system

Abstract

We provide the system. [Solution] Multiple sensor devices for acquiring environmental data, An image data acquisition device for obtaining visitor data, An analysis device that analyzes the aforementioned environmental data and visitor data to perform demand forecasting, An ordering device that automatically places orders for goods based on the aforementioned demand forecast, A display device that visualizes store management information, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the retail industry, difficulties in inventory management due to labor shortages and insufficient demand forecasting have become serious problems. Furthermore, there may be delays in responding to climate variations and local events, resulting in loss of sales opportunities and excess inventory. Also, in the midst of diversifying consumer needs, it is required to efficiently grasp customers' purchasing tendencies and quickly make product proposals. Therefore, it is necessary to comprehensively solve these problems and improve the efficiency of store operations and customer satisfaction.

Means for Solving the Problems

[0005] This invention comprises multiple sensor devices for acquiring environmental data and an image data acquisition device for acquiring visitor data. By combining an analysis device that analyzes this data and performs demand forecasting with an ordering device that automatically orders products based on the forecast results, optimal inventory management is achieved. Furthermore, a display device that visualizes store management information allows for real-time monitoring of store conditions. This provides a system that reduces the burden caused by labor shortages in retail stores and enables accurate demand forecasting and efficient inventory management.

[0006] "Environmental data" refers to information that indicates physical and meteorological conditions inside and outside the store, such as temperature, humidity, and weather.

[0007] A "sensor device" is a measuring instrument necessary for acquiring environmental data in real time.

[0008] "Visitor data" refers to information that shows the number of customers who visit a store, their attributes (such as age group and gender), and their behavioral patterns.

[0009] An "image data acquisition device" refers to equipment such as cameras that capture images and videos in order to understand the behavior and attributes of visitors.

[0010] An "analysis device" is a computer system used to process and analyze acquired data to forecast demand.

[0011] "Demand forecasting" is the process of estimating the future demand for a product based on past data and current conditions.

[0012] An "ordering system" is a system that automatically places orders for necessary goods based on demand forecast results from an analysis device.

[0013] "Display device" refers to a display or monitor used to visually show analysis, ordering information, and store management status.

[0014] "Product recommendation" refers to activities aimed at recommending the most suitable products to specific consumer segments based on analyzed consumer data. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, when an emotion engine is combined. [Figure 14]It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

[0024] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0031] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0035] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0036] This invention is a system aimed at improving the efficiency of retail operations, automating a series of processes including environmental data collection, visitor analysis, demand forecasting, inventory management, and information display.

[0037] The server first continuously collects environmental data such as temperature, humidity, and weather through multiple sensor devices installed inside and outside the store. In parallel, an image data acquisition device monitors the number of customers visiting the store and their behavior patterns, and transmits this data to the server in real time.

[0038] The server stores the collected data in a database and processes it further using an analysis device. The analysis device uses a combination of historical and current real-time data to run an algorithm that predicts future demand, forecasting when specific products will need to be ordered. This demand forecasting utilizes machine learning techniques to continuously update the model and improve data accuracy.

[0039] The terminal uses analysis results to present inventory management information to store staff. The display shows order quantity suggestions based on demand forecasts, as well as alerts regarding the risks of insufficient or excess inventory. This allows store staff to understand the store's inventory status in real time and make quick decisions.

[0040] Users can use the displayed information to confirm any necessary approvals and develop campaigns and marketing strategies tailored to their specific needs. In particular, optimizing product displays and promotions to reflect demand forecasts can aim to improve customer satisfaction.

[0041] As a concrete example, considering fluctuations in product demand based on season and weather, demand for hot beverages and soups increases during the winter. A server can predict this based on past sales data and secure sufficient inventory in advance. This prevents lost opportunities and maximizes sales.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server periodically acquires environmental data such as temperature, humidity, and weather from sensor devices placed inside and outside the store and stores it in a database.

[0045] Step 2:

[0046] The server receives data on the number of visitors, their attributes, and their behavioral patterns, captured by the image data acquisition device, and stores it in a database.

[0047] Step 3:

[0048] The server preprocesses the collected environmental and visitor data, removing noise and organizing the necessary information.

[0049] Step 4:

[0050] The server passes the pre-processed data to an analysis device, which then combines it with historical sales data to build a demand forecasting model. This model uses machine learning algorithms to estimate future demand.

