user as output.

[0521] Step 14:

[0522] Unpopular product notifications

[0523] The server notifies the user about unpopular products. It uses the product classification results as input and generates a notification. It notifies the user about unpopular products as output.

[0524] Step 15:

[0525] Collecting Emotional Data

[0526] The server collects emotion data using an emotion engine to recognize user emotions. It performs face recognition and voice analysis via a camera and microphone. It receives real-time face and voice data as input and generates emotion data. It generates emotion data for analysis as output.

[0527] Step 16:

[0528] Emotional state analysis

[0529] The server analyzes the collected emotional data in real time to understand the user's current emotional state. It uses the emotional data as input and applies an algorithm to analyze it, generating data that determines the user's emotional state as output.

[0530] Step 17:

[0531] Notification optimization

[0532] The server optimizes the content and frequency of notifications based on the user's emotional state. If the user is feeling stressed, it reduces the frequency of notifications and displays positive messages. It uses the emotional state data as input and modifies the notification strategy. It outputs the optimized notifications to the user.

[0533] (Application example 2)

[0534] 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."

[0535] Conventional inventory management systems had the ability to collect sales and inventory data to forecast demand and automatically generate replenishment instructions, but they were unable to adjust inventory management methods taking user emotions into account. Furthermore, they lacked a means for store staff to check inventory status in real time and respond based on customer emotions. As a result, they were unable to fully improve inventory management efficiency or user satisfaction.

[0536] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting sales data, means for collecting inventory data, means for acquiring seasonal information and market trend data, means for performing demand forecasting using an AI algorithm based on the collected data, means for monitoring inventory levels in real time, means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold, means for analyzing inventory turnover and proposing efficient rotation, means for classifying and notifying slow-selling and fast-selling items in real time, means for integrating an emotion processing engine that recognizes user emotions and collecting emotion data through facial recognition and voice analysis, means for adjusting an inventory management method according to the user's emotional state based on the collected emotion data, and means for displaying inventory status in real time using smart glasses and proposing responses based on customer emotions. This enables improved efficiency and accuracy of inventory management, reduced user burden, and improved customer satisfaction.

[0537] Key Word Definitions

[0538] "Sales data" refers to information relating to the sale of a product, and includes data such as the transaction date and time, product name, sales quantity, and price.

[0539] "Inventory data" is information indicating the quantity and location of currently held products, the condition of each product, and the inventory history.

[0540] "Seasonal information" is data about sales patterns and consumer behavior that are affected by seasonal fluctuations.

[0541] "Market trend data" refers to information about current market consumer demand, trends, competitor trends, and so on.

[0542] "AI algorithm" is a general term for computational methods and mathematical models used to analyze and predict data using artificial intelligence.

[0543] "Demand forecasting" is the process of analyzing past sales data and market trend data to predict future demand for products.

[0544] "Stock level" is a value that indicates the number of a particular product in stock at a given point in time.

[0545] A "threshold" is a set value that is a criterion for the occurrence of a specific condition or event.

[0546] A "replenishment order" is an order to a supplier or warehouse to supply goods when inventory is low.

[0547] "Turnover rate" is an indicator that shows the frequency of goods being received and shipped, and is a criterion for evaluating inventory efficiency.

[0548] "Rotation" is a method for efficiently managing inventory placement and shipping order.

[0549] The "emotion processing engine" is a system that analyzes the user's facial expressions and voice and recognizes their emotions.

[0550] "Facial recognition" is a technology that uses a camera to detect a person's face and obtain its identification information.

[0551] "Voice analysis" is a technology that analyzes voice data to detect its content and the speaker's emotions.

[0552] "Emotion data" is information that expresses the user's emotional state in numerical values ​​or categories.

[0553] "Smart glasses" are eyeglass-type devices with display capabilities that allow users to view information in real time.

[0554] "Real-time inventory display" means that the current inventory information is displayed on the smart glasses at that moment.

[0555] "Customer emotion-based response" is the process of providing optimal service and product recommendations based on the customer's recognized emotional state.

[0556] MODE FOR CARRYING OUT THE INVENTION

[0557] To implement this invention, the system is mainly composed of a server, a terminal, and a user. The functions of each component and specific implementation methods thereof will be described below.

[0558] Server Functions and Implementation Methods

[0559] 1. Collect sales and inventory data:

[0560] The server periodically collects sales data from the POS system and online store and stores it in a database. It also retrieves current inventory data from the inventory management system. This allows for accurate inventory status in real time. The collected data is processed using Python libraries (e.g., Pandas and SQLAlchemy).

[0561] 2. Obtaining seasonality and market trend data:

[0562] The server obtains seasonal data and market trend information through external APIs, such as weather information APIs and market data APIs, and uses this data to forecast future demand.

[0563] 3. Demand forecasting using AI algorithms:

[0564] Train demand forecasting models based on collected sales, inventory, seasonality, and market trend data. Use Python machine learning libraries (e.g., TensorFlow and scikit-learn) to build and operate forecasting models based on historical data.

[0565] 4. Inventory level monitoring and automatic replenishment instructions:

[0566] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold, which are then sent to suppliers and notify the user upon completion.

[0567] 5. Emotion processing engine integration:

[0568] The server integrates an emotion processing engine that uses facial recognition and voice analysis to recognize user emotions. This includes facial recognition and voice analysis technologies using OpenCV and TensorFlow. The collected emotion data is analyzed in real time and used to adjust the inventory management system.

[0569] 6. Information display using smart glasses:

[0570] The smart glasses allow store staff to check stock availability in real time, and the same display also shows how to respond based on the customer's emotional state, using data transfer via Bluetooth and Wi-Fi.

[0571] Terminal functions and implementation methods

[0572] 1. Data transmission:

[0573] The terminal sends sales and inventory data in CSV format to the server, which transmits this data in real time as each transaction occurs.

[0574] 2. User Interface:

[0575] It provides an interface for users to check inventory information and replenishment status. Web applications and native applications are provided using smart devices (e.g., smartphones and tablets).

[0576] User roles and examples

[0577] 1. Real-time inventory check and action:

[0578] Users wear smart glasses and can check inventory information and demand forecast data in real time. For example, if a beverage runs low on stock, a notification will appear on the glasses and an order to replenish the supply will be automatically sent to the supplier.

[0579] 2. Emotional customer service:

[0580] If the customer is smiling, the prompt will say "Let us know if we can help you," and if the customer is unhappy, the prompt will say "Is there a problem?". Examples of such prompts include:

[0581] If the customer is smiling, it says "Let us know if we can help you."

[0582] If the customer seems unhappy, it asks, "Is there a problem?"

[0583] When stock is low, you will receive a notification saying, "Stock is low. Please prepare to replenish."

[0584] There is.

[0585] This system will improve the efficiency and accuracy of inventory management, reduce the burden on users, and increase customer satisfaction.

[0586] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0587] Program processing flow

[0588] Step 1:

[0589] The server periodically collects sales data from POS systems and online stores and stores it in a database. Specifically, sales data is sent from the terminal to the server in real time when each transaction occurs. The input data is sales information (product ID, number of units sold, price, date and time), and libraries such as Pandas and SQLAlchemy are used to store this in the database. The latest sales data is saved in the database as output.

[0590] Step 2:

[0591] The server collects current inventory data from the inventory management system and grasps the latest inventory status. The input data is inventory information (product ID, inventory quantity, warehouse location), which is also saved in the database in real time. The output is the latest inventory data saved in the database.

[0592] Step 3:

[0593] The server uses external APIs to obtain seasonal information and market trend data. Examples of data obtained from APIs include weather information and past sales trends. After obtaining this data, it is used as a training dataset for the AI ​​model. Seasonal information and market trend data are collected as input, and these data are stored in a database as output.

[0594] Step 4:

[0595] The server uses an AI algorithm to make demand forecasts based on the collected sales data, inventory data, seasonal information, and market trend data. Specifically, it uses TensorFlow and scikit-learn to build and train a predictive model based on past data. Past sales data, inventory data, seasonal information, and market trend data are required as input, and future demand forecast results are obtained as output.

[0596] Step 5:

[0597] The server monitors inventory levels in real time based on the results of demand forecasts and automatically generates replenishment instructions when they fall below a set threshold. Specifically, it checks inventory data using Python processing, and if it falls below the threshold, it takes action to send replenishment instructions to suppliers by email or API. Real-time inventory data and a threshold are required as input, and the replenishment instructions are sent to suppliers as output.

[0598] Step 6:

[0599] A user wearing smart glasses can check inventory information in real time. This information is sent from the server to the smart glasses via Bluetooth or WiFi, and the current inventory status is displayed. The input is inventory information from the server, and the output is the inventory status displayed on the smart glasses display.

[0600] Step 7:

[0601] The server runs an emotion processing engine that performs facial recognition and voice analysis to recognize the user's emotions. It uses OpenCV and TensorFlow to perform facial recognition and voice analysis and collect emotion data. Raw data from the camera and microphone is required as input, and the output is the user's emotional state expressed as a number or category.

[0602] Step 8:

[0603] The user receives a prompt based on the emotional data displayed through the smart glasses. For example, if the customer is smiling, the smart glasses will display a prompt such as "Let us know if we can help you," and if the customer is in a bad mood, the smart glasses will display a prompt such as "Is there a problem?". An appropriate message is generated based on the emotional data as input, and the message is displayed on the smart glasses as output.

[0604] This series of processes makes inventory management more efficient, improves accuracy, reduces the burden on users, and improves customer satisfaction.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] [Second embodiment]

[0609] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0610] 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.

[0611] 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).

[0612] 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.

[0613] 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.

[0614] 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).

[0615] 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.

[0616] 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.

[0617] 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.

[0618] 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.

[0619] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0620] 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."

[0621] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. Specifically, it operates in cooperation with a server, terminals, and users.

[0622] System configuration

[0623] Data collection

[0624] 1. Server

[0625] The server periodically collects sales data from POS systems and online stores.

[0626] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[0627] The server uses external APIs to obtain seasonal information and market trend data.

[0628] 2. Terminal

[0629] The terminal is responsible for transmitting data from the POS system and online store to the server.

[0630] The terminal works in conjunction with an inventory management system and sends inventory data to a server.

[0631] Data analysis and demand forecasting

[0632] 1. Server

[0633] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[0634] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[0635] The server uses the trained model to predict future demand.

[0636] The server displays the prediction results on a dashboard so that users can view them.

[0637] Stock level monitoring and automatic replenishment

[0638] 1. Server

[0639] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below set thresholds.

[0640] The server automatically sends the order instructions to the supplier.

[0641] The server notifies the user that the replenishment has occurred.

[0642] 2. Users

[0643] The user can check the progress of the order and replenishment on the terminal.

[0644] Inventory Optimization

[0645] 1. Server

[0646] The server analyzes inventory turnover and suggests efficient rotation.

[0647] The server suggests to the user that older stock be given priority in displaying the items.

[0648] 2. Users

[0649] The user updates the product display based on the server's suggestions.

[0650] Real-time tracking

[0651] 1. Server

[0652] The server monitors all inventory status in real time and reflects the latest information on the dashboard.

[0653] The server classifies popular and unpopular items and notifies the user.

[0654] 2. Users

[0655] Users take measures such as promotions and discounts to combat slow-selling products.

[0656] Specific examples

[0657] Data collection

[0658] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[0659] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[0660] Data analysis and demand forecasting

[0661] The server trains the AI ​​model based on sales data from the past October to predict demand for the next week. The forecast results are displayed on a dashboard for users to check.

[0662] Stock level monitoring and automatic replenishment

[0663] When the beverage inventory falls below 50 units, the server automatically sends an order to the supplier. The user can check the replenishment status and approve it via their terminal.

[0664] Inventory Optimization

[0665] The server analyzes the inventory turnover rate and suggests to the user that they should prioritize the display of beverages that arrived in August. The user updates their product display accordingly.

[0666] Real-time tracking

[0667] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[0668] In this way, the system of the present invention operates in cooperation with the server, terminals, and users to improve the efficiency and accuracy of inventory management.

[0669] The processing flow will be explained below.

[0670] Step 1:

[0671] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[0672] Step 2:

[0673] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[0674] Step 3:

[0675] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[0676] Step 4:

[0677] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[0678] Step 5:

[0679] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[0680] Step 6:

[0681] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[0682] Step 7:

[0683] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[0684] Step 8:

[0685] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[0686] Step 9:

[0687] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[0688] Step 10:

[0689] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[0690] Step 11:

[0691] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[0692] Step 12:

[0693] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[0694] Step 13:

[0695] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[0696] Step 14:

[0697] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[0698] Step 15:

[0699] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[0700] Example 1

[0701] 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."

[0702] In conventional inventory management systems, sales and inventory information was often collected manually, making it difficult to ensure accurate data and timely inventory replenishment. Furthermore, demand forecasting and efficient inventory rotation were not performed, increasing the risk of excess inventory and shortages. Furthermore, measures to address poorly selling products were delayed, making it difficult to grasp information on best-selling products in real time.

[0703] 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.

[0704] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal data and market trend information; means for forecasting demand using an artificial intelligence algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying products with poor sales and products with good sales in real time; means including an interface for users to check order status and replenishment; and terminal means for linking with the inventory management system and transmitting collected inventory information to the server. This enables efficient and accurate inventory management, timely inventory replenishment based on demand forecasts, and understanding of sales status in real time.

[0705] "Sales information" refers to data such as the quantity, price, and transaction time of the goods sold.

[0706] "Inventory information" refers to data such as the quantity, type, and storage location of products currently stored in warehouses or stores.

[0707] "Seasonal Data" refers to data regarding sales trends or fluctuations in demand during a particular season or time of year.

[0708] "Market trend information" refers to data that shows overall market trends and changes in consumer behavior.

[0709] "Artificial intelligence algorithms" refer to computer programs and methods for analyzing data and making predictions and decisions.

[0710] "Demand forecasting" refers to the process of predicting future sales volumes.

[0711] "Inventory Level" refers to the quantity of inventory at a particular location.

[0712] A "threshold" refers to a value that indicates a particular standard or limit.

[0713] "Replenishment orders" refer to orders or instructions to add inventory.

[0714] "Placing an order" refers to the process of requesting the supply of required goods.

[0715] "Inventory turnover" refers to the rate at which inventory is sold within a certain period of time.

[0716] "Rotation" refers to strategies and methods for efficiently rotating inventory.

[0717] "Products with poor sales" refers to products whose sales are below expectations.

[0718] "Good selling products" refer to products whose sales are favorable compared to expectations.

[0719] "Notification" refers to a message or alert that notifies you of a specific event.

[0720] "Interface" refers to the means or screen through which a user interacts with a system.

[0721] "Inventory management system" refers to the general term for software and hardware used to manage and monitor inventory information.

[0722] "Terminal" refers to a device or equipment that can be directly operated by a user.

[0723] This invention is a system that uses artificial intelligence (AI) to analyze sales information and inventory information and automate inventory management. This system mainly involves a server, terminals, and users, and operates in the following steps.

[0724] Hardware and software used

[0725] server

[0726] Hardware used: High-performance server computer

[0727] Software used: database software (e.g., MySQL or PostgreSQL), AI libraries (e.g., TensorFlow or PyTorch), data processing libraries (e.g., pandas)

[0728] Terminal

[0729] Hardware used: POS terminal, inventory management system linked terminal

[0730] Software used: Data transmission program, communication library (e.g., HTTP client)

[0731] User

[0732] Hardware required: A standard PC or tablet device

[0733] Software used: Web browser, dashboard display software

[0734] System Operation

[0735] Server Operation

[0736] The server periodically collects sales information from the POS system and online store. Specifically, it executes an SQL query to retrieve sales information in CSV format every night at midnight. The server also retrieves the latest inventory information from the inventory management system every hour. Furthermore, the server retrieves seasonal data and market trend information through an external API.

[0737] The server cleanses the collected data and removes invalid data and missing values. This process uses a data processing library (e.g., pandas). Next, it uses the cleansed data to train a demand forecasting model using an AI algorithm. For training, it uses AI libraries such as TensorFlow and PyTorch.

[0738] A trained AI model is used to predict future demand. The prediction results are displayed in real time on a dashboard for users to review. The server also monitors inventory levels in real time, automatically generating replenishment instructions and placing orders when they fall below a set threshold. The user is notified when replenishment is complete.