[0051] Step 5:

[0052] Based on the results of the demand forecasting model, the server evaluates the inventory status of each product and identifies which products need to be ordered.

[0053] Step 6:

[0054] The server automatically sends order instructions to suppliers via the ordering device for products it determines require ordering. At this time, it generates order information including product name, quantity, and delivery date.

[0055] Step 7:

[0056] The terminal generates a real-time dashboard based on demand forecasts and inventory information provided by the server, and displays it visually to the store manager.

[0057] Step 8:

[0058] The terminal displays an alert and notifies the store manager if there is a risk of insufficient or excessive inventory.

[0059] Step 9:

[0060] Based on the information displayed on the dashboard, users can provide feedback to the system as needed to help improve future models.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] Efficiently forecasting demand and managing inventory in retail operations is crucial for maximizing sales and preventing lost opportunities. However, traditional systems struggle with accurate demand forecasting and rapid inventory management, relying on human judgment and posing a high risk of misfortunes and inventory shortages.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes a plurality of detector means for acquiring environmental information, an image information acquisition means for acquiring visitor information, and an information processing means for analyzing the environmental information and visitor information and performing demand forecasting. This enables highly accurate demand forecasting based on environmental changes and visitor behavior patterns, and allows for automated product management and efficient inventory control.

[0066] "Environmental information" refers to data about the physical conditions surrounding the store, such as temperature, humidity, and weather.

[0067] A "detector means" is a collection of devices or sensors for measuring and collecting environmental information.

[0068] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0069] "Image information acquisition means" refers to devices such as cameras used to acquire visitor information.

[0070] "Information processing means" refers to a computer device and its software used to analyze collected data and generate information related to demand forecasting and inventory management.

[0071] "Product management means" refers to a device or system that places orders for products and adjusts inventory based on demand forecast results.

[0072] "Information display means" refers to devices such as displays that provide store operation information to staff visually.

[0073] "Store efficiency" is a concept that refers to the utilization of resources and the maximization of profits in store operations.

[0074] "Market trends" refer to information about changes and trends in the market viewed over time.

[0075] This invention is a comprehensive system to support retail operations. The server continuously collects environmental information using multiple sensors installed inside and outside the store. These include temperature sensors, humidity sensors, and weather sensors. These sensors work in conjunction with data loggers to transmit information to the server.

[0076] Simultaneously, cameras installed at the store entrance and inside the store are used as a means of acquiring image information to collect visitor information. This captures the number of visitors and their behavior patterns, which are then transmitted to the server in real time. The server stores the acquired environmental information and visitor information in a structured database. Here, MySQL (registered trademark), a relational database management system, is used.

[0077] The server performs analysis and demand forecasting using Python scripts, SciKit-Learn, TENSORFLOW®, and other data analysis software. Demand forecasting is performed using time series analysis and machine learning algorithms. The analysis results are displayed via terminals using information display devices. This display is done via digital signage and tablet devices, providing staff with real-time inventory information and order quantity suggestions.

[0078] Based on this information, users make necessary decisions and formulate orders for required products and promotional strategies. For example, if increased demand for hot beverages is expected during the winter, the server will make a forecast based on past sales data and suggest the optimal inventory level in advance.

[0079] An example of a prompt for a generating AI model is, "Based on sales data for December over the past three years, predict the demand for hot beverages in the next December." This prompt allows the user to obtain specific predictive data and develop a sales strategy.

[0080] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0081] Step 1:

[0082] The server collects environmental information from multiple sensors. Specifically, temperature and humidity sensors measure the physical conditions around the store and periodically send this data to the server. The input is real-time data from each sensor, which the server stores in a database, converting it into a format usable for future analysis. This process allows for the detection of environmental changes around the store and provides the basic data necessary for subsequent demand forecasting.

[0083] Step 2:

[0084] The server collects visitor information using image information acquisition methods. Cameras installed in the store count the number of visitors and analyze customer behavior patterns, transmitting this data to the server in real time. The input is camera images, and the output is digital information such as the number of visitors and their behavior patterns. The server processes this data using image analysis software to understand visitor trends.

[0085] Step 3:

[0086] The server processes the collected environmental and visitor information and stores it in a database. Input is data from sensors and cameras, and output is structured database entries. MySQL is used for this database, and the data is stored with timestamps. This allows historical information to be referenced and used for subsequent data analysis.