[0739] The server also analyzes inventory turnover and proposes efficient rotation by generating a report recommending the prioritization of older inventory.The server also monitors all inventory status in real time, classifying and notifying products that are selling poorly or well.

[0740] Device behavior

[0741] The terminal periodically sends sales information from the POS system and online store to the server. It also works with the inventory management system to send collected inventory information to the server, allowing the server to always obtain the latest information.

[0742] User operations

[0743] Users can use the dashboard provided by the server to check inventory status and demand forecast results in real time. For items that are not selling well, they can take measures such as promotions and discounts. They can also receive notifications from the server to check order status and replenishment and take appropriate action.

[0744] Specific examples

[0745] Server processing example

[0746] The server runs the SQL query "select from sales where date = current_date()" every night to collect sales information from the POS system, updates the latest inventory information every hour, and runs Python scripts to cleanse the data frame with the pandas library and train the AI ​​model with TensorFlow.

[0747] Terminal processing example

[0748] The terminal uploads sales information to the server at regular intervals, and also shares the latest inventory information with the server.

[0749] User operation example

[0750] Users can view the dashboard to see the results of the next week's demand forecast, get notified about slow-selling items, and implement promotions.

[0751] Prompt Sentence Examples

[0752] "Please introduce this system. Please explain in detail the processing steps of the program that uses AI to analyze sales and inventory information and automate inventory management."

[0753] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0754] Step 1:

[0755] The server periodically collects sales information. Specifically, it retrieves the day's sales information in CSV format from the POS system every night at midnight. The input is the POS system's sales information database, and the output is the collected CSV file. The server executes an SQL query to extract data using the command "select from sales where date = current_date()". The retrieved data is saved in a specified directory.

[0756] Step 2:

[0757] The server collects inventory information. Specifically, it retrieves the latest inventory data from the inventory management system every hour. The input is the inventory information database of the inventory management system, and the output is the collected inventory data. The server calls the API via an HTTP request to retrieve the inventory data.

[0758] Step 3:

[0759] The server obtains seasonal data and market trend information. Specifically, it uses an external API to obtain weekly forecasts and market trend information. The input is the season information and market data API, and the output is the obtained seasonal data and market trend information. The server sends a request to the REST API endpoint and receives data in JSON format.

[0760] Step 4:

[0761] The server cleanses the collected data, removing invalid data and missing values. The input is the collected sales information, inventory information, seasonal data, and market trend information, and the output is a cleansed dataset. The server uses Python scripts and the pandas library to arrange the data using methods such as "df.dropna()" and "df[df['sales'] > 0]".

[0762] Step 5:

[0763] The server trains an AI demand forecasting model. Specifically, it uses the cleansed data and an AI algorithm (e.g., TensorFlow or PyTorch) to train the demand forecasting model. The input is the cleansed dataset, and the output is the trained point model. The server runs code such as "model.fit(data, epochs=100)" to train the model.

[0764] Step 6:

[0765] The server uses a trained AI model to forecast demand. Specifically, it predicts future sales figures and displays the results on a dashboard. The input is the trained model and the latest data, and the output is the prediction results. The server uses the method "predictions = model.predict(new_data)" to reflect the results on the dashboard.

[0766] Step 7:

[0767] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold (e.g., 50 units). The input is a real-time inventory database, and the output is replenishment orders. The server executes logic such as "if inventory < threshold: generate_replenishment_order()".

[0768] Step 8:

[0769] The server sends the order instruction to the supplier. The input is the automatically generated replenishment instruction, and the output is the order request sent to the supplier. Specifically, the order instruction is sent to the supplier via an API request.

[0770] Step 9:

[0771] The user checks for replenishment. Specifically, they receive a notification from the server and check the order status on the dashboard. The input is the notification from the server, and the output is the user's confirmation and response. The user checks the order status and replenishment status on the dashboard and takes the necessary action.

[0772] Step 10:

[0773] The server analyzes inventory turnover and proposes efficient rotation. The input is real-time inventory data, and the output is the turnover analysis results and a proposal report. The server uses a data analysis algorithm to calculate efficient inventory rotation and proposes it to the user.

[0774] Step 11:

[0775] The server grasps sales status in real time, classifies products into those that are selling poorly and those that are selling well, and notifies them. The input is real-time sales data, and the output is the classification results and notifications. The server periodically analyzes the data and notifies the dashboard and users.

[0776] (Application example 1)

[0777] 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."

[0778] In today's brick-and-mortar stores, improving the efficiency and accuracy of inventory management is a key issue. In particular, there is a need to grasp sales and inventory data in real time, forecast demand, and replenish inventory at the appropriate time. It is also necessary to take prompt action to address poorly selling items and propose efficient product display solutions. However, these tasks require a lot of time and effort, and are prone to human error. Furthermore, there is a need for a system that allows store managers and staff to instantly grasp the situation on-site.

[0779] 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.

[0780] In this invention, the server includes: means for periodically collecting sales data; means for collecting inventory data; means for acquiring seasonal information and market trend data; means for forecasting demand using an AI algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; means for checking inventory status in real time using a smart device (smartphone or smart glasses); means for proposing promotions for slow-selling items; and means for proposing replenishment times based on future demand forecasts. This enables the efficiency and accuracy of inventory management in physical stores to be improved.

[0781] "Sales data" refers to data relating to the quantity and amount of purchased goods generated through sales activities at physical stores.

[0782] "Inventory data" refers to data regarding the quantity and types of products currently stored in a physical store.

[0783] "Seasonal information" is information relating to sales trends and demand that fluctuate during specific seasons or periods.

[0784] "Market trend data" is the latest information on overall market trends and consumer purchasing habits.

[0785] An "AI algorithm" is a computational method using artificial intelligence to analyze massive amounts of data, find patterns, and derive next actions or predictions.

[0786] "Demand forecasting" is the process of predicting future sales volumes and demand based on past sales data and market trends.

[0787] "Inventory level" refers to the status of the number of specific items in stock in a store or warehouse.

[0788] A "replenishment instruction" is an instruction to add stock when the stock falls below a certain threshold.

[0789] "Placing an order" is the act of ordering goods from a supplier.

[0790] "Turnover rate" is an indicator that indicates the sales rate of inventory items over a certain period of time.

[0791] "Rotation" is the process of changing the placement and order of inventory items to ensure proper management.

[0792] A "best-selling product" is a product that is currently very popular and is being purchased by many consumers.

[0793] A "slow-selling product" is a product that is not being purchased much by consumers at the moment.

[0794] "Notification" is the act of promptly notifying a user of specific information.

[0795] A "smart device" is a portable electronic device (e.g., a smartphone or smart glasses) that can connect to the Internet and send and receive information.

[0796] "Promotion" refers to advertising and campaign activities to promote sales of slow-selling products.

[0797] The invention is a system that improves the efficiency and accuracy of inventory management in physical stores. This system uses AI to analyze sales data and inventory data and automates inventory management. An embodiment of this system is described below.

[0798] System configuration

[0799] The system consists of three main parts: the server, the terminal, and the user. The specific operation procedure is as follows:

[0800] Data collection

[0801] server

[0802] The server periodically collects sales data from POS systems and online stores, obtains current inventory data from inventory management systems, and uses external APIs to obtain seasonal information and market trend data.

[0803] Terminal

[0804] The terminal is responsible for sending data from the POS system or online store to the server. The terminal is used to link inventory data to the server.

[0805] Data analysis and demand forecasting

[0806] server

[0807] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[0808] Based on the cleansed data, an AI algorithm is used to train a demand forecasting model to predict future demand.

[0809] The prediction results are reflected in the dashboard and can be viewed by users.

[0810] Stock level monitoring and automatic replenishment

[0811] server

[0812] The server monitors inventory levels in real time and automatically generates replenishment instructions and sends order instructions to suppliers when inventory levels fall below a set threshold.

[0813] When the replenishment is completed, the user is notified.

[0814] User

[0815] Users can check the order progress and replenishment status on the terminal.

[0816] Inventory Optimization

[0817] server

[0818] The server analyzes inventory turnover and suggests efficient rotation.

[0819] The system suggests to the user to prioritize displaying older stock.

[0820] User

[0821] The user updates the product display based on the server's suggestions.

[0822] Real-time tracking and promotions

[0823] server

[0824] The server monitors all inventory status in real time and updates the dashboard with the latest information.

[0825] Categorize best-selling and worst-selling items and notify users.

[0826] User

[0827] Take measures such as promotions and discounts on slow-selling products.

[0828] Example of a system

[0829] This system is realized using specific hardware and software. The hardware used is a server equipped with a high-performance database and an AI computing unit, and smartphones or smart glasses are suitable terminals. The software used is Python Flask or Django for the server, and React Native (smartphones) or ARKit (smart glasses) for the client. TensorFlow and Keras are used for data analysis.

[0830] Specific example explanation

[0831] For example, the server collects the day's sales data from the POS system overnight and updates the current stock status from the inventory management system. Using a smartphone or smart glasses, store staff can check the stock status in real time. Furthermore, an AI model is used to predict demand for the next week based on past sales data, and the results suggest the appropriate time for replenishment.

[0832] Example prompt sentence:

[0833] "Please refer to the sales data for the past three years as of mid-October and forecast demand for next week."

[0834] By inputting these prompts, the AI ​​model performs detailed data analysis and provides specific demand forecasts, thereby improving the efficiency and accuracy of inventory management in physical stores.

[0835] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0836] Step 1:

[0837] The server collects sales data

[0838] Input: Sales data from POS systems and online stores

[0839] Specific operation: The server periodically connects to the POS system or online store to collect sales data, for example, by retrieving data through an API in the middle of the night.

[0840] Output: Collected sales data is stored on the server

[0841] Step 2:

[0842] The server collects inventory data

[0843] Input: Inventory data from inventory management system

[0844] Specific operation: The server connects to the inventory management system to obtain current inventory data, retrieves the data via API, and stores it on the server.

[0845] Output: The latest inventory data is stored on the server.

[0846] Step 3:

[0847] Server retrieves seasonal information and market trend data

[0848] Input: Seasonality and market trend data from external APIs

[0849] What it does: The server sends requests to external APIs to retrieve seasonality and market trend data. This can involve web scraping or API calls.

[0850] Output: The acquired seasonal information and market trend data is stored on the server.

[0851] Step 4:

[0852] The server cleanses the data

[0853] Inputs: Collected sales data, inventory data, seasonality information, market trend data

[0854] Specific operation: The server cleanses the collected data and removes invalid data and missing values. For example, it filters out data with negative values ​​and missing values.

[0855] Output: The cleansed data is passed to the AI ​​algorithm

[0856] Step 5:

[0857] The server uses an AI algorithm to predict demand.

[0858] Input: Cleansed data

[0859] How it works: The server uses the cleansed data to train an AI model to predict future demand, for example, using past sales data to predict sales for the next week.

[0860] Output: Forecasted supply and demand data is generated

[0861] Step 6:

[0862] The server monitors inventory levels in real time.

[0863] Input: Latest inventory data

[0864] What it does: The server monitors inventory levels in real time and immediately issues an alert if they fall below a set threshold.

[0865] Output: Status information on whether stock levels are normal or not

[0866] Step 7:

[0867] The server automatically generates replenishment instructions and places orders.

[0868] Input: Stock level status information

[0869] Specific operation: When the inventory level falls below a threshold, the server automatically generates replenishment instructions and sends order instructions to the supplier.

[0870] Output: Purchase order sent to supplier

[0871] Step 8:

[0872] The server analyzes inventory turnover and suggests efficient rotation.

[0873] Input: Past sales data and inventory data

[0874] Specific operation: The server calculates the inventory turnover rate and suggests an efficient display method, for example, suggesting that old inventory should be displayed at the front and new inventory at the back.

[0875] Output: The user is notified of the rotation suggestion

[0876] Step 9:

[0877] The server proposes a promotion for a slow-selling item

[0878] Input: Real-time sales data

[0879] What it does: The server detects slow-selling products and offers promotions or discounts for them, for example, offering limited-time sales on specific products.

[0880] Output: The user is notified of the promotion offer.

[0881] Step 10:

[0882] Users can check inventory status in real time using their smart devices.

[0883] Input: Stock status data provided by the server

[0884] Specific operation: The user checks the inventory status in real time through the application via a smartphone or smart glasses, for example, by viewing the inventory status on the in-app dashboard.

[0885] Output: Action guidelines based on the inventory status identified by the user

[0886] 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.

[0887] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. In addition, by combining this with an emotion engine that recognizes user emotions, it realizes more user-friendly inventory management.

[0888] System configuration

[0889] Data collection

[0890] 1. Server

[0891] The server periodically collects sales data from POS systems and online stores, and stores the collected data in a database on the server.

[0892] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[0893] The server uses external APIs to obtain seasonal information and market trend data.

[0894] 2. Terminal

[0895] The terminal sends sales data from the POS system or online store to the server. The data is sent to the server in real time as each transaction occurs.

[0896] The terminal connects to the inventory management system and sends inventory data to the server.

[0897] Data analysis and demand forecasting

[0898] 1. Server

[0899] The server cleanses the collected data, removing any invalid data or missing values.

[0900] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[0901] Use the trained model to predict future demand and display the forecast results in a dashboard.

[0902] Stock level monitoring and automatic replenishment

[0903] 1. Server

[0904] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold.

[0905] The server automatically sends the order instructions to the supplier.

[0906] The server notifies the user that the replenishment has occurred.

[0907] 2. Users

[0908] Users can check the order progress and replenishment status on the terminal.

[0909] Inventory Optimization

[0910] 1. Server

[0911] The server analyzes inventory turnover and suggests efficient rotation.

[0912] The server suggests to the user that older stock be given priority in displaying the items.

[0913] 2. Users

[0914] The user updates the product display based on the server's suggestions.

[0915] Real-time tracking

[0916] 1. Server

[0917] The server monitors inventory status in real time and displays the latest information on the dashboard.

[0918] The server classifies popular and unpopular items and notifies the user.

[0919] 2. Users

[0920] Users take measures such as promotions and discounts to combat slow-selling products.

[0921] Emotion engine integration

[0922] 1. Emotion Engine

[0923] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine collects emotional data through facial recognition and voice analysis.

[0924] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[0925] The server adjusts inventory management methods based on the user's emotional state and optimizes notifications and suggestions to reduce stress for the user.

[0926] 2. Users

[0927] Users receive notifications and suggestions based on emotion recognition from the server and provide feedback on inventory management as needed.

[0928] Specific examples

[0929] Data collection

[0930] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[0931] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[0932] Data analysis and demand forecasting

[0933] The server trains the AI ​​model based on past sales data to predict demand for the next week, and the forecast results are displayed on a dashboard for users to view.

[0934] Stock level monitoring and automatic replenishment

[0935] When beverage inventory falls below a specified threshold, the server automatically sends an order to the supplier, and the user can check the replenishment status and approve it via their terminal.

[0936] Inventory Optimization

[0937] The server analyzes the inventory turnover rate and suggests to the user to prioritize the display of older inventory. The user updates the product display based on the suggestions.

[0938] Real-time tracking

[0939] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[0940] Emotion engine integration

[0941] The server recognizes the user's emotions and adjusts the frequency of notifications or displays positive messages if the user is feeling stressed.

[0942] Users take appropriate inventory management actions based on feedback from the emotion engine to maintain efficient operations.

[0943] In this way, the system of the present invention links the server, terminals, and users, and further integrates the emotion engine, thereby improving the efficiency and accuracy of inventory management and reducing the burden on users.

[0944] The processing flow will be explained below.

[0945] Step 1:

[0946] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[0947] Step 2:

[0948] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[0949] Step 3:

[0950] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[0951] Step 4:

[0952] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[0953] Step 5:

[0954] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[0955] Step 6:

[0956] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[0957] Step 7:

[0958] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[0959] Step 8:

[0960] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[0961] Step 9:

[0962] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[0963] Step 10:

[0964] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[0965] Step 11:

[0966] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[0967] Step 12:

[0968] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[0969] Step 13:

[0970] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[0971] Step 14:

[0972] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[0973] Step 15:

[0974] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[0975] Step 16:

[0976] The server collects emotional data using an emotion engine that recognizes the user's emotions. Specifically, it obtains the user's emotional state in real time through facial recognition and voice analysis.

[0977] Step 17:

[0978] The server analyzes the collected emotional data in real time to understand the user's current emotional state, for example, detecting if the user is feeling stressed.