[0087] Step 4:

[0088] The server performs data analysis using a Python program. This program retrieves environmental and visitor information from a database as input and uses machine learning algorithms to forecast demand. The output is the forecast result, which is generated as a graph representing demand fluctuations and as numerical forecast values. Libraries such as SciKit-Learn and TensorFlow are used for the analysis, generating a forecast model based on historical data.

[0089] Step 5:

[0090] The terminal displays analysis results in a user-friendly format for staff. Input is demand forecast data generated by the server, and output is demand forecast information and order suggestions displayed on the terminal's dashboard. The display device is designed to allow staff to instantly grasp inventory status, enabling them to efficiently plan orders.

[0091] Step 6:

[0092] Users make decisions based on the information displayed on their devices. The input is the displayed predictive data, and the output is specific ordering instructions and promotional plans. Using this data, users can effectively implement sales strategies while maintaining optimal inventory levels.

[0093] (Application Example 1)

[0094] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] To improve the efficiency of inventory management and sales promotion in retail stores, accurate demand forecasting based on environmental and visitor information is necessary. However, conventional systems lacked methods to properly acquire this data, analyze it in real time, and reflect it in efficient ordering systems and sales promotion measures. As a result, there were challenges such as excess inventory, stockout risks, and inefficient promotional measures, which reduced operational efficiency.

[0096] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0097] In this invention, the server includes multiple measuring device means for acquiring environmental information, image data acquisition means for acquiring visitor information, and analysis means for analyzing the environmental information and visitor information to perform demand forecasting. This enables efficient ordering of goods and optimization of sales promotion measures in stores.

[0098] "Environmental information" refers to data that shows external conditions such as temperature, humidity, and weather inside and outside the store.

[0099] "Measuring devices" refer to sensors and equipment installed to acquire environmental information.

[0100] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0101] "Image data acquisition means" refers to devices that use cameras and image processing technology to collect visitor information.

[0102] "Analysis means" refers to analytical devices and software used to predict demand based on collected environmental and visitor information.

[0103] "Goods" refers to merchandise or products sold in stores.

[0104] "Ordering method" refers to equipment or software that automatically orders necessary goods based on demand forecasts.

[0105] "Store operation information" refers to information regarding the store's inventory status and sales activities.

[0106] "Display means" refers to display devices or interfaces that visually provide analysis results and store operation information.

[0107] "Sales promotion measures" are strategic activities aimed at stimulating customer purchasing intent and boosting sales.

[0108] In this invention, a server installed in the store plays a central role. The server uses multiple measuring devices to acquire environmental information. These measuring devices include temperature and humidity sensors and weather sensors. This information is acquired in real time and stored in a database. Visitor information is collected using image data acquisition means, i.e., cameras installed in the store, and transmitted to the server.

[0109] The server uses analysis tools such as Python and TensorFlow to analyze this information. These tools generate multiple forecasting models based on a combination of historical and real-time data to predict demand. These forecasting models enable the prediction of demand for goods and products, allowing for timely ordering of items. This information is displayed as part of the store's operational information on display devices, specifically in-store terminals and staff mobile devices.

[0110] The terminal displays the analysis results, allowing store staff to quickly implement inventory management and sales promotion strategies based on this information. For example, if specific weather conditions are predicted, strategies to promote related products will be displayed on the screen. One practical application is a function that predicts increased demand for umbrellas during the rainy season and optimizes inventory accordingly.

[0111] Examples of prompts to input into a generative AI model are as follows:

[0112] "Based on the forecast for umbrella demand during the rainy season, please propose the optimal promotional strategy."

[0113] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0114] Step 1:

[0115] The server acquires environmental information from temperature, humidity, and weather sensors installed inside and outside the store. The input is sensor data, and the output is continuously updated environmental information data. The acquired data is stored in a database. This operation allows for real-time monitoring of weather conditions around the store.

[0116] Step 2:

[0117] The server acquires visitor information using cameras installed in the store. Specifically, it uses image processing technology to identify the number of customers and their behavioral patterns. The input is image data from the cameras, and the output is visitor information data. This operation provides basic data for analyzing the characteristics and trends of customers visiting the store.

[0118] Step 3:

[0119] The server analyzes collected environmental and visitor information. Machine learning algorithms using Python and TensorFlow are employed for the analysis. The input is information from a stored database, and the output is a forecast based on a demand forecasting model. This operation improves the accuracy of demand forecasting and makes it possible to predict future sales trends.