[0979] Step 18:

[0980] The server adjusts inventory management methods based on the user's emotional state, for example, reducing the frequency of notifications and displaying positive messages if the user is feeling stressed.

[0981] Step 19:

[0982] The user receives notifications and suggestions based on emotion recognition from the server, and provides feedback on inventory management as needed. By accepting responses based on emotions, the user can manage inventory while reducing stress.

[0983] In this way, the system of the present invention allows the server, terminals, and users to work together, and by integrating an emotion engine, it is possible to improve the efficiency and accuracy of inventory management while also reducing the burden on users.

[0984] Example 2

[0985] 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."

[0986] In modern inventory management systems, it is important to effectively manage sales and inventory information in real time and to perform highly accurate demand forecasts. However, in conventional systems, data collection and analysis are often performed manually, resulting in problems with efficiency and accuracy. In addition, inventory management and notifications do not take user emotions into account, which tends to place a heavy burden on users. To solve these issues, a more automated and highly accurate inventory management system is needed.

[0987] 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.

[0988] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal information and market trend information; means for forecasting demand using an AI algorithm based on the collected information; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; and means for recognizing a user's emotional state using an emotion engine and optimizing notifications and suggestions. This automates a series of processes, from collecting sales and inventory information to demand forecasting and optimal notifications and suggestions based on the user's emotions, enabling more efficient and accurate inventory management.

[0989] "Sales information" is data relating to the sales results of products and services, and includes details such as the date and time of the transaction, product name, quantity, and price.

[0990] "Inventory information" is data that indicates the current inventory status, such as the quantity of products stored in warehouses or stores, inventory history, and location information.

[0991] "Seasonal information" is data on consumption trends and sales trends related to specific seasons or events.

[0992] "Market trend information" is data on economic trends, such as the current market supply and demand balance and changes in consumer preferences.

[0993] An "AI algorithm" is a mathematical model or method for analyzing and predicting data using artificial intelligence technology.

[0994] "Demand forecasting" is the process of predicting future sales volumes based on past sales data and external factors.

[0995] "Stock level" is information that indicates how much of a particular product is currently in stock.

[0996] A "replenishment instruction" is an instruction to replenish new products when inventory is low.

[0997] "Placing an order" is the process of ordering goods from a supplier or source.

[0998] "Inventory turnover" is an indicator that shows how much merchandise is being brought in and out of stock over a certain period of time.

[0999] "Rotation" is a method of efficiently managing inventory by replacing it chronologically.

[1000] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[1001] "Notification" refers to notifications or notices sent from the system to the user.

[1002] A "suggestion" is a recommendation of an action or improvement method for the system to take to the user.

[1003] This invention is a system that collects sales information and inventory information, forecasts demand based on the information, and automates inventory management. Furthermore, by combining it with an emotion engine that recognizes user emotions, it has the advantage of reducing the burden on users.

[1004] System configuration

[1005] Data collection

[1006] server

[1007] The server periodically collects sales information from POS systems and online stores, makes API calls using a scripting language such as Python, retrieves the data, and stores it in a database.

[1008] The server collects inventory information in real time from the inventory management system, retrieves the data using HTTP requests, and stores it in a database.

[1009] The server also periodically retrieves seasonal and market trend information using external APIs, including, for example, weather forecast APIs and market trend APIs.

[1010] Terminal

[1011] The terminal transmits sales information to the server in real time each time a transaction occurs in a POS system or online store.

[1012] The terminals work in conjunction with an inventory management system and send inventory information to the server, which ensures that the latest inventory status is always reflected.

[1013] Data analysis and demand forecasting

[1014] server

[1015] The server cleanses the collected data, using the Python Pandas library to remove invalid data and missing values.

[1016] The server uses AI algorithms to train demand forecasting models based on the cleansed data, using machine learning libraries such as TensorFlow and Scikit-learn.

[1017] The trained model is used to predict future demand and the results are displayed in a dashboard, which users can view through a browser-based dashboard.

[1018] Stock level monitoring and automatic replenishment

[1019] server

[1020] The server monitors inventory levels in real time and automatically generates replenishment orders if they fall below a set threshold.

[1021] The server then places orders with suppliers based on the generated replenishment instructions. Orders are placed via email or a dedicated API.

[1022] The server notifies the user that the refill is complete.

[1023] User

[1024] Users can check the progress of their orders and check replenishment status through a dedicated interface, and are notified immediately when replenishment is complete.

[1025] Inventory Optimization

[1026] server

[1027] The server analyzes inventory turnover and suggests efficient rotation, for example, suggesting to the user to prioritize displaying older inventory.

[1028] Computer programs find ways to avoid inventory delays and backlogs and rotate products efficiently.

[1029] User

[1030] The user updates the product display based on the server's suggestions.

[1031] Real-time tracking

[1032] server

[1033] The server monitors all inventory status in real time, and the latest information is reflected on the dashboard.

[1034] The server classifies popular and unpopular items and notifies the user.

[1035] User

[1036] Users take measures such as promotions and discounts to combat slow-selling products.

[1037] Emotion engine integration

[1038] Emotion Engine

[1039] The server is equipped with an emotion engine that recognizes the user's emotions and collects emotional information through facial recognition and voice analysis.

[1040] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[1041] The server adjusts the content and frequency of notifications and suggestions based on the user's emotional state. By providing positive messages and timely notifications, the server reduces the user's stress.

[1042] User

[1043] Users receive and utilize the feedback and suggestions provided by the emotion engine to improve the efficiency of their inventory management.

[1044] Specific examples

[1045] A specific example of this is a process in which the server collects the day's sales information from the POS system in the middle of the night and obtains the latest stock status from the inventory management system.The server also trains an AI model based on past sales information to predict demand for the next week, and displays the results on a dashboard so that users can check them.

[1046] Prompt Sentence Examples

[1047] "Please provide an outline of your system for efficiently managing sales and inventory data. Also, explain how you use AI to analyze the collected data and how you build a user-friendly interface using an emotion engine."

[1048] In this way, the system of the present invention aims to improve the efficiency and accuracy of inventory management by linking the server, terminals, and users and further integrating the emotion engine.

[1049] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1050] Step 1:

[1051] Collection of sales information

[1052] The server periodically collects sales information from POS systems and online stores. For example, it uses a Python script to retrieve sales data from an API endpoint. It receives sales data from the API endpoint (transaction date and time, product name, quantity, price, etc.) as input and stores the sales data in a database as output.

[1053] Step 2:

[1054] Collecting inventory information

[1055] The server collects inventory information from the inventory management system in real time. It retrieves the inventory information using HTTP requests and stores it in a database. It receives current inventory information (product ID, quantity, location, etc.) from the inventory management system as input, and updates the database with the latest inventory status as output.

[1056] Step 3:

[1057] Obtaining seasonal and market trend information

[1058] The server uses external APIs to obtain seasonal and market trend information. Specifically, it obtains information from specified API endpoints. It receives seasonal and market trend data (weather information, consumption trends, etc.) as input and stores this data in a database as output.

[1059] Step 4:

[1060] Data Cleansing

[1061] The server cleanses the collected sales, inventory, seasonality, and market trend information. It uses the Python Pandas library to cleanse the data and remove incorrect data and missing values. It takes all the collected data as input and produces a cleansed dataset as output.

[1062] Step 5:

[1063] Training a demand forecasting model

[1064] The server uses AI algorithms to train a demand forecasting model based on the cleansed data. It uses machine learning libraries such as TensorFlow and Scikit-learn. It receives the cleansed dataset as input, selects features from the data, and trains the model. It generates a trained demand forecasting model as output.

[1065] Step 6:

[1066] Demand forecasting

[1067] The server uses the trained model to predict future demand. It provides new sales information and external information as inputs to the model and outputs future demand. The output results are reflected in a dashboard and provided to users in a visualized form.

[1068] Step 7:

[1069] Monitoring inventory levels

[1070] The server monitors inventory levels in real time and generates alerts if they fall below a set threshold. It receives real-time inventory information as input, checks inventory levels, and generates alerts as output, indicating that the conditions for a replenishment order have been met.

[1071] Step 8:

[1072] Generate replenishment orders

[1073] The server automatically generates replenishment orders when inventory levels fall below a set threshold. It receives inventory level alerts as input and creates replenishment orders. It sends the generated replenishment orders to suppliers as output.

[1074] Step 9:

[1075] Ordering from suppliers

[1076] The server places an order with the supplier based on the replenishment instructions. It sends order information via email or a dedicated API. It receives replenishment instructions as input and sends an order to the supplier. It outputs confirmation that the order information has been sent.

[1077] Step 10:

[1078] Inventory Turnover Analysis

[1079] The server analyzes inventory turnover. It combines sales data and inventory data for analysis and proposes efficient rotation. It receives past sales information and inventory information as input and calculates the turnover rate. It generates the inventory turnover analysis results as output and presents them to the user as a proposal.

[1080] Step 11:

[1081] Proposal for efficient rotation

[1082] The server suggests to the user to prioritize stocking older stock based on the results of inventory turnover analysis. It receives the results of the turnover analysis as input, generates a suggestion for efficient rotation, and notifies the user of the suggestion as output.

[1083] Step 12:

[1084] Real-time inventory monitoring

[1085] The server monitors the inventory status in real time and reflects the latest information on the dashboard. It receives real-time inventory data as input, updates the dashboard, and visualizes the latest information as output and provides it to the user.

[1086] Step 13:

[1087] Best-selling product categories

[1088] The server analyzes the sales data and classifies popular and unpopular products. It uses the sales data as input and applies machine learning algorithms to perform the classification. It then returns the classification results to the user as output.

[1089] Step 14:

[1090] Unpopular product notifications

[1091] The server notifies the user about unpopular products. It uses the product classification results as input and generates a notification. It notifies the user about unpopular products as output.

[1092] Step 15:

[1093] Collecting Emotional Data

[1094] The server collects emotion data using an emotion engine to recognize user emotions. It performs face recognition and voice analysis via a camera and microphone. It receives real-time face and voice data as input and generates emotion data. It generates emotion data for analysis as output.

[1095] Step 16:

[1096] Emotional state analysis

[1097] The server analyzes the collected emotional data in real time to understand the user's current emotional state. It uses the emotional data as input and applies an algorithm to analyze it, generating data that determines the user's emotional state as output.

[1098] Step 17:

[1099] Notification optimization

[1100] The server optimizes the content and frequency of notifications based on the user's emotional state. If the user is feeling stressed, it reduces the frequency of notifications and displays positive messages. It uses the emotional state data as input and modifies the notification strategy. It outputs the optimized notifications to the user.

[1101] (Application example 2)

[1102] 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."

[1103] Conventional inventory management systems had the ability to collect sales and inventory data to forecast demand and automatically generate replenishment instructions, but they were unable to adjust inventory management methods taking user emotions into account. Furthermore, they lacked a means for store staff to check inventory status in real time and respond based on customer emotions. As a result, they were unable to fully improve inventory management efficiency or user satisfaction.

[1104] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting sales data, means for collecting inventory data, means for acquiring seasonal information and market trend data, means for performing demand forecasting using an AI algorithm based on the collected data, means for monitoring inventory levels in real time, means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold, means for analyzing inventory turnover and proposing efficient rotation, means for classifying and notifying slow-selling and fast-selling items in real time, means for integrating an emotion processing engine that recognizes user emotions and collecting emotion data through facial recognition and voice analysis, means for adjusting an inventory management method according to the user's emotional state based on the collected emotion data, and means for displaying inventory status in real time using smart glasses and proposing responses based on customer emotions. This enables improved efficiency and accuracy of inventory management, reduced user burden, and improved customer satisfaction.

[1105] Key Word Definitions

[1106] "Sales data" refers to information relating to the sale of a product, and includes data such as the transaction date and time, product name, sales quantity, and price.

[1107] "Inventory data" is information indicating the quantity and location of currently held products, the condition of each product, and the inventory history.

[1108] "Seasonal information" is data about sales patterns and consumer behavior that are affected by seasonal fluctuations.

[1109] "Market trend data" refers to information about current market consumer demand, trends, competitor trends, and so on.

[1110] "AI algorithm" is a general term for computational methods and mathematical models used to analyze and predict data using artificial intelligence.

[1111] "Demand forecasting" is the process of analyzing past sales data and market trend data to predict future demand for products.

[1112] "Stock level" is a value that indicates the number of a particular product in stock at a given point in time.

[1113] A "threshold" is a set value that is a criterion for the occurrence of a specific condition or event.

[1114] A "replenishment order" is an order to a supplier or warehouse to supply goods when inventory is low.

[1115] "Turnover rate" is an indicator that shows the frequency of goods being received and shipped, and is a criterion for evaluating inventory efficiency.

[1116] "Rotation" is a method for efficiently managing inventory placement and shipping order.

[1117] The "emotion processing engine" is a system that analyzes the user's facial expressions and voice and recognizes their emotions.

[1118] "Facial recognition" is a technology that uses a camera to detect a person's face and obtain its identification information.

[1119] "Voice analysis" is a technology that analyzes voice data to detect its content and the speaker's emotions.

[1120] "Emotion data" is information that expresses the user's emotional state in numerical values ​​or categories.

[1121] "Smart glasses" are eyeglass-type devices with display capabilities that allow users to view information in real time.

[1122] "Real-time inventory display" means that the current inventory information is displayed on the smart glasses at that moment.

[1123] "Customer emotion-based response" is the process of providing optimal service and product recommendations based on the customer's recognized emotional state.

[1124] MODE FOR CARRYING OUT THE INVENTION

[1125] To implement this invention, the system is mainly composed of a server, a terminal, and a user. The functions of each component and specific implementation methods thereof will be described below.

[1126] Server Functions and Implementation Methods

[1127] 1. Collect sales and inventory data:

[1128] The server periodically collects sales data from the POS system and online store and stores it in a database. It also retrieves current inventory data from the inventory management system. This allows for accurate inventory status in real time. The collected data is processed using Python libraries (e.g., Pandas and SQLAlchemy).

[1129] 2. Obtaining seasonality and market trend data:

[1130] The server obtains seasonal data and market trend information through external APIs, such as weather information APIs and market data APIs, and uses this data to forecast future demand.

[1131] 3. Demand forecasting using AI algorithms:

[1132] Train demand forecasting models based on collected sales, inventory, seasonality, and market trend data. Use Python machine learning libraries (e.g., TensorFlow and scikit-learn) to build and operate forecasting models based on historical data.

[1133] 4. Inventory level monitoring and automatic replenishment instructions:

[1134] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold, which are then sent to suppliers and notify the user upon completion.

[1135] 5. Emotion processing engine integration:

[1136] The server integrates an emotion processing engine that uses facial recognition and voice analysis to recognize user emotions. This includes facial recognition and voice analysis technologies using OpenCV and TensorFlow. The collected emotion data is analyzed in real time and used to adjust the inventory management system.

[1137] 6. Information display using smart glasses:

[1138] The smart glasses allow store staff to check stock availability in real time, and the same display also shows how to respond based on the customer's emotional state, using data transfer via Bluetooth and Wi-Fi.

[1139] Terminal functions and implementation methods

[1140] 1. Data transmission:

[1141] The terminal sends sales and inventory data in CSV format to the server, which transmits this data in real time as each transaction occurs.

[1142] 2. User Interface:

[1143] It provides an interface for users to check inventory information and replenishment status. Web applications and native applications are provided using smart devices (e.g., smartphones and tablets).

[1144] User roles and examples

[1145] 1. Real-time inventory check and action:

[1146] Users wear smart glasses and can check inventory information and demand forecast data in real time. For example, if a beverage runs low on stock, a notification will appear on the glasses and an order to replenish the supply will be automatically sent to the supplier.

[1147] 2. Emotional customer service:

[1148] If the customer is smiling, the prompt will say "Let us know if we can help you," and if the customer is unhappy, the prompt will say "Is there a problem?". Examples of such prompts include:

[1149] If the customer is smiling, it says "Let us know if we can help you."

[1150] If the customer seems unhappy, it asks, "Is there a problem?"

[1151] When stock is low, you will receive a notification saying, "Stock is low. Please prepare to replenish."

[1152] There is.

[1153] This system will improve the efficiency and accuracy of inventory management, reduce the burden on users, and increase customer satisfaction.

[1154] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1155] Program processing flow

[1156] Step 1:

[1157] The server periodically collects sales data from POS systems and online stores and stores it in a database. Specifically, sales data is sent from the terminal to the server in real time when each transaction occurs. The input data is sales information (product ID, number of units sold, price, date and time), and libraries such as Pandas and SQLAlchemy are used to store this in the database. The latest sales data is saved in the database as output.

[1158] Step 2:

[1159] The server collects current inventory data from the inventory management system and grasps the latest inventory status. The input data is inventory information (product ID, inventory quantity, warehouse location), which is also saved in the database in real time. The output is the latest inventory data saved in the database.

[1160] Step 3:

[1161] The server uses external APIs to obtain seasonal information and market trend data. Examples of data obtained from APIs include weather information and past sales trends. After obtaining this data, it is used as a training dataset for the AI ​​model. Seasonal information and market trend data are collected as input, and these data are stored in a database as output.

[1162] Step 4:

[1163] The server uses an AI algorithm to make demand forecasts based on the collected sales data, inventory data, seasonal information, and market trend data. Specifically, it uses TensorFlow and scikit-learn to build and train a predictive model based on past data. Past sales data, inventory data, seasonal information, and market trend data are required as input, and future demand forecast results are obtained as output.

[1164] Step 5:

[1165] The server monitors inventory levels in real time based on the results of demand forecasts and automatically generates replenishment instructions when they fall below a set threshold. Specifically, it checks inventory data using Python processing, and if it falls below the threshold, it takes action to send replenishment instructions to suppliers by email or API. Real-time inventory data and a threshold are required as input, and the replenishment instructions are sent to suppliers as output.

[1166] Step 6:

[1167] A user wearing smart glasses can check inventory information in real time. This information is sent from the server to the smart glasses via Bluetooth or WiFi, and the current inventory status is displayed. The input is inventory information from the server, and the output is the inventory status displayed on the smart glasses display.

[1168] Step 7:

[1169] The server runs an emotion processing engine that performs facial recognition and voice analysis to recognize the user's emotions. It uses OpenCV and TensorFlow to perform facial recognition and voice analysis and collect emotion data. Raw data from the camera and microphone is required as input, and the output is the user's emotional state expressed as a number or category.

[1170] Step 8:

[1171] The user receives a prompt based on the emotional data displayed through the smart glasses. For example, if the customer is smiling, the smart glasses will display a prompt such as "Let us know if we can help you," and if the customer is in a bad mood, the smart glasses will display a prompt such as "Is there a problem?". An appropriate message is generated based on the emotional data as input, and the message is displayed on the smart glasses as output.

[1172] This series of processes makes inventory management more efficient, improves accuracy, reduces the burden on users, and improves customer satisfaction.

[1173] 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.

[1174] 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.

[1175] 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.

[1176] [Third embodiment]

[1177] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1178] 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.

[1179] 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).

[1180] 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.

[1181] 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.

[1182] 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).

[1183] 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.

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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.

[1188] 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."

[1189] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. Specifically, it operates in cooperation with a server, terminals, and users.

[1190] System configuration

[1191] Data collection

[1192] 1. Server

[1193] The server periodically collects sales data from POS systems and online stores.

[1194] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[1195] The server uses external APIs to obtain seasonal information and market trend data.

[1196] 2. Terminal

[1197] The terminal is responsible for transmitting data from the POS system and online store to the server.

[1198] The terminal works in conjunction with an inventory management system and sends inventory data to a server.

[1199] Data analysis and demand forecasting

[1200] 1. Server

[1201] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[1202] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[1203] The server uses the trained model to predict future demand.

[1204] The server displays the prediction results on a dashboard so that users can view them.

[1205] Stock level monitoring and automatic replenishment

[1206] 1. Server

[1207] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below set thresholds.

[1208] The server automatically sends the order instructions to the supplier.

[1209] The server notifies the user that the replenishment has occurred.

[1210] 2. Users

[1211] The user can check the progress of the order and replenishment on the terminal.

[1212] Inventory Optimization

[1213] 1. Server

[1214] The server analyzes inventory turnover and suggests efficient rotation.

[1215] The server suggests to the user that older stock be given priority in displaying the items.

[1216] 2. Users

[1217] The user updates the product display based on the server's suggestions.

[1218] Real-time tracking

[1219] 1. Server

[1220] The server monitors all inventory status in real time and reflects the latest information on the dashboard.

[1221] The server classifies popular and unpopular items and notifies the user.

[1222] 2. Users

[1223] Users take measures such as promotions and discounts to combat slow-selling products.

[1224] Specific examples

[1225] Data collection

[1226] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[1227] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[1228] Data analysis and demand forecasting

[1229] The server trains the AI ​​model based on sales data from the past October to predict demand for the next week. The forecast results are displayed on a dashboard for users to check.

[1230] Stock level monitoring and automatic replenishment

[1231] When the beverage inventory falls below 50 units, the server automatically sends an order to the supplier. The user can check the replenishment status and approve it via their terminal.

[1232] Inventory Optimization

[1233] The server analyzes the inventory turnover rate and suggests to the user that they should prioritize the display of beverages that arrived in August. The user updates their product display accordingly.

[1234] Real-time tracking

[1235] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[1236] In this way, the system of the present invention operates in cooperation with the server, terminals, and users to improve the efficiency and accuracy of inventory management.

[1237] The processing flow will be explained below.

[1238] Step 1:

[1239] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[1240] Step 2:

[1241] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[1242] Step 3:

[1243] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[1244] Step 4:

[1245] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[1246] Step 5:

[1247] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[1248] Step 6:

[1249] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[1250] Step 7:

[1251] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[1252] Step 8:

[1253] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[1254] Step 9:

[1255] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[1256] Step 10:

[1257] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[1258] Step 11:

[1259] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[1260] Step 12:

[1261] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[1262] Step 13:

[1263] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[1264] Step 14:

[1265] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[1266] Step 15:

[1267] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[1268] Example 1

[1269] 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."

[1270] In conventional inventory management systems, sales and inventory information was often collected manually, making it difficult to ensure accurate data and timely inventory replenishment. Furthermore, demand forecasting and efficient inventory rotation were not performed, increasing the risk of excess inventory and shortages. Furthermore, measures to address poorly selling products were delayed, making it difficult to grasp information on best-selling products in real time.

[1271] 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.

[1272] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal data and market trend information; means for forecasting demand using an artificial intelligence algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying products with poor sales and products with good sales in real time; means including an interface for users to check order status and replenishment; and terminal means for linking with the inventory management system and transmitting collected inventory information to the server. This enables efficient and accurate inventory management, timely inventory replenishment based on demand forecasts, and understanding of sales status in real time.

[1273] "Sales information" refers to data such as the quantity, price, and transaction time of the goods sold.

[1274] "Inventory information" refers to data such as the quantity, type, and storage location of products currently stored in warehouses or stores.

[1275] "Seasonal Data" refers to data regarding sales trends or fluctuations in demand during a particular season or time of year.

[1276] "Market trend information" refers to data that shows overall market trends and changes in consumer behavior.

[1277] "Artificial intelligence algorithms" refer to computer programs and methods for analyzing data and making predictions and decisions.

[1278] "Demand forecasting" refers to the process of predicting future sales volumes.

[1279] "Inventory Level" refers to the quantity of inventory at a particular location.

[1280] A "threshold" refers to a value that indicates a particular standard or limit.

[1281] "Replenishment orders" refer to orders or instructions to add inventory.

[1282] "Placing an order" refers to the process of requesting the supply of required goods.

[1283] "Inventory turnover" refers to the rate at which inventory is sold within a certain period of time.

[1284] "Rotation" refers to strategies and methods for efficiently rotating inventory.

[1285] "Products with poor sales" refers to products whose sales are below expectations.

[1286] "Good selling products" refer to products whose sales are favorable compared to expectations.

[1287] "Notification" refers to a message or alert that notifies you of a specific event.

[1288] "Interface" refers to the means or screen through which a user interacts with a system.

[1289] "Inventory management system" refers to the general term for software and hardware used to manage and monitor inventory information.

[1290] "Terminal" refers to a device or equipment that can be directly operated by a user.

[1291] This invention is a system that uses artificial intelligence (AI) to analyze sales information and inventory information and automate inventory management. This system mainly involves a server, terminals, and users, and operates in the following steps.

[1292] Hardware and software used

[1293] server

[1294] Hardware used: High-performance server computer

[1295] Software used: database software (e.g., MySQL or PostgreSQL), AI libraries (e.g., TensorFlow or PyTorch), data processing libraries (e.g., pandas)

[1296] Terminal

[1297] Hardware used: POS terminal, inventory management system linked terminal

[1298] Software used: Data transmission program, communication library (e.g., HTTP client)

[1299] User

[1300] Hardware required: A standard PC or tablet device

[1301] Software used: Web browser, dashboard display software

[1302] System Operation

[1303] Server Operation

[1304] The server periodically collects sales information from the POS system and online store. Specifically, it executes an SQL query to retrieve sales information in CSV format every night at midnight. The server also retrieves the latest inventory information from the inventory management system every hour. Furthermore, the server retrieves seasonal data and market trend information through an external API.

[1305] The server cleanses the collected data and removes invalid data and missing values. This process uses a data processing library (e.g., pandas). Next, it uses the cleansed data to train a demand forecasting model using an AI algorithm. For training, it uses AI libraries such as TensorFlow and PyTorch.

[1306] A trained AI model is used to predict future demand. The prediction results are displayed in real time on a dashboard for users to review. The server also monitors inventory levels in real time, automatically generating replenishment instructions and placing orders when they fall below a set threshold. The user is notified when replenishment is complete.

[1307] The server also analyzes inventory turnover and proposes efficient rotation by generating a report recommending the prioritization of older inventory.The server also monitors all inventory status in real time, classifying and notifying products that are selling poorly or well.

[1308] Device behavior

[1309] The terminal periodically sends sales information from the POS system and online store to the server. It also works with the inventory management system to send collected inventory information to the server, allowing the server to always obtain the latest information.

[1310] User operations

[1311] Users can use the dashboard provided by the server to check inventory status and demand forecast results in real time. For items that are not selling well, they can take measures such as promotions and discounts. They can also receive notifications from the server to check order status and replenishment and take appropriate action.

[1312] Specific examples

[1313] Server processing example

[1314] The server runs the SQL query "select from sales where date = current_date()" every night to collect sales information from the POS system, updates the latest inventory information every hour, and runs Python scripts to cleanse the data frame with the pandas library and train the AI ​​model with TensorFlow.

[1315] Terminal processing example

[1316] The terminal uploads sales information to the server at regular intervals, and also shares the latest inventory information with the server.

[1317] User operation example

[1318] Users can view the dashboard to see the results of the next week's demand forecast, get notified about slow-selling items, and implement promotions.

[1319] Prompt Sentence Examples

[1320] "Please introduce this system. Please explain in detail the processing steps of the program that uses AI to analyze sales and inventory information and automate inventory management."

[1321] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1322] Step 1:

[1323] The server periodically collects sales information. Specifically, it retrieves the day's sales information in CSV format from the POS system every night at midnight. The input is the POS system's sales information database, and the output is the collected CSV file. The server executes an SQL query to extract data using the command "select from sales where date = current_date()". The retrieved data is saved in a specified directory.

[1324] Step 2:

[1325] The server collects inventory information. Specifically, it retrieves the latest inventory data from the inventory management system every hour. The input is the inventory information database of the inventory management system, and the output is the collected inventory data. The server calls the API via an HTTP request to retrieve the inventory data.

[1326] Step 3:

[1327] The server obtains seasonal data and market trend information. Specifically, it uses an external API to obtain weekly forecasts and market trend information. The input is the season information and market data API, and the output is the obtained seasonal data and market trend information. The server sends a request to the REST API endpoint and receives data in JSON format.

[1328] Step 4:

[1329] The server cleanses the collected data, removing invalid data and missing values. The input is the collected sales information, inventory information, seasonal data, and market trend information, and the output is a cleansed dataset. The server uses Python scripts and the pandas library to arrange the data using methods such as "df.dropna()" and "df[df['sales'] > 0]".

[1330] Step 5:

[1331] The server trains an AI demand forecasting model. Specifically, it uses the cleansed data and an AI algorithm (e.g., TensorFlow or PyTorch) to train the demand forecasting model. The input is the cleansed dataset, and the output is the trained point model. The server runs code such as "model.fit(data, epochs=100)" to train the model.

[1332] Step 6:

[1333] The server uses a trained AI model to forecast demand. Specifically, it predicts future sales figures and displays the results on a dashboard. The input is the trained model and the latest data, and the output is the prediction results. The server uses the method "predictions = model.predict(new_data)" to reflect the results on the dashboard.

[1334] Step 7:

[1335] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold (e.g., 50 units). The input is a real-time inventory database, and the output is replenishment orders. The server executes logic such as "if inventory < threshold: generate_replenishment_order()".

[1336] Step 8:

[1337] The server sends the order instruction to the supplier. The input is the automatically generated replenishment instruction, and the output is the order request sent to the supplier. Specifically, the order instruction is sent to the supplier via an API request.

[1338] Step 9:

[1339] The user checks for replenishment. Specifically, they receive a notification from the server and check the order status on the dashboard. The input is the notification from the server, and the output is the user's confirmation and response. The user checks the order status and replenishment status on the dashboard and takes the necessary action.

[1340] Step 10:

[1341] The server analyzes inventory turnover and proposes efficient rotation. The input is real-time inventory data, and the output is the turnover analysis results and a proposal report. The server uses a data analysis algorithm to calculate efficient inventory rotation and proposes it to the user.

[1342] Step 11:

[1343] The server grasps sales status in real time, classifies products into those that are selling poorly and those that are selling well, and notifies them. The input is real-time sales data, and the output is the classification results and notifications. The server periodically analyzes the data and notifies the dashboard and users.

[1344] (Application example 1)

[1345] 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."

[1346] In today's brick-and-mortar stores, improving the efficiency and accuracy of inventory management is a key issue. In particular, there is a need to grasp sales and inventory data in real time, forecast demand, and replenish inventory at the appropriate time. It is also necessary to take prompt action to address poorly selling items and propose efficient product display solutions. However, these tasks require a lot of time and effort, and are prone to human error. Furthermore, there is a need for a system that allows store managers and staff to instantly grasp the situation on-site.

[1347] 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.

[1348] In this invention, the server includes: means for periodically collecting sales data; means for collecting inventory data; means for acquiring seasonal information and market trend data; means for forecasting demand using an AI algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; means for checking inventory status in real time using a smart device (smartphone or smart glasses); means for proposing promotions for slow-selling items; and means for proposing replenishment times based on future demand forecasts. This enables the efficiency and accuracy of inventory management in physical stores to be improved.

[1349] "Sales data" refers to data relating to the quantity and amount of purchased goods generated through sales activities at physical stores.

[1350] "Inventory data" refers to data regarding the quantity and types of products currently stored in a physical store.

[1351] "Seasonal information" is information relating to sales trends and demand that fluctuate during specific seasons or periods.

[1352] "Market trend data" is the latest information on overall market trends and consumer purchasing habits.

[1353] An "AI algorithm" is a computational method using artificial intelligence to analyze massive amounts of data, find patterns, and derive next actions or predictions.

[1354] "Demand forecasting" is the process of predicting future sales volumes and demand based on past sales data and market trends.

[1355] "Inventory level" refers to the status of the number of specific items in stock in a store or warehouse.

[1356] A "replenishment instruction" is an instruction to add stock when the stock falls below a certain threshold.

[1357] "Placing an order" is the act of ordering goods from a supplier.

[1358] "Turnover rate" is an indicator that indicates the sales rate of inventory items over a certain period of time.

[1359] "Rotation" is the process of changing the placement and order of inventory items to ensure proper management.

[1360] A "best-selling product" is a product that is currently very popular and is being purchased by many consumers.

[1361] A "slow-selling product" is a product that is not being purchased much by consumers at the moment.

[1362] "Notification" is the act of promptly notifying a user of specific information.

[1363] A "smart device" is a portable electronic device (e.g., a smartphone or smart glasses) that can connect to the Internet and send and receive information.

[1364] "Promotion" refers to advertising and campaign activities to promote sales of slow-selling products.

[1365] The invention is a system that improves the efficiency and accuracy of inventory management in physical stores. This system uses AI to analyze sales data and inventory data and automates inventory management. An embodiment of this system is described below.