[0120] Step 4:

[0121] The server executes an automated process for ordering goods based on the prediction results. The input is the output of the prediction model, and the output is an optimized order list. This operation reduces the risk of stockouts and excess inventory and helps maintain an appropriate supply of goods.

[0122] Step 5:

[0123] The terminal displays forecast results and order information received from the server to the store staff. Inputs are order lists and demand forecast data from the server, and output is visualized store management information. This allows staff to understand the work situation in real time and respond quickly.

[0124] Step 6:

[0125] Users refer to the information displayed on their terminal and make necessary approvals or corrections. Input is the displayed store management information, and output is the approved order details or the revised sales plan. This process enables efficient inventory management and sales strategies.

[0126] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0127] This invention provides a system that enables more sophisticated store operations by recognizing the emotions of customers, in addition to forecasting demand from environmental and visitor data. By incorporating an emotion engine, this system grasps the emotional state of customers and optimizes store operations and customer service based on that information.

[0128] The server comprehensively manages environmental data such as temperature, humidity, and weather acquired from various sensor devices, as well as visitor data acquired from image data acquisition devices. In addition, the server also receives emotional data provided by the emotion engine and stores this data in its database.

[0129] The emotion engine analyzes visitors' facial expressions and voices to identify their emotional state (joy, anger, surprise, anxiety, etc.). This emotional data is then transmitted to a server. The analysis device uses this emotional data, in addition to conventional data, to more accurately predict visitors' purchasing intent and preferences, and to make appropriate product recommendations.

[0130] The terminal provides analyzed emotional data to store staff via a display device. This allows staff to respond according to each customer's emotional state, enabling them to provide more personalized service. The system can also automatically adjust store environment settings (music selection, lighting adjustments, etc.) based on emotions.

[0131] As a concrete example, suppose a visitor enters a store and the emotion engine detects signs of stress from the customer's facial expression. Based on this information, the server sends instructions to the terminal suggesting products with relaxing effects or creating a comfortable environment. Store staff can then use the displayed information to suggest appropriate products to the customer.

[0132] By using this system, stores can provide optimal service tailored to customers' emotions, thereby improving customer satisfaction.

[0133] The following describes the processing flow.

[0134] Step 1:

[0135] The server acquires environmental data such as temperature, humidity, and weather from multiple sensor devices installed in the store at regular intervals and stores it in a database.

[0136] Step 2:

[0137] The server performs facial recognition of visitors through an image data acquisition device, collects data on the number of visitors, their attributes, and behavioral patterns, and stores it in a database.

[0138] Step 3:

[0139] The emotion engine analyzes the visitor's facial expressions and voice to identify emotional states such as joy, anger, surprise, and anxiety, and sends that data to the server.

[0140] Step 4:

[0141] The server integrates and preprocesses the collected environmental data, visitor data, and sentiment data before passing it on to the analysis device. This includes noise reduction and standardization of data formats.

[0142] Step 5:

[0143] The analysis device uses pre-processed data to build a demand forecasting model in combination with historical sales data. It takes sentiment data into account to predict the popularity of specific products and customers' selection intentions.

[0144] Step 6:

[0145] Based on the demand forecast results, the server initiates the ordering process for the necessary goods through the automated ordering system. It generates order information and sends order instructions to the supplier system.

[0146] Step 7:

[0147] The terminal receives demand forecast results and sentiment data from the server, generates a real-time dashboard, and displays it to store staff.

[0148] Step 8:

[0149] The terminal displays alerts and suggestions to store staff based on the customer's emotional state. Specifically, if a customer is seeking relaxation, it provides information suggesting relevant products.

[0150] Step 9:

[0151] Users make decisions regarding customer service and store operations based on the information displayed on their devices, and provide feedback to the system to be used for future improvements.

[0152] (Example 2)

[0153] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0154] Traditional store management systems make it difficult to offer product suggestions and services that take into account the emotions of visitors, resulting in limited improvements in customer satisfaction. Furthermore, the inability to reflect visitors' feelings in real time hinders more personalized service and effective marketing.

[0155] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0156] In this invention, the server includes multiple detection means for acquiring environmental information, video information acquisition means for acquiring visitor information, and emotion recognition means for analyzing the visitor's emotional state and making product suggestions based on that information. This enables personalized and effective product suggestions tailored to the customer's emotions and optimizes store operations.