[1366] System configuration

[1367] The system consists of three main parts: the server, the terminal, and the user. The specific operation procedure is as follows:

[1368] Data collection

[1369] server

[1370] The server periodically collects sales data from POS systems and online stores, obtains current inventory data from inventory management systems, and uses external APIs to obtain seasonal information and market trend data.

[1371] Terminal

[1372] The terminal is responsible for sending data from the POS system or online store to the server. The terminal is used to link inventory data to the server.

[1373] Data analysis and demand forecasting

[1374] server

[1375] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[1376] Based on the cleansed data, an AI algorithm is used to train a demand forecasting model to predict future demand.

[1377] The prediction results are reflected in the dashboard and can be viewed by users.

[1378] Stock level monitoring and automatic replenishment

[1379] server

[1380] The server monitors inventory levels in real time and automatically generates replenishment instructions and sends order instructions to suppliers when inventory levels fall below a set threshold.

[1381] When the replenishment is completed, the user is notified.

[1382] User

[1383] Users can check the order progress and replenishment status on the terminal.

[1384] Inventory Optimization

[1385] server

[1386] The server analyzes inventory turnover and suggests efficient rotation.

[1387] The system suggests to the user to prioritize displaying older stock.

[1388] User

[1389] The user updates the product display based on the server's suggestions.

[1390] Real-time tracking and promotions

[1391] server

[1392] The server monitors all inventory status in real time and updates the dashboard with the latest information.

[1393] Categorize best-selling and worst-selling items and notify users.

[1394] User

[1395] Take measures such as promotions and discounts on slow-selling products.

[1396] Example of a system

[1397] This system is realized using specific hardware and software. The hardware used is a server equipped with a high-performance database and an AI computing unit, and smartphones or smart glasses are suitable terminals. The software used is Python Flask or Django for the server, and React Native (smartphones) or ARKit (smart glasses) for the client. TensorFlow and Keras are used for data analysis.

[1398] Specific example explanation

[1399] For example, the server collects the day's sales data from the POS system overnight and updates the current stock status from the inventory management system. Using a smartphone or smart glasses, store staff can check the stock status in real time. Furthermore, an AI model is used to predict demand for the next week based on past sales data, and the results suggest the appropriate time for replenishment.

[1400] Example prompt sentence:

[1401] "Please refer to the sales data for the past three years as of mid-October and forecast demand for next week."

[1402] By inputting these prompts, the AI ​​model performs detailed data analysis and provides specific demand forecasts, thereby improving the efficiency and accuracy of inventory management in physical stores.

[1403] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1404] Step 1:

[1405] The server collects sales data

[1406] Input: Sales data from POS systems and online stores

[1407] Specific operation: The server periodically connects to the POS system or online store to collect sales data, for example, by retrieving data through an API in the middle of the night.

[1408] Output: Collected sales data is stored on the server

[1409] Step 2:

[1410] The server collects inventory data

[1411] Input: Inventory data from inventory management system

[1412] Specific operation: The server connects to the inventory management system to obtain current inventory data, retrieves the data via API, and stores it on the server.

[1413] Output: The latest inventory data is stored on the server.

[1414] Step 3:

[1415] Server retrieves seasonal information and market trend data

[1416] Input: Seasonality and market trend data from external APIs

[1417] What it does: The server sends requests to external APIs to retrieve seasonality and market trend data. This can involve web scraping or API calls.

[1418] Output: The acquired seasonal information and market trend data is stored on the server.

[1419] Step 4:

[1420] The server cleanses the data

[1421] Inputs: Collected sales data, inventory data, seasonality information, market trend data

[1422] Specific operation: The server cleanses the collected data and removes invalid data and missing values. For example, it filters out data with negative values ​​and missing values.

[1423] Output: The cleansed data is passed to the AI ​​algorithm

[1424] Step 5:

[1425] The server uses an AI algorithm to predict demand.

[1426] Input: Cleansed data

[1427] How it works: The server uses the cleansed data to train an AI model to predict future demand, for example, using past sales data to predict sales for the next week.

[1428] Output: Forecasted supply and demand data is generated

[1429] Step 6:

[1430] The server monitors inventory levels in real time.

[1431] Input: Latest inventory data

[1432] What it does: The server monitors inventory levels in real time and immediately issues an alert if they fall below a set threshold.

[1433] Output: Status information on whether stock levels are normal or not

[1434] Step 7:

[1435] The server automatically generates replenishment instructions and places orders.

[1436] Input: Stock level status information

[1437] Specific operation: When the inventory level falls below a threshold, the server automatically generates replenishment instructions and sends order instructions to the supplier.

[1438] Output: Purchase order sent to supplier

[1439] Step 8:

[1440] The server analyzes inventory turnover and suggests efficient rotation.

[1441] Input: Past sales data and inventory data

[1442] Specific operation: The server calculates the inventory turnover rate and suggests an efficient display method, for example, suggesting that old inventory should be displayed at the front and new inventory at the back.

[1443] Output: The user is notified of the rotation suggestion

[1444] Step 9:

[1445] The server proposes a promotion for a slow-selling item

[1446] Input: Real-time sales data

[1447] What it does: The server detects slow-selling products and offers promotions or discounts for them, for example, offering limited-time sales on specific products.

[1448] Output: The user is notified of the promotion offer.

[1449] Step 10:

[1450] Users can check inventory status in real time using their smart devices.

[1451] Input: Stock status data provided by the server

[1452] Specific operation: The user checks the inventory status in real time through the application via a smartphone or smart glasses, for example, by viewing the inventory status on the in-app dashboard.

[1453] Output: Action guidelines based on the inventory status identified by the user

[1454] 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.

[1455] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. In addition, by combining this with an emotion engine that recognizes user emotions, it realizes more user-friendly inventory management.

[1456] System configuration

[1457] Data collection

[1458] 1. Server

[1459] The server periodically collects sales data from POS systems and online stores, and stores the collected data in a database on the server.

[1460] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[1461] The server uses external APIs to obtain seasonal information and market trend data.

[1462] 2. Terminal

[1463] The terminal sends sales data from the POS system or online store to the server. The data is sent to the server in real time as each transaction occurs.

[1464] The terminal connects to the inventory management system and sends inventory data to the server.

[1465] Data analysis and demand forecasting

[1466] 1. Server

[1467] The server cleanses the collected data, removing any invalid data or missing values.

[1468] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[1469] Use the trained model to predict future demand and display the forecast results in a dashboard.

[1470] Stock level monitoring and automatic replenishment

[1471] 1. Server

[1472] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold.

[1473] The server automatically sends the order instructions to the supplier.

[1474] The server notifies the user that the replenishment has occurred.

[1475] 2. Users

[1476] Users can check the order progress and replenishment status on the terminal.

[1477] Inventory Optimization

[1478] 1. Server

[1479] The server analyzes inventory turnover and suggests efficient rotation.

[1480] The server suggests to the user that older stock be given priority in displaying the items.

[1481] 2. Users

[1482] The user updates the product display based on the server's suggestions.

[1483] Real-time tracking

[1484] 1. Server

[1485] The server monitors inventory status in real time and displays the latest information on the dashboard.

[1486] The server classifies popular and unpopular items and notifies the user.

[1487] 2. Users

[1488] Users take measures such as promotions and discounts to combat slow-selling products.

[1489] Emotion engine integration

[1490] 1. Emotion Engine

[1491] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine collects emotional data through facial recognition and voice analysis.

[1492] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[1493] The server adjusts inventory management methods based on the user's emotional state and optimizes notifications and suggestions to reduce stress for the user.

[1494] 2. Users

[1495] Users receive notifications and suggestions based on emotion recognition from the server and provide feedback on inventory management as needed.

[1496] Specific examples

[1497] Data collection

[1498] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[1499] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[1500] Data analysis and demand forecasting

[1501] The server trains the AI ​​model based on past sales data to predict demand for the next week, and the forecast results are displayed on a dashboard for users to view.

[1502] Stock level monitoring and automatic replenishment

[1503] When beverage inventory falls below a specified threshold, the server automatically sends an order to the supplier, and the user can check the replenishment status and approve it via their terminal.

[1504] Inventory Optimization

[1505] The server analyzes the inventory turnover rate and suggests to the user to prioritize the display of older inventory. The user updates the product display based on the suggestions.

[1506] Real-time tracking

[1507] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[1508] Emotion engine integration

[1509] The server recognizes the user's emotions and adjusts the frequency of notifications or displays positive messages if the user is feeling stressed.

[1510] Users take appropriate inventory management actions based on feedback from the emotion engine to maintain efficient operations.

[1511] In this way, the system of the present invention links the server, terminals, and users, and further integrates the emotion engine, thereby improving the efficiency and accuracy of inventory management and reducing the burden on users.

[1512] The processing flow will be explained below.

[1513] Step 1:

[1514] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[1515] Step 2:

[1516] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[1517] Step 3:

[1518] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[1519] Step 4:

[1520] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[1521] Step 5:

[1522] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[1523] Step 6:

[1524] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[1525] Step 7:

[1526] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[1527] Step 8:

[1528] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[1529] Step 9:

[1530] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[1531] Step 10:

[1532] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[1533] Step 11:

[1534] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[1535] Step 12:

[1536] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[1537] Step 13:

[1538] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[1539] Step 14:

[1540] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[1541] Step 15:

[1542] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[1543] Step 16:

[1544] The server collects emotional data using an emotion engine that recognizes the user's emotions. Specifically, it obtains the user's emotional state in real time through facial recognition and voice analysis.

[1545] Step 17:

[1546] The server analyzes the collected emotional data in real time to understand the user's current emotional state, for example, detecting if the user is feeling stressed.

[1547] Step 18:

[1548] The server adjusts inventory management methods based on the user's emotional state, for example, reducing the frequency of notifications and displaying positive messages if the user is feeling stressed.

[1549] Step 19:

[1550] The user receives notifications and suggestions based on emotion recognition from the server, and provides feedback on inventory management as needed. By accepting responses based on emotions, the user can manage inventory while reducing stress.

[1551] In this way, the system of the present invention allows the server, terminals, and users to work together, and by integrating an emotion engine, it is possible to improve the efficiency and accuracy of inventory management while also reducing the burden on users.

[1552] Example 2

[1553] 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."

[1554] In modern inventory management systems, it is important to effectively manage sales and inventory information in real time and to perform highly accurate demand forecasts. However, in conventional systems, data collection and analysis are often performed manually, resulting in problems with efficiency and accuracy. In addition, inventory management and notifications do not take user emotions into account, which tends to place a heavy burden on users. To solve these issues, a more automated and highly accurate inventory management system is needed.

[1555] 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.

[1556] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal information and market trend information; means for forecasting demand using an AI algorithm based on the collected information; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; and means for recognizing a user's emotional state using an emotion engine and optimizing notifications and suggestions. This automates a series of processes, from collecting sales and inventory information to demand forecasting and optimal notifications and suggestions based on the user's emotions, enabling more efficient and accurate inventory management.

[1557] "Sales information" is data relating to the sales results of products and services, and includes details such as the date and time of the transaction, product name, quantity, and price.

[1558] "Inventory information" is data that indicates the current inventory status, such as the quantity of products stored in warehouses or stores, inventory history, and location information.

[1559] "Seasonal information" is data on consumption trends and sales trends related to specific seasons or events.

[1560] "Market trend information" is data on economic trends, such as the current market supply and demand balance and changes in consumer preferences.

[1561] An "AI algorithm" is a mathematical model or method for analyzing and predicting data using artificial intelligence technology.

[1562] "Demand forecasting" is the process of predicting future sales volumes based on past sales data and external factors.

[1563] "Stock level" is information that indicates how much of a particular product is currently in stock.

[1564] A "replenishment instruction" is an instruction to replenish new products when inventory is low.

[1565] "Placing an order" is the process of ordering goods from a supplier or source.

[1566] "Inventory turnover" is an indicator that shows how much merchandise is being brought in and out of stock over a certain period of time.

[1567] "Rotation" is a method of efficiently managing inventory by replacing it chronologically.

[1568] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[1569] "Notification" refers to notifications or notices sent from the system to the user.

[1570] A "suggestion" is a recommendation of an action or improvement method for the system to take to the user.

[1571] This invention is a system that collects sales information and inventory information, forecasts demand based on the information, and automates inventory management. Furthermore, by combining it with an emotion engine that recognizes user emotions, it has the advantage of reducing the burden on users.

[1572] System configuration

[1573] Data collection

[1574] server

[1575] The server periodically collects sales information from POS systems and online stores, makes API calls using a scripting language such as Python, retrieves the data, and stores it in a database.

[1576] The server collects inventory information in real time from the inventory management system, retrieves the data using HTTP requests, and stores it in a database.

[1577] The server also periodically retrieves seasonal and market trend information using external APIs, including, for example, weather forecast APIs and market trend APIs.

[1578] Terminal

[1579] The terminal transmits sales information to the server in real time each time a transaction occurs in a POS system or online store.

[1580] The terminals work in conjunction with an inventory management system and send inventory information to the server, which ensures that the latest inventory status is always reflected.

[1581] Data analysis and demand forecasting

[1582] server

[1583] The server cleanses the collected data, using the Python Pandas library to remove invalid data and missing values.

[1584] The server uses AI algorithms to train demand forecasting models based on the cleansed data, using machine learning libraries such as TensorFlow and Scikit-learn.

[1585] The trained model is used to predict future demand and the results are displayed in a dashboard, which users can view through a browser-based dashboard.

[1586] Stock level monitoring and automatic replenishment

[1587] server

[1588] The server monitors inventory levels in real time and automatically generates replenishment orders if they fall below a set threshold.

[1589] The server then places orders with suppliers based on the generated replenishment instructions. Orders are placed via email or a dedicated API.

[1590] The server notifies the user that the refill is complete.

[1591] User

[1592] Users can check the progress of their orders and check replenishment status through a dedicated interface, and are notified immediately when replenishment is complete.

[1593] Inventory Optimization

[1594] server

[1595] The server analyzes inventory turnover and suggests efficient rotation, for example, suggesting to the user to prioritize displaying older inventory.

[1596] Computer programs find ways to avoid inventory delays and backlogs and rotate products efficiently.

[1597] User

[1598] The user updates the product display based on the server's suggestions.

[1599] Real-time tracking

[1600] server

[1601] The server monitors all inventory status in real time, and the latest information is reflected on the dashboard.

[1602] The server classifies popular and unpopular items and notifies the user.

[1603] User

[1604] Users take measures such as promotions and discounts to combat slow-selling products.

[1605] Emotion engine integration

[1606] Emotion Engine

[1607] The server is equipped with an emotion engine that recognizes the user's emotions and collects emotional information through facial recognition and voice analysis.

[1608] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[1609] The server adjusts the content and frequency of notifications and suggestions based on the user's emotional state. By providing positive messages and timely notifications, the server reduces the user's stress.

[1610] User

[1611] Users receive and utilize the feedback and suggestions provided by the emotion engine to improve the efficiency of their inventory management.

[1612] Specific examples

[1613] A specific example of this is a process in which the server collects the day's sales information from the POS system in the middle of the night and obtains the latest stock status from the inventory management system.The server also trains an AI model based on past sales information to predict demand for the next week, and displays the results on a dashboard so that users can check them.

[1614] Prompt Sentence Examples

[1615] "Please provide an outline of your system for efficiently managing sales and inventory data. Also, explain how you use AI to analyze the collected data and how you build a user-friendly interface using an emotion engine."

[1616] In this way, the system of the present invention aims to improve the efficiency and accuracy of inventory management by linking the server, terminals, and users and further integrating the emotion engine.

[1617] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1618] Step 1:

[1619] Collection of sales information

[1620] The server periodically collects sales information from POS systems and online stores. For example, it uses a Python script to retrieve sales data from an API endpoint. It receives sales data from the API endpoint (transaction date and time, product name, quantity, price, etc.) as input and stores the sales data in a database as output.

[1621] Step 2:

[1622] Collecting inventory information

[1623] The server collects inventory information from the inventory management system in real time. It retrieves the inventory information using HTTP requests and stores it in a database. It receives current inventory information (product ID, quantity, location, etc.) from the inventory management system as input, and updates the database with the latest inventory status as output.

[1624] Step 3:

[1625] Obtaining seasonal and market trend information

[1626] The server uses external APIs to obtain seasonal and market trend information. Specifically, it obtains information from specified API endpoints. It receives seasonal and market trend data (weather information, consumption trends, etc.) as input and stores this data in a database as output.

[1627] Step 4:

[1628] Data Cleansing

[1629] The server cleanses the collected sales, inventory, seasonality, and market trend information. It uses the Python Pandas library to cleanse the data and remove incorrect data and missing values. It takes all the collected data as input and produces a cleansed dataset as output.

[1630] Step 5:

[1631] Training a demand forecasting model

[1632] The server uses AI algorithms to train a demand forecasting model based on the cleansed data. It uses machine learning libraries such as TensorFlow and Scikit-learn. It receives the cleansed dataset as input, selects features from the data, and trains the model. It generates a trained demand forecasting model as output.

[1633] Step 6:

[1634] Demand forecasting

[1635] The server uses the trained model to predict future demand. It provides new sales information and external information as inputs to the model and outputs future demand. The output results are reflected in a dashboard and provided to users in a visualized form.

[1636] Step 7:

[1637] Monitoring inventory levels

[1638] The server monitors inventory levels in real time and generates alerts if they fall below a set threshold. It receives real-time inventory information as input, checks inventory levels, and generates alerts as output, indicating that the conditions for a replenishment order have been met.

[1639] Step 8:

[1640] Generate replenishment orders

[1641] The server automatically generates replenishment orders when inventory levels fall below a set threshold. It receives inventory level alerts as input and creates replenishment orders. It sends the generated replenishment orders to suppliers as output.

[1642] Step 9:

[1643] Ordering from suppliers

[1644] The server places an order with the supplier based on the replenishment instructions. It sends order information via email or a dedicated API. It receives replenishment instructions as input and sends an order to the supplier. It outputs confirmation that the order information has been sent.

[1645] Step 10:

[1646] Inventory Turnover Analysis

[1647] The server analyzes inventory turnover. It combines sales data and inventory data for analysis and proposes efficient rotation. It receives past sales information and inventory information as input and calculates the turnover rate. It generates the inventory turnover analysis results as output and presents them to the user as a proposal.

[1648] Step 11:

[1649] Proposal for efficient rotation

[1650] The server suggests to the user to prioritize stocking older stock based on the results of inventory turnover analysis. It receives the results of the turnover analysis as input, generates a suggestion for efficient rotation, and notifies the user of the suggestion as output.

[1651] Step 12:

[1652] Real-time inventory monitoring

[1653] The server monitors the inventory status in real time and reflects the latest information on the dashboard. It receives real-time inventory data as input, updates the dashboard, and visualizes the latest information as output and provides it to the user.

[1654] Step 13:

[1655] Best-selling product categories

[1656] The server analyzes the sales data and classifies popular and unpopular products. It uses the sales data as input and applies machine learning algorithms to perform the classification. It then returns the classification results to the user as output.

[1657] Step 14:

[1658] Unpopular product notifications

[1659] The server notifies the user about unpopular products. It uses the product classification results as input and generates a notification. It notifies the user about unpopular products as output.

[1660] Step 15:

[1661] Collecting Emotional Data

[1662] The server collects emotion data using an emotion engine to recognize user emotions. It performs face recognition and voice analysis via a camera and microphone. It receives real-time face and voice data as input and generates emotion data. It generates emotion data for analysis as output.

[1663] Step 16:

[1664] Emotional state analysis

[1665] The server analyzes the collected emotional data in real time to understand the user's current emotional state. It uses the emotional data as input and applies an algorithm to analyze it, generating data that determines the user's emotional state as output.

[1666] Step 17:

[1667] Notification optimization

[1668] The server optimizes the content and frequency of notifications based on the user's emotional state. If the user is feeling stressed, it reduces the frequency of notifications and displays positive messages. It uses the emotional state data as input and modifies the notification strategy. It outputs the optimized notifications to the user.

[1669] (Application example 2)

[1670] 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."

[1671] Conventional inventory management systems had the ability to collect sales and inventory data to forecast demand and automatically generate replenishment instructions, but they were unable to adjust inventory management methods taking user emotions into account. Furthermore, they lacked a means for store staff to check inventory status in real time and respond based on customer emotions. As a result, they were unable to fully improve inventory management efficiency or user satisfaction.

[1672] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for periodically collecting sales data, means for collecting inventory data, means for acquiring seasonal information and market trend data, means for performing demand forecasting using an AI algorithm based on the collected data, means for monitoring inventory levels in real time, means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold, means for analyzing inventory turnover and proposing efficient rotation, means for classifying and notifying slow-selling and fast-selling items in real time, means for integrating an emotion processing engine that recognizes user emotions and collecting emotion data through facial recognition and voice analysis, means for adjusting an inventory management method according to the user's emotional state based on the collected emotion data, and means for displaying inventory status in real time using smart glasses and proposing responses based on customer emotions. This enables improved efficiency and accuracy of inventory management, reduced user burden, and improved customer satisfaction.

[1673] Key Word Definitions

[1674] "Sales data" refers to information relating to the sale of a product, and includes data such as the transaction date and time, product name, sales quantity, and price.

[1675] "Inventory data" is information indicating the quantity and location of currently held products, the condition of each product, and the inventory history.

[1676] "Seasonal information" is data about sales patterns and consumer behavior that are affected by seasonal fluctuations.

[1677] "Market trend data" refers to information about current market consumer demand, trends, competitor trends, and so on.

[1678] "AI algorithm" is a general term for computational methods and mathematical models used to analyze and predict data using artificial intelligence.

[1679] "Demand forecasting" is the process of analyzing past sales data and market trend data to predict future demand for products.

[1680] "Stock level" is a value that indicates the number of a particular product in stock at a given point in time.

[1681] A "threshold" is a set value that is a criterion for the occurrence of a specific condition or event.

[1682] A "replenishment order" is an order to a supplier or warehouse to supply goods when inventory is low.

[1683] "Turnover rate" is an indicator that shows the frequency of goods being received and shipped, and is a criterion for evaluating inventory efficiency.

[1684] "Rotation" is a method for efficiently managing inventory placement and shipping order.

[1685] The "emotion processing engine" is a system that analyzes the user's facial expressions and voice and recognizes their emotions.

[1686] "Facial recognition" is a technology that uses a camera to detect a person's face and obtain its identification information.

[1687] "Voice analysis" is a technology that analyzes voice data to detect its content and the speaker's emotions.

[1688] "Emotion data" is information that expresses the user's emotional state in numerical values ​​or categories.

[1689] "Smart glasses" are eyeglass-type devices with display capabilities that allow users to view information in real time.

[1690] "Real-time inventory display" means that the current inventory information is displayed on the smart glasses at that moment.

[1691] "Customer emotion-based response" is the process of providing optimal service and product recommendations based on the customer's recognized emotional state.

[1692] MODE FOR CARRYING OUT THE INVENTION

[1693] To implement this invention, the system is mainly composed of a server, a terminal, and a user. The functions of each component and specific implementation methods thereof will be described below.

[1694] Server Functions and Implementation Methods

[1695] 1. Collect sales and inventory data:

[1696] The server periodically collects sales data from the POS system and online store and stores it in a database. It also retrieves current inventory data from the inventory management system. This allows for accurate inventory status in real time. The collected data is processed using Python libraries (e.g., Pandas and SQLAlchemy).

[1697] 2. Obtaining seasonality and market trend data:

[1698] The server obtains seasonal data and market trend information through external APIs, such as weather information APIs and market data APIs, and uses this data to forecast future demand.

[1699] 3. Demand forecasting using AI algorithms:

[1700] Train demand forecasting models based on collected sales, inventory, seasonality, and market trend data. Use Python machine learning libraries (e.g., TensorFlow and scikit-learn) to build and operate forecasting models based on historical data.

[1701] 4. Inventory level monitoring and automatic replenishment instructions:

[1702] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold, which are then sent to suppliers and notify the user upon completion.

[1703] 5. Emotion processing engine integration:

[1704] The server integrates an emotion processing engine that uses facial recognition and voice analysis to recognize user emotions. This includes facial recognition and voice analysis technologies using OpenCV and TensorFlow. The collected emotion data is analyzed in real time and used to adjust the inventory management system.

[1705] 6. Information display using smart glasses:

[1706] The smart glasses allow store staff to check stock availability in real time, and the same display also shows how to respond based on the customer's emotional state, using data transfer via Bluetooth and Wi-Fi.

[1707] Terminal functions and implementation methods

[1708] 1. Data transmission:

[1709] The terminal sends sales and inventory data in CSV format to the server, which transmits this data in real time as each transaction occurs.

[1710] 2. User Interface:

[1711] It provides an interface for users to check inventory information and replenishment status. Web applications and native applications are provided using smart devices (e.g., smartphones and tablets).

[1712] User roles and examples

[1713] 1. Real-time inventory check and action:

[1714] Users wear smart glasses and can check inventory information and demand forecast data in real time. For example, if a beverage runs low on stock, a notification will appear on the glasses and an order to replenish the supply will be automatically sent to the supplier.

[1715] 2. Emotional customer service:

[1716] If the customer is smiling, the prompt will say "Let us know if we can help you," and if the customer is unhappy, the prompt will say "Is there a problem?". Examples of such prompts include:

[1717] If the customer is smiling, it says "Let us know if we can help you."

[1718] If the customer seems unhappy, it asks, "Is there a problem?"

[1719] When stock is low, you will receive a notification saying, "Stock is low. Please prepare to replenish."

[1720] There is.

[1721] This system will improve the efficiency and accuracy of inventory management, reduce the burden on users, and increase customer satisfaction.

[1722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1723] Program processing flow

[1724] Step 1:

[1725] The server periodically collects sales data from POS systems and online stores and stores it in a database. Specifically, sales data is sent from the terminal to the server in real time when each transaction occurs. The input data is sales information (product ID, number of units sold, price, date and time), and libraries such as Pandas and SQLAlchemy are used to store this in the database. The latest sales data is saved in the database as output.

[1726] Step 2:

[1727] The server collects current inventory data from the inventory management system and grasps the latest inventory status. The input data is inventory information (product ID, inventory quantity, warehouse location), which is also saved in the database in real time. The output is the latest inventory data saved in the database.

[1728] Step 3:

[1729] The server uses external APIs to obtain seasonal information and market trend data. Examples of data obtained from APIs include weather information and past sales trends. After obtaining this data, it is used as a training dataset for the AI ​​model. Seasonal information and market trend data are collected as input, and these data are stored in a database as output.

[1730] Step 4:

[1731] The server uses an AI algorithm to make demand forecasts based on the collected sales data, inventory data, seasonal information, and market trend data. Specifically, it uses TensorFlow and scikit-learn to build and train a predictive model based on past data. Past sales data, inventory data, seasonal information, and market trend data are required as input, and future demand forecast results are obtained as output.

[1732] Step 5:

[1733] The server monitors inventory levels in real time based on the results of demand forecasts and automatically generates replenishment instructions when they fall below a set threshold. Specifically, it checks inventory data using Python processing, and if it falls below the threshold, it takes action to send replenishment instructions to suppliers by email or API. Real-time inventory data and a threshold are required as input, and the replenishment instructions are sent to suppliers as output.

[1734] Step 6:

[1735] A user wearing smart glasses can check inventory information in real time. This information is sent from the server to the smart glasses via Bluetooth or WiFi, and the current inventory status is displayed. The input is inventory information from the server, and the output is the inventory status displayed on the smart glasses display.

[1736] Step 7:

[1737] The server runs an emotion processing engine that performs facial recognition and voice analysis to recognize the user's emotions. It uses OpenCV and TensorFlow to perform facial recognition and voice analysis and collect emotion data. Raw data from the camera and microphone is required as input, and the output is the user's emotional state expressed as a number or category.

[1738] Step 8:

[1739] The user receives a prompt based on the emotional data displayed through the smart glasses. For example, if the customer is smiling, the smart glasses will display a prompt such as "Let us know if we can help you," and if the customer is in a bad mood, the smart glasses will display a prompt such as "Is there a problem?". An appropriate message is generated based on the emotional data as input, and the message is displayed on the smart glasses as output.

[1740] This series of processes makes inventory management more efficient, improves accuracy, reduces the burden on users, and improves customer satisfaction.

[1741] 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.

[1742] 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.

[1743] 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.

[1744] [Fourth embodiment]

[1745] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1746] 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.

[1747] 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).

[1748] 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.

[1749] 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.

[1750] 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).

[1751] 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.

[1752] 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.

[1753] 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.

[1754] 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.

[1755] 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.

[1756] 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.

[1757] 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."

[1758] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. Specifically, it operates in cooperation with a server, terminals, and users.

[1759] System configuration

[1760] Data collection

[1761] 1. Server

[1762] The server periodically collects sales data from POS systems and online stores.

[1763] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[1764] The server uses external APIs to obtain seasonal information and market trend data.

[1765] 2. Terminal

[1766] The terminal is responsible for transmitting data from the POS system and online store to the server.

[1767] The terminal works in conjunction with an inventory management system and sends inventory data to a server.

[1768] Data analysis and demand forecasting

[1769] 1. Server

[1770] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[1771] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[1772] The server uses the trained model to predict future demand.

[1773] The server displays the prediction results on a dashboard so that users can view them.

[1774] Stock level monitoring and automatic replenishment

[1775] 1. Server

[1776] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below set thresholds.

[1777] The server automatically sends the order instructions to the supplier.

[1778] The server notifies the user that the replenishment has occurred.

[1779] 2. Users

[1780] The user can check the progress of the order and replenishment on the terminal.

[1781] Inventory Optimization

[1782] 1. Server

[1783] The server analyzes inventory turnover and suggests efficient rotation.

[1784] The server suggests to the user that older stock be given priority in displaying the items.

[1785] 2. Users

[1786] The user updates the product display based on the server's suggestions.

[1787] Real-time tracking

[1788] 1. Server

[1789] The server monitors all inventory status in real time and reflects the latest information on the dashboard.

[1790] The server classifies popular and unpopular items and notifies the user.

[1791] 2. Users

[1792] Users take measures such as promotions and discounts to combat slow-selling products.

[1793] Specific examples

[1794] Data collection

[1795] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[1796] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[1797] Data analysis and demand forecasting

[1798] The server trains the AI ​​model based on sales data from the past October to predict demand for the next week. The forecast results are displayed on a dashboard for users to check.

[1799] Stock level monitoring and automatic replenishment

[1800] When the beverage inventory falls below 50 units, the server automatically sends an order to the supplier. The user can check the replenishment status and approve it via their terminal.

[1801] Inventory Optimization

[1802] The server analyzes the inventory turnover rate and suggests to the user that they should prioritize the display of beverages that arrived in August. The user updates their product display accordingly.

[1803] Real-time tracking

[1804] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[1805] In this way, the system of the present invention operates in cooperation with the server, terminals, and users to improve the efficiency and accuracy of inventory management.

[1806] The processing flow will be explained below.

[1807] Step 1:

[1808] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[1809] Step 2:

[1810] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[1811] Step 3:

[1812] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[1813] Step 4:

[1814] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[1815] Step 5:

[1816] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[1817] Step 6:

[1818] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[1819] Step 7:

[1820] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[1821] Step 8:

[1822] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[1823] Step 9:

[1824] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[1825] Step 10:

[1826] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[1827] Step 11:

[1828] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[1829] Step 12:

[1830] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[1831] Step 13:

[1832] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[1833] Step 14:

[1834] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[1835] Step 15:

[1836] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[1837] Example 1

[1838] 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."

[1839] In conventional inventory management systems, sales and inventory information was often collected manually, making it difficult to ensure accurate data and timely inventory replenishment. Furthermore, demand forecasting and efficient inventory rotation were not performed, increasing the risk of excess inventory and shortages. Furthermore, measures to address poorly selling products were delayed, making it difficult to grasp information on best-selling products in real time.

[1840] 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.

[1841] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal data and market trend information; means for forecasting demand using an artificial intelligence algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when the inventory level falls below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying products with poor sales and products with good sales in real time; means including an interface for users to check order status and replenishment; and terminal means for linking with the inventory management system and transmitting collected inventory information to the server. This enables efficient and accurate inventory management, timely inventory replenishment based on demand forecasts, and understanding of sales status in real time.

[1842] "Sales information" refers to data such as the quantity, price, and transaction time of the goods sold.

[1843] "Inventory information" refers to data such as the quantity, type, and storage location of products currently stored in warehouses or stores.

[1844] "Seasonal Data" refers to data regarding sales trends or fluctuations in demand during a particular season or time of year.