[0157] "Environmental information" refers to data related to the physical conditions of the store's exterior and interior, such as temperature, humidity, and weather.

[0158] A "detection device" refers to various sensor devices used to acquire environmental information, which allows for real-time monitoring of environmental changes.

[0159] "Visitor information" refers to data on the attributes and trends of customers who visit a store, including the time of visit, the number of people, and their behavioral patterns.

[0160] A "video information acquisition device" refers to cameras and other optical equipment used to acquire visitor information, recording the movements and actions of visitors.

[0161] "Analysis means" refers to system functions that integrate and analyze acquired environmental and visitor information to support business decision-making.

[0162] "Emotion recognition means" refers to technological means for analyzing a visitor's facial expressions and voice to identify their emotional state.

[0163] "Ordering method" refers to a function that automatically places orders for necessary products based on demand forecasts and customer sentiment, thereby optimizing inventory management.

[0164] "Display means" refers to screens, monitors, etc., used to visually present analysis results and store operation information.

[0165] "Store operation information" refers to data related to store operations, such as store performance, market trends, and customer sentiment.

[0166] To implement this invention, a server plays a central role. The server works in conjunction with various sensor devices to collect environmental data such as temperature, humidity, and weather in real time. It also uses a video information acquisition device to acquire image data of visitors. At this time, the server centrally manages the collected data and stores it in a database as environmental information and visitor information.

[0167] Emotion recognition technology utilizes software called an emotion engine. This software leverages deep learning to analyze the visitor's facial expressions and voice data to estimate their emotional state. The emotional data is then sent to a server and stored in a database.

[0168] An AI model will be implemented as an analytical tool. This AI model will analyze environmental information, visitor information, and sentiment data within the server to predict visitors' purchasing intent and preferences. Based on these analysis results, the server will send appropriate product suggestions to the terminals.

[0169] The terminal acts as a display device, showing the analyzed data to store staff. Using this information, store staff can provide personalized service to each visitor. Furthermore, the system can automatically adjust the music and lighting within the store according to the customer's mood.

[0170] For example, if the server recognizes that a visitor's emotional state is "stressed," it can display product suggestions with relaxation effects on the terminal, allowing store staff to make appropriate suggestions to the customer. This allows customers to enjoy their experience in the store with peace of mind, and as a result, it is possible to improve customer satisfaction at the store.

[0171] An example of a prompt message would be: "Please explain how this system analyzes visitors' emotions and optimizes store operations based on that analysis."

[0172] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0173] Step 1:

[0174] The server collects data such as temperature, humidity, and weather using various sensor devices to acquire environmental data. This input data is accumulated on the server and stored in a database as environmental information. The server performs operations such as acquiring data sent from sensors at regular intervals, correcting for abnormal or missing values, and then saving the data.

[0175] Step 2:

[0176] The server acquires image data of visitors using a video information acquisition device. This image data is converted into visitor information and stored in a database. The server analyzes the images and extracts data such as the number of visitors, their movements, and the time they entered the store.

[0177] Step 3:

[0178] The emotion engine generates emotion data by analyzing facial expressions and voices based on acquired visitor image data. Using image and voice data as input, a deep learning model extracts features from this data to estimate the emotional state. The emotion data is then labeled with categories such as "joy," "anger," "surprise," and "anxiety," and sent to the server.

[0179] Step 4:

[0180] The server processes integrated environmental information, visitor information, and sentiment data using an AI model as an analytical tool. This model predicts visitors' purchasing intent and product preferences, and generates analysis results. All integrated data is supplied to the AI ​​model as input, and the analysis results output product purchase recommendations and demand forecasts.

[0181] Step 5:

[0182] Based on the analyzed results, the server sends appropriate product suggestions and instructions to store staff to the terminal. The server formats the analysis results and sends and outputs specific suggestions for optimizing performance (e.g., relaxation products) to the terminal.

[0183] Step 6:

[0184] The terminal displays information sent from the server. Store staff use the information displayed on the terminal to provide personalized service and suggest the most suitable products and services to visitors. This allows visitors to receive services tailored to their emotional state. The terminal uses a display to show the analysis results in an easy-to-read format.

[0185] Step 7:

[0186] The system automatically adjusts the store's music and lighting settings based on emotional state data obtained from the server. This provides the optimal atmosphere according to the visitor's emotional state. Changes to the environment settings are carried out by an automated process based on specific scenarios.

[0187] (Application Example 2)

[0188] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0189] In modern retail operations, it is common practice to forecast demand using environmental and visitor information. However, there is a growing need to consider visitors' emotional states in addition to these factors to provide more personalized and effective customer service. Existing systems do not adequately optimize store operations and customer service based on emotional changes, hindering improvements in customer satisfaction.

[0190] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0191] In this invention, the server includes multiple sensor means for acquiring environmental information, image information acquisition means for acquiring visitor information, analysis means for analyzing environmental information and visitor information and performing demand forecasting, and means for recognizing the emotional state of visitors and optimizing customer service, which includes an emotion analysis engine. This enables advanced store management based on visitor emotion information.

[0192] "Environmental information" refers to data that represents the state of the external environment, and includes various elements such as temperature, humidity, and weather.

[0193] "Sensing means" refers to equipment used to acquire environmental information, and includes devices that measure the physical environment, such as thermometers and hygrometers.

[0194] "Visitor information" refers to data about people who visit a store, and is information obtained through images, audio, and other means.

[0195] "Image information acquisition means" refers to a device used to collect image data of visitors using cameras, video cameras, etc.

[0196] "Analysis means" refers to a device that has the function of performing demand forecasting by analyzing data based on acquired environmental information and visitor information.

[0197] "Demand forecasting" refers to information used to predict customer purchasing choices and product demand, enabling efficient inventory management and sales planning.

[0198] An "ordering device" is a device or system that places orders with suppliers in order to automatically supply goods based on demand forecasts.

[0199] "Display means" refers to devices used to visually present analysis results and store management information, and includes displays and projectors.

[0200] An "emotion analysis engine" is software that analyzes a visitor's facial expressions and voice to identify their emotional state and use that information to optimize customer service.

[0201] "Optimizing customer service" is the process of providing personalized services based on the customer's emotional state in order to improve customer satisfaction.

[0202] The system for carrying out this invention includes multiple sensor devices, an image information acquisition device, an analysis device, an ordering device, a display device, and an emotion analysis engine. A server plays a role in comprehensively managing these hardware and software components.

[0203] Specifically, sensor devices collect environmental information, and image information acquisition devices collect visitor information. A server receives this collected information and uses analysis devices to analyze the environmental information, visitor information, and sentiment data. Software such as Microsoft® Azure® Cognitive Services and Google® Cloud Vision AI can be used for the analysis.

[0204] Based on the analysis results, the server performs demand forecasting and sends ordering instructions for appropriate items to the ordering system. Furthermore, it visually provides the analyzed data to store staff through the display system, instantly conveying the information necessary for customer service.

[0205] For example, when a customer enters a store, a camera captures the customer's facial expression, and a server analyzes that information. If the analysis identifies that the customer is expressing "joy," the server provides guidance to the staff on how to present appropriate products.

[0206] Furthermore, when generating programs, a generation AI model can be used to form prompt statements. For example, the prompt "Generate suggestions for relaxing products to recommend to customers who are feeling stressed" can be input to the system, and the results can be used.

[0207] This system enables the provision of personalized service based on customer emotions, leading to increased efficiency in store operations and improved customer satisfaction.

[0208] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0209] Step 1:

[0210] The sensor device collects environmental information.

[0211] The server acquires environmental information such as temperature, humidity, and weather from multiple sensor devices. This allows detailed environmental data to be input into the server. The server then standardizes this data and temporarily stores it for the next analysis step.

[0212] Step 2:

[0213] The image information acquisition device acquires visitor information.

[0214] The server receives images of visitors transmitted from the camera. Using this image data as input, the server analyzes the visitor's facial expressions using facial recognition software. Audio data is also processed simultaneously as needed to identify the visitor's emotional state. The analyzed emotional data is processed by an emotion analysis engine, and the identified emotional state is output to the server.

[0215] Step 3:

[0216] The analysis tool uses the acquired data to perform demand forecasting.

[0217] The server integrates collected environmental information, visitor information, and sentiment data, and applies a demand forecasting model. This uses machine learning algorithms to predict consumer purchasing behavior. Based on the input data, it outputs a list of items that will be needed in the near future.

[0218] Step 4:

[0219] The system automatically orders the necessary items based on the ordering method.