[1845] "Market trend information" refers to data that shows overall market trends and changes in consumer behavior.

[1846] "Artificial intelligence algorithms" refer to computer programs and methods for analyzing data and making predictions and decisions.

[1847] "Demand forecasting" refers to the process of predicting future sales volumes.

[1848] "Inventory Level" refers to the quantity of inventory at a particular location.

[1849] A "threshold" refers to a value that indicates a particular standard or limit.

[1850] "Replenishment orders" refer to orders or instructions to add inventory.

[1851] "Placing an order" refers to the process of requesting the supply of required goods.

[1852] "Inventory turnover" refers to the rate at which inventory is sold within a certain period of time.

[1853] "Rotation" refers to strategies and methods for efficiently rotating inventory.

[1854] "Products with poor sales" refers to products whose sales are below expectations.

[1855] "Good selling products" refer to products whose sales are favorable compared to expectations.

[1856] "Notification" refers to a message or alert that notifies you of a specific event.

[1857] "Interface" refers to the means or screen through which a user interacts with a system.

[1858] "Inventory management system" refers to the general term for software and hardware used to manage and monitor inventory information.

[1859] "Terminal" refers to a device or equipment that can be directly operated by a user.

[1860] This invention is a system that uses artificial intelligence (AI) to analyze sales information and inventory information and automate inventory management. This system mainly involves a server, terminals, and users, and operates in the following steps.

[1861] Hardware and software used

[1862] server

[1863] Hardware used: High-performance server computer

[1864] Software used: database software (e.g., MySQL or PostgreSQL), AI libraries (e.g., TensorFlow or PyTorch), data processing libraries (e.g., pandas)

[1865] Terminal

[1866] Hardware used: POS terminal, inventory management system linked terminal

[1867] Software used: Data transmission program, communication library (e.g., HTTP client)

[1868] User

[1869] Hardware required: A standard PC or tablet device

[1870] Software used: Web browser, dashboard display software

[1871] System Operation

[1872] Server Operation

[1873] The server periodically collects sales information from the POS system and online store. Specifically, it executes an SQL query to retrieve sales information in CSV format every night at midnight. The server also retrieves the latest inventory information from the inventory management system every hour. Furthermore, the server retrieves seasonal data and market trend information through an external API.

[1874] The server cleanses the collected data and removes invalid data and missing values. This process uses a data processing library (e.g., pandas). Next, it uses the cleansed data to train a demand forecasting model using an AI algorithm. For training, it uses AI libraries such as TensorFlow and PyTorch.

[1875] A trained AI model is used to predict future demand. The prediction results are displayed in real time on a dashboard for users to review. The server also monitors inventory levels in real time, automatically generating replenishment instructions and placing orders when they fall below a set threshold. The user is notified when replenishment is complete.

[1876] The server also analyzes inventory turnover and proposes efficient rotation by generating a report recommending the prioritization of older inventory.The server also monitors all inventory status in real time, classifying and notifying products that are selling poorly or well.

[1877] Device behavior

[1878] The terminal periodically sends sales information from the POS system and online store to the server. It also works with the inventory management system to send collected inventory information to the server, allowing the server to always obtain the latest information.

[1879] User operations

[1880] Users can use the dashboard provided by the server to check inventory status and demand forecast results in real time. For items that are not selling well, they can take measures such as promotions and discounts. They can also receive notifications from the server to check order status and replenishment and take appropriate action.

[1881] Specific examples

[1882] Server processing example

[1883] The server runs the SQL query "select from sales where date = current_date()" every night to collect sales information from the POS system, updates the latest inventory information every hour, and runs Python scripts to cleanse the data frame with the pandas library and train the AI ​​model with TensorFlow.

[1884] Terminal processing example

[1885] The terminal uploads sales information to the server at regular intervals, and also shares the latest inventory information with the server.

[1886] User operation example

[1887] Users can view the dashboard to see the results of the next week's demand forecast, get notified about slow-selling items, and implement promotions.

[1888] Prompt Sentence Examples

[1889] "Please introduce this system. Please explain in detail the processing steps of the program that uses AI to analyze sales and inventory information and automate inventory management."

[1890] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1891] Step 1:

[1892] The server periodically collects sales information. Specifically, it retrieves the day's sales information in CSV format from the POS system every night at midnight. The input is the POS system's sales information database, and the output is the collected CSV file. The server executes an SQL query to extract data using the command "select from sales where date = current_date()". The retrieved data is saved in a specified directory.

[1893] Step 2:

[1894] The server collects inventory information. Specifically, it retrieves the latest inventory data from the inventory management system every hour. The input is the inventory information database of the inventory management system, and the output is the collected inventory data. The server calls the API via an HTTP request to retrieve the inventory data.

[1895] Step 3:

[1896] The server obtains seasonal data and market trend information. Specifically, it uses an external API to obtain weekly forecasts and market trend information. The input is the season information and market data API, and the output is the obtained seasonal data and market trend information. The server sends a request to the REST API endpoint and receives data in JSON format.

[1897] Step 4:

[1898] The server cleanses the collected data, removing invalid data and missing values. The input is the collected sales information, inventory information, seasonal data, and market trend information, and the output is a cleansed dataset. The server uses Python scripts and the pandas library to arrange the data using methods such as "df.dropna()" and "df[df['sales'] > 0]".

[1899] Step 5:

[1900] The server trains an AI demand forecasting model. Specifically, it uses the cleansed data and an AI algorithm (e.g., TensorFlow or PyTorch) to train the demand forecasting model. The input is the cleansed dataset, and the output is the trained point model. The server runs code such as "model.fit(data, epochs=100)" to train the model.

[1901] Step 6:

[1902] The server uses a trained AI model to forecast demand. Specifically, it predicts future sales figures and displays the results on a dashboard. The input is the trained model and the latest data, and the output is the prediction results. The server uses the method "predictions = model.predict(new_data)" to reflect the results on the dashboard.

[1903] Step 7:

[1904] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold (e.g., 50 units). The input is a real-time inventory database, and the output is replenishment orders. The server executes logic such as "if inventory < threshold: generate_replenishment_order()".

[1905] Step 8:

[1906] The server sends the order instruction to the supplier. The input is the automatically generated replenishment instruction, and the output is the order request sent to the supplier. Specifically, the order instruction is sent to the supplier via an API request.

[1907] Step 9:

[1908] The user checks for replenishment. Specifically, they receive a notification from the server and check the order status on the dashboard. The input is the notification from the server, and the output is the user's confirmation and response. The user checks the order status and replenishment status on the dashboard and takes the necessary action.

[1909] Step 10:

[1910] The server analyzes inventory turnover and proposes efficient rotation. The input is real-time inventory data, and the output is the turnover analysis results and a proposal report. The server uses a data analysis algorithm to calculate efficient inventory rotation and proposes it to the user.

[1911] Step 11:

[1912] The server grasps sales status in real time, classifies products into those that are selling poorly and those that are selling well, and notifies them. The input is real-time sales data, and the output is the classification results and notifications. The server periodically analyzes the data and notifies the dashboard and users.

[1913] (Application example 1)

[1914] 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."

[1915] In today's brick-and-mortar stores, improving the efficiency and accuracy of inventory management is a key issue. In particular, there is a need to grasp sales and inventory data in real time, forecast demand, and replenish inventory at the appropriate time. It is also necessary to take prompt action to address poorly selling items and propose efficient product display solutions. However, these tasks require a lot of time and effort, and are prone to human error. Furthermore, there is a need for a system that allows store managers and staff to instantly grasp the situation on-site.

[1916] 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.

[1917] In this invention, the server includes: means for periodically collecting sales data; means for collecting inventory data; means for acquiring seasonal information and market trend data; means for forecasting demand using an AI algorithm based on the collected data; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; means for checking inventory status in real time using a smart device (smartphone or smart glasses); means for proposing promotions for slow-selling items; and means for proposing replenishment times based on future demand forecasts. This enables the efficiency and accuracy of inventory management in physical stores to be improved.

[1918] "Sales data" refers to data relating to the quantity and amount of purchased goods generated through sales activities at physical stores.

[1919] "Inventory data" refers to data regarding the quantity and types of products currently stored in a physical store.

[1920] "Seasonal information" is information relating to sales trends and demand that fluctuate during specific seasons or periods.

[1921] "Market trend data" is the latest information on overall market trends and consumer purchasing habits.

[1922] An "AI algorithm" is a computational method using artificial intelligence to analyze massive amounts of data, find patterns, and derive next actions or predictions.

[1923] "Demand forecasting" is the process of predicting future sales volumes and demand based on past sales data and market trends.

[1924] "Inventory level" refers to the status of the number of specific items in stock in a store or warehouse.

[1925] A "replenishment instruction" is an instruction to add stock when the stock falls below a certain threshold.

[1926] "Placing an order" is the act of ordering goods from a supplier.

[1927] "Turnover rate" is an indicator that indicates the sales rate of inventory items over a certain period of time.

[1928] "Rotation" is the process of changing the placement and order of inventory items to ensure proper management.

[1929] A "best-selling product" is a product that is currently very popular and is being purchased by many consumers.

[1930] A "slow-selling product" is a product that is not being purchased much by consumers at the moment.

[1931] "Notification" is the act of promptly notifying a user of specific information.

[1932] A "smart device" is a portable electronic device (e.g., a smartphone or smart glasses) that can connect to the Internet and send and receive information.

[1933] "Promotion" refers to advertising and campaign activities to promote sales of slow-selling products.

[1934] The invention is a system that improves the efficiency and accuracy of inventory management in physical stores. This system uses AI to analyze sales data and inventory data and automates inventory management. An embodiment of this system is described below.

[1935] System configuration

[1936] The system consists of three main parts: the server, the terminal, and the user. The specific operation procedure is as follows:

[1937] Data collection

[1938] server

[1939] The server periodically collects sales data from POS systems and online stores, obtains current inventory data from inventory management systems, and uses external APIs to obtain seasonal information and market trend data.

[1940] Terminal

[1941] The terminal is responsible for sending data from the POS system or online store to the server. The terminal is used to link inventory data to the server.

[1942] Data analysis and demand forecasting

[1943] server

[1944] The server cleanses the collected sales data, inventory data, seasonal information, and market trend data to remove invalid data and missing values.

[1945] Based on the cleansed data, an AI algorithm is used to train a demand forecasting model to predict future demand.

[1946] The prediction results are reflected in the dashboard and can be viewed by users.

[1947] Stock level monitoring and automatic replenishment

[1948] server

[1949] The server monitors inventory levels in real time and automatically generates replenishment instructions and sends order instructions to suppliers when inventory levels fall below a set threshold.

[1950] When the replenishment is completed, the user is notified.

[1951] User

[1952] Users can check the order progress and replenishment status on the terminal.

[1953] Inventory Optimization

[1954] server

[1955] The server analyzes inventory turnover and suggests efficient rotation.

[1956] The system suggests to the user to prioritize displaying older stock.

[1957] User

[1958] The user updates the product display based on the server's suggestions.

[1959] Real-time tracking and promotions

[1960] server

[1961] The server monitors all inventory status in real time and updates the dashboard with the latest information.

[1962] Categorize best-selling and worst-selling items and notify users.

[1963] User

[1964] Take measures such as promotions and discounts on slow-selling products.

[1965] Example of a system

[1966] This system is realized using specific hardware and software. The hardware used is a server equipped with a high-performance database and an AI computing unit, and smartphones or smart glasses are suitable terminals. The software used is Python Flask or Django for the server, and React Native (smartphones) or ARKit (smart glasses) for the client. TensorFlow and Keras are used for data analysis.

[1967] Specific example explanation

[1968] For example, the server collects the day's sales data from the POS system overnight and updates the current stock status from the inventory management system. Using a smartphone or smart glasses, store staff can check the stock status in real time. Furthermore, an AI model is used to predict demand for the next week based on past sales data, and the results suggest the appropriate time for replenishment.

[1969] Example prompt sentence:

[1970] "Please refer to the sales data for the past three years as of mid-October and forecast demand for next week."

[1971] By inputting these prompts, the AI ​​model performs detailed data analysis and provides specific demand forecasts, thereby improving the efficiency and accuracy of inventory management in physical stores.

[1972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1973] Step 1:

[1974] The server collects sales data

[1975] Input: Sales data from POS systems and online stores

[1976] Specific operation: The server periodically connects to the POS system or online store to collect sales data, for example, by retrieving data through an API in the middle of the night.

[1977] Output: Collected sales data is stored on the server

[1978] Step 2:

[1979] The server collects inventory data

[1980] Input: Inventory data from inventory management system

[1981] Specific operation: The server connects to the inventory management system to obtain current inventory data, retrieves the data via API, and stores it on the server.

[1982] Output: The latest inventory data is stored on the server.

[1983] Step 3:

[1984] Server retrieves seasonal information and market trend data

[1985] Input: Seasonality and market trend data from external APIs

[1986] What it does: The server sends requests to external APIs to retrieve seasonality and market trend data. This can involve web scraping or API calls.

[1987] Output: The acquired seasonal information and market trend data is stored on the server.

[1988] Step 4:

[1989] The server cleanses the data

[1990] Inputs: Collected sales data, inventory data, seasonality information, market trend data

[1991] Specific operation: The server cleanses the collected data and removes invalid data and missing values. For example, it filters out data with negative values ​​and missing values.

[1992] Output: The cleansed data is passed to the AI ​​algorithm

[1993] Step 5:

[1994] The server uses an AI algorithm to predict demand.

[1995] Input: Cleansed data

[1996] How it works: The server uses the cleansed data to train an AI model to predict future demand, for example, using past sales data to predict sales for the next week.

[1997] Output: Forecasted supply and demand data is generated

[1998] Step 6:

[1999] The server monitors inventory levels in real time.

[2000] Input: Latest inventory data

[2001] What it does: The server monitors inventory levels in real time and immediately issues an alert if they fall below a set threshold.

[2002] Output: Status information on whether stock levels are normal or not

[2003] Step 7:

[2004] The server automatically generates replenishment instructions and places orders.

[2005] Input: Stock level status information

[2006] Specific operation: When the inventory level falls below a threshold, the server automatically generates replenishment instructions and sends order instructions to the supplier.

[2007] Output: Purchase order sent to supplier

[2008] Step 8:

[2009] The server analyzes inventory turnover and suggests efficient rotation.

[2010] Input: Past sales data and inventory data

[2011] Specific operation: The server calculates the inventory turnover rate and suggests an efficient display method, for example, suggesting that old inventory should be displayed at the front and new inventory at the back.

[2012] Output: The user is notified of the rotation suggestion

[2013] Step 9:

[2014] The server proposes a promotion for a slow-selling item

[2015] Input: Real-time sales data

[2016] What it does: The server detects slow-selling products and offers promotions or discounts for them, for example, offering limited-time sales on specific products.

[2017] Output: The user is notified of the promotion offer.

[2018] Step 10:

[2019] Users can check inventory status in real time using their smart devices.

[2020] Input: Stock status data provided by the server

[2021] Specific operation: The user checks the inventory status in real time through the application via a smartphone or smart glasses, for example, by viewing the inventory status on the in-app dashboard.

[2022] Output: Action guidelines based on the inventory status identified by the user

[2023] 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.

[2024] This invention is a system that uses AI to analyze sales data and inventory data and automates inventory management. In addition, by combining this with an emotion engine that recognizes user emotions, it realizes more user-friendly inventory management.

[2025] System configuration

[2026] Data collection

[2027] 1. Server

[2028] The server periodically collects sales data from POS systems and online stores, and stores the collected data in a database on the server.

[2029] The server collects current inventory data from the inventory management system and keeps track of the latest inventory status.

[2030] The server uses external APIs to obtain seasonal information and market trend data.

[2031] 2. Terminal

[2032] The terminal sends sales data from the POS system or online store to the server. The data is sent to the server in real time as each transaction occurs.

[2033] The terminal connects to the inventory management system and sends inventory data to the server.

[2034] Data analysis and demand forecasting

[2035] 1. Server

[2036] The server cleanses the collected data, removing any invalid data or missing values.

[2037] The server uses AI algorithms to train a demand forecasting model based on the cleansed data.

[2038] Use the trained model to predict future demand and display the forecast results in a dashboard.

[2039] Stock level monitoring and automatic replenishment

[2040] 1. Server

[2041] The server monitors inventory levels in real time and automatically generates replenishment orders when they fall below a set threshold.

[2042] The server automatically sends the order instructions to the supplier.

[2043] The server notifies the user that the replenishment has occurred.

[2044] 2. Users

[2045] Users can check the order progress and replenishment status on the terminal.

[2046] Inventory Optimization

[2047] 1. Server

[2048] The server analyzes inventory turnover and suggests efficient rotation.

[2049] The server suggests to the user that older stock be given priority in displaying the items.

[2050] 2. Users

[2051] The user updates the product display based on the server's suggestions.

[2052] Real-time tracking

[2053] 1. Server

[2054] The server monitors inventory status in real time and displays the latest information on the dashboard.

[2055] The server classifies popular and unpopular items and notifies the user.

[2056] 2. Users

[2057] Users take measures such as promotions and discounts to combat slow-selling products.

[2058] Emotion engine integration

[2059] 1. Emotion Engine

[2060] The server is equipped with an emotion engine that recognizes the user's emotions. The emotion engine collects emotional data through facial recognition and voice analysis.

[2061] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[2062] The server adjusts inventory management methods based on the user's emotional state and optimizes notifications and suggestions to reduce stress for the user.

[2063] 2. Users

[2064] Users receive notifications and suggestions based on emotion recognition from the server and provide feedback on inventory management as needed.

[2065] Specific examples

[2066] Data collection

[2067] The server collects the day's sales data from the POS system in the middle of the night and updates the current stock status from the inventory management system.

[2068] The terminal sends sales data in CSV format to the server and connects the latest inventory data to the server.

[2069] Data analysis and demand forecasting

[2070] The server trains the AI ​​model based on past sales data to predict demand for the next week, and the forecast results are displayed on a dashboard for users to view.

[2071] Stock level monitoring and automatic replenishment

[2072] When beverage inventory falls below a specified threshold, the server automatically sends an order to the supplier, and the user can check the replenishment status and approve it via their terminal.

[2073] Inventory Optimization

[2074] The server analyzes the inventory turnover rate and suggests to the user to prioritize the display of older inventory. The user updates the product display based on the suggestions.

[2075] Real-time tracking

[2076] The server monitors all inventory in real time and updates the dashboard with the latest information, notifying users of slow-selling items so they can run promotions.

[2077] Emotion engine integration

[2078] The server recognizes the user's emotions and adjusts the frequency of notifications or displays positive messages if the user is feeling stressed.

[2079] Users take appropriate inventory management actions based on feedback from the emotion engine to maintain efficient operations.

[2080] In this way, the system of the present invention links the server, terminals, and users, and further integrates the emotion engine, thereby improving the efficiency and accuracy of inventory management and reducing the burden on users.

[2081] The processing flow will be explained below.

[2082] Step 1:

[2083] The server periodically collects sales data from POS systems and online stores. Specifically, it accumulates sales data as it is generated and stores the information in a database within the server.

[2084] Step 2:

[2085] The terminal transmits sales data from the POS system or online store to the server. The terminal has the function of transmitting data to the server in real time as each transaction occurs.

[2086] Step 3:

[2087] The server collects current inventory data from the inventory management system, including the quantity of inventory, product location, and inventory receipt and delivery history.

[2088] Step 4:

[2089] The terminal works in conjunction with the inventory management system to transmit inventory data to the server. The terminal has the function of transmitting data to the server in real time whenever inventory changes.

[2090] Step 5:

[2091] The server uses external APIs to retrieve seasonal information and market trend data in order to collect data corresponding to specific periods or events.

[2092] Step 6:

[2093] The server cleanses all collected data and removes invalid data and missing values. Specifically, it standardizes data formats and complements missing values.

[2094] Step 7:

[2095] The server uses AI algorithms to train demand forecasting models based on the cleansed data, including historical sales data, inventory data, and seasonality information.

[2096] Step 8:

[2097] The server uses the trained model to predict future demand and generates the results, which are then displayed on a dashboard for users to view.

[2098] Step 9:

[2099] The server monitors inventory levels in real time, automatically generates replenishment orders when they fall below a set threshold, and records the replenishment orders generated by the server in a database.

[2100] Step 10:

[2101] The server automatically sends an order instruction to the supplier, and the order content is generated based on the replenishment instruction and sent to the supplier's system.

[2102] Step 11:

[2103] The user checks the progress of the order and the replenishment status on the terminal, which has an interface that displays the order status and forecast results.

[2104] Step 12:

[2105] The server analyzes the inventory turnover rate and proposes efficient rotation, and presents the user with a strategy for prioritizing the use of old inventory.

[2106] Step 13:

[2107] The user updates the product display and placement based on the server's suggestions. The user implements the recommended methods to improve inventory turnover.

[2108] Step 14:

[2109] The server monitors all inventory status in real time and updates the dashboard with the latest information. The server automatically classifies popular and unpopular items and notifies the user.

[2110] Step 15:

[2111] The user takes measures such as promotions and discounts for products that are not selling well. The user executes a specific response plan based on the notification from the server.

[2112] Step 16:

[2113] The server collects emotional data using an emotion engine that recognizes the user's emotions. Specifically, it obtains the user's emotional state in real time through facial recognition and voice analysis.

[2114] Step 17:

[2115] The server analyzes the collected emotional data in real time to understand the user's current emotional state, for example, detecting if the user is feeling stressed.

[2116] Step 18:

[2117] The server adjusts inventory management methods based on the user's emotional state, for example, reducing the frequency of notifications and displaying positive messages if the user is feeling stressed.

[2118] Step 19:

[2119] The user receives notifications and suggestions based on emotion recognition from the server, and provides feedback on inventory management as needed. By accepting responses based on emotions, the user can manage inventory while reducing stress.

[2120] In this way, the system of the present invention allows the server, terminals, and users to work together, and by integrating an emotion engine, it is possible to improve the efficiency and accuracy of inventory management while also reducing the burden on users.

[2121] Example 2

[2122] 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."

[2123] In modern inventory management systems, it is important to effectively manage sales and inventory information in real time and to perform highly accurate demand forecasts. However, in conventional systems, data collection and analysis are often performed manually, resulting in problems with efficiency and accuracy. In addition, inventory management and notifications do not take user emotions into account, which tends to place a heavy burden on users. To solve these issues, a more automated and highly accurate inventory management system is needed.

[2124] 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.

[2125] In this invention, the server includes: means for periodically collecting sales information; means for collecting inventory information; means for acquiring seasonal information and market trend information; means for forecasting demand using an AI algorithm based on the collected information; means for monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; means for analyzing inventory turnover and proposing efficient rotation; means for classifying and notifying slow-selling and hot-selling items in real time; and means for recognizing a user's emotional state using an emotion engine and optimizing notifications and suggestions. This automates a series of processes, from collecting sales and inventory information to demand forecasting and optimal notifications and suggestions based on the user's emotions, enabling more efficient and accurate inventory management.

[2126] "Sales information" is data relating to the sales results of products and services, and includes details such as the date and time of the transaction, product name, quantity, and price.

[2127] "Inventory information" is data that indicates the current inventory status, such as the quantity of products stored in warehouses or stores, inventory history, and location information.

[2128] "Seasonal information" is data on consumption trends and sales trends related to specific seasons or events.

[2129] "Market trend information" is data on economic trends, such as the current market supply and demand balance and changes in consumer preferences.

[2130] An "AI algorithm" is a mathematical model or method for analyzing and predicting data using artificial intelligence technology.

[2131] "Demand forecasting" is the process of predicting future sales volumes based on past sales data and external factors.

[2132] "Stock level" is information that indicates how much of a particular product is currently in stock.

[2133] A "replenishment instruction" is an instruction to replenish new products when inventory is low.

[2134] "Placing an order" is the process of ordering goods from a supplier or source.

[2135] "Inventory turnover" is an indicator that shows how much merchandise is being brought in and out of stock over a certain period of time.

[2136] "Rotation" is a method of efficiently managing inventory by replacing it chronologically.

[2137] An "emotion engine" is a system for recognizing and analyzing a user's emotional state.

[2138] "Notification" refers to notifications or notices sent from the system to the user.

[2139] A "suggestion" is a recommendation of an action or improvement method for the system to take to the user.

[2140] This invention is a system that collects sales information and inventory information, forecasts demand based on the information, and automates inventory management. Furthermore, by combining it with an emotion engine that recognizes user emotions, it has the advantage of reducing the burden on users.

[2141] System configuration

[2142] Data collection

[2143] server

[2144] The server periodically collects sales information from POS systems and online stores, makes API calls using a scripting language such as Python, retrieves the data, and stores it in a database.

[2145] The server collects inventory information in real time from the inventory management system, retrieves the data using HTTP requests, and stores it in a database.

[2146] The server also periodically retrieves seasonal and market trend information using external APIs, including, for example, weather forecast APIs and market trend APIs.

[2147] Terminal

[2148] The terminal transmits sales information to the server in real time each time a transaction occurs in a POS system or online store.

[2149] The terminals work in conjunction with an inventory management system and send inventory information to the server, which ensures that the latest inventory status is always reflected.

[2150] Data analysis and demand forecasting

[2151] server

[2152] The server cleanses the collected data, using the Python Pandas library to remove invalid data and missing values.

[2153] The server uses AI algorithms to train demand forecasting models based on the cleansed data, using machine learning libraries such as TensorFlow and Scikit-learn.

[2154] The trained model is used to predict future demand and the results are displayed in a dashboard, which users can view through a browser-based dashboard.

[2155] Stock level monitoring and automatic replenishment

[2156] server

[2157] The server monitors inventory levels in real time and automatically generates replenishment orders if they fall below a set threshold.

[2158] The server then places orders with suppliers based on the generated replenishment instructions. Orders are placed via email or a dedicated API.

[2159] The server notifies the user that the refill is complete.

[2160] User

[2161] Users can check the progress of their orders and check replenishment status through a dedicated interface, and are notified immediately when replenishment is complete.

[2162] Inventory Optimization

[2163] server

[2164] The server analyzes inventory turnover and suggests efficient rotation, for example, suggesting to the user to prioritize displaying older inventory.

[2165] Computer programs find ways to avoid inventory delays and backlogs and rotate products efficiently.

[2166] User

[2167] The user updates the product display based on the server's suggestions.

[2168] Real-time tracking

[2169] server

[2170] The server monitors all inventory status in real time, and the latest information is reflected on the dashboard.

[2171] The server classifies popular and unpopular items and notifies the user.

[2172] User

[2173] Users take measures such as promotions and discounts to combat slow-selling products.

[2174] Emotion engine integration

[2175] Emotion Engine

[2176] The server is equipped with an emotion engine that recognizes the user's emotions and collects emotional information through facial recognition and voice analysis.

[2177] The server analyzes the collected emotional data in real time to understand the user's current emotional state.

[2178] The server adjusts the content and frequency of notifications and suggestions based on the user's emotional state. By providing positive messages and timely notifications, the server reduces the user's stress.

[2179] User

[2180] Users receive and utilize the feedback and suggestions provided by the emotion engine to improve the efficiency of their inventory management.

[2181] Specific examples

[2182] A specific example of this is a process in which the server collects the day's sales information from the POS system in the middle of the night and obtains the latest stock status from the inventory management system.The server also trains an AI model based on past sales information to predict demand for the next week, and displays the results on a dashboard so that users can check them.

[2183] Prompt Sentence Examples

[2184] "Please provide an outline of your system for efficiently managing sales and inventory data. Also, explain how you use AI to analyze the collected data and how you build a user-friendly interface using an emotion engine."

[2185] In this way, the system of the present invention aims to improve the efficiency and accuracy of inventory management by linking the server, terminals, and users and further integrating the emotion engine.

[2186] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2187] Step 1:

[2188] Collection of sales information

[2189] The server periodically collects sales information from POS systems and online stores. For example, it uses a Python script to retrieve sales data from an API endpoint. It receives sales data from the API endpoint (transaction date and time, product name, quantity, price, etc.) as input and stores the sales data in a database as output.

[2190] Step 2:

[2191] Collecting inventory information

[2192] The server collects inventory information from the inventory management system in real time. It retrieves the inventory information using HTTP requests and stores it in a database. It receives current inventory information (product ID, quantity, location, etc.) from the inventory management system as input, and updates the database with the latest inventory status as output.

[2193] Step 3:

[2194] Obtaining seasonal and market trend information

[2195] The server uses external APIs to obtain seasonal and market trend information. Specifically, it obtains information from specified API endpoints. It receives seasonal and market trend data (weather information, consumption trends, etc.) as input and stores this data in a database as output.

[2196] Step 4:

[2197] Data Cleansing

[2198] The server cleanses the collected sales, inventory, seasonality, and market trend information. It uses the Python Pandas library to cleanse the data and remove incorrect data and missing values. It takes all the collected data as input and produces a cleansed dataset as output.

[2199] Step 5:

[2200] Training a demand forecasting model

[2201] The server uses AI algorithms to train a demand forecasting model based on the cleansed data. It uses machine learning libraries such as TensorFlow and Scikit-learn. It receives the cleansed dataset as input, selects features from the data, and trains the model. It generates a trained demand forecasting model as output.

[2202] Step 6:

[2203] Demand forecasting

[2204] The server uses the trained model to predict future demand. It provides new sales information and external information as inputs to the model and outputs future demand. The output results are reflected in a dashboard and provided to users in a visualized form.

[2205] Step 7:

[2206] Monitoring inventory levels

[2207] The server monitors inventory levels in real time and generates alerts if they fall below a set threshold. It receives real-time inventory information as input, checks inventory levels, and generates alerts as output, indicating that the conditions for a replenishment order have been met.

[2208] Step 8:

[2209] Generate replenishment orders

[2210] The server automatically generates replenishment orders when inventory levels fall below a set threshold. It receives inventory level alerts as input and creates replenishment orders. It sends the generated replenishment orders to suppliers as output.

[2211] Step 9:

[2212] Ordering from suppliers

[2213] The server places an order with the supplier based on the replenishment instructions. It sends order information via email or a dedicated API. It receives replenishment instructions as input and sends an order to the supplier. It outputs confirmation that the order information has been sent.

[2214] Step 10:

[2215] Inventory Turnover Analysis

[2216] The server analyzes inventory turnover. It combines sales data and inventory data for analysis and proposes efficient rotation. It receives past sales information and inventory information as input and calculates the turnover rate. It generates the inventory turnover analysis results as output and presents them to the user as a proposal.

[2217] Step 11:

[2218] Proposal for efficient rotation

[2219] The server suggests to the user to prioritize stocking older stock based on the results of inventory turnover analysis. It receives the results of the turnover analysis as input, generates a suggestion for efficient rotation, and notifies the user of the suggestion as output.

[2220] Step 12:

[2221] Real-time inventory monitoring

[2222] The server monitors the inventory status in real time and reflects the latest information on the dashboard. It receives real-time inventory data as input, updates the dashboard, and visualizes the latest information as output and provides it to the user.

[2223] Step 13:

[2224] Best-selling product categories

[2225] The server analyzes the sales data and classifies popular and unpopular products. It uses the sales data as input and applies machine learning algorithms to perform the classification. It then returns the classification results to the user as output.

[2226] Step 14:

[2227] Unpopular product notifications

[2228] The server notifies the user about unpopular products. It uses the product classification results as input and generates a notification. It notifies the user about unpopular products as output.

[2229] Step 15:

[2230] Collecting Emotional Data

[2231] The server collects emotion data using an emotion engine to recognize user emotions. It performs face recognition and voice analysis via a camera and microphone. It receives real-time face and voice data as input and generates emotion data. It generates emotion data for analysis as output.

[2232] Step 16:

[2233] Emotional state analysis

[2234] The server analyzes the collected emotional data in real time to understand the user's current emotional state. It uses the emotional data as input and applies an algorithm to analyze it, generating data that determines the user's emotional state as o...

Claims

1. A means of collecting sales data on a regular basis; a means for collecting inventory data; a means for obtaining seasonality information and market trend data; A means of forecasting demand using AI algorithms based on collected data; a means of monitoring inventory levels in real time; means for automatically generating replenishment instructions and placing orders when inventory levels fall below a preset threshold; A means to analyze inventory turnover and propose efficient rotation; A means to classify and notify slow-selling and hot-selling products in real time, A system including:

2. The system of claim 1 further comprising means for performing data preprocessing to remove incorrect data and missing values.

3. 10. The system of claim 1, further comprising means for notifying the user that an automatic replenishment has occurred and including an interface for user confirmation.

Images