[0220] The server issues instructions to suppliers to order goods based on demand forecasts. This is done via an e-commerce platform, and order information is output. Specific quantities and items are specified, enabling efficient inventory management.

[0221] Step 5:

[0222] Provide information to staff through display means.

[0223] Users receive analysis results from the display device, including store performance, visitor sentiment, and recommended actions. The display device provides staff with visualized data to quickly personalize customer interactions. Based on the output information, staff can take specific actions.

[0224] Step 6:

[0225] Generates prompt messages and adjusts the system's response.

[0226] The server uses a generative AI model to create prompt messages. For example, it might generate a prompt message such as, "Generate suggestions for relaxing products to recommend to customers who are feeling stressed." Using this prompt as input data, appropriate information and product suggestions are generated and fed back into store operations.

[0227] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0243] This invention is a system aimed at improving the efficiency of retail operations, automating a series of processes including environmental data collection, visitor analysis, demand forecasting, inventory management, and information display.

[0244] The server first continuously collects environmental data such as temperature, humidity, and weather through multiple sensor devices installed inside and outside the store. In parallel, an image data acquisition device monitors the number of customers visiting the store and their behavior patterns, and transmits this data to the server in real time.

[0245] The server stores the collected data in a database and processes it further using an analysis device. The analysis device uses a combination of historical and current real-time data to run an algorithm that predicts future demand, forecasting when specific products will need to be ordered. This demand forecasting utilizes machine learning techniques to continuously update the model and improve data accuracy.

[0246] The terminal uses analysis results to present inventory management information to store staff. The display shows order quantity suggestions based on demand forecasts, as well as alerts regarding the risks of insufficient or excess inventory. This allows store staff to understand the store's inventory status in real time and make quick decisions.

[0247] Users can use the displayed information to confirm any necessary approvals and develop campaigns and marketing strategies tailored to their specific needs. In particular, optimizing product displays and promotions to reflect demand forecasts can aim to improve customer satisfaction.

[0248] As a concrete example, considering fluctuations in product demand based on season and weather, demand for hot beverages and soups increases during the winter. A server can predict this based on past sales data and secure sufficient inventory in advance. This prevents lost opportunities and maximizes sales.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The server periodically acquires environmental data such as temperature, humidity, and weather from sensor devices placed inside and outside the store and stores it in a database.

[0252] Step 2:

[0253] The server receives data on the number of visitors, their attributes, and their behavioral patterns, captured by the image data acquisition device, and stores it in a database.

[0254] Step 3:

[0255] The server preprocesses the collected environmental and visitor data, removing noise and organizing the necessary information.

[0256] Step 4:

[0257] The server passes the pre-processed data to an analysis device, which then combines it with historical sales data to build a demand forecasting model. This model uses machine learning algorithms to estimate future demand.

[0258] Step 5:

[0259] Based on the results of the demand forecasting model, the server evaluates the inventory status of each product and identifies which products need to be ordered.

[0260] Step 6:

[0261] The server automatically sends order instructions to suppliers via the ordering device for products it determines require ordering. At this time, it generates order information including product name, quantity, and delivery date.

[0262] Step 7:

[0263] The terminal generates a real-time dashboard based on demand forecasts and inventory information provided by the server, and displays it visually to the store manager.

[0264] Step 8:

[0265] The terminal displays an alert and notifies the store manager if there is a risk of insufficient or excessive inventory.

[0266] Step 9:

[0267] Based on the information displayed on the dashboard, users can provide feedback to the system as needed to help improve future models.

[0268] (Example 1)

[0269] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0270] Efficiently forecasting demand and managing inventory in retail operations is crucial for maximizing sales and preventing lost opportunities. However, traditional systems struggle with accurate demand forecasting and rapid inventory management, relying on human judgment and posing a high risk of misfortunes and inventory shortages.

[0271] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0272] In this invention, the server includes a plurality of detector means for acquiring environmental information, an image information acquisition means for acquiring visitor information, and an information processing means for analyzing the environmental information and visitor information and performing demand forecasting. This enables highly accurate demand forecasting based on environmental changes and visitor behavior patterns, and allows for automated product management and efficient inventory control.

[0273] "Environmental information" refers to data about the physical conditions surrounding the store, such as temperature, humidity, and weather.

[0274] A "detector means" is a collection of devices or sensors for measuring and collecting environmental information.

[0275] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0276] "Image information acquisition means" refers to devices such as cameras used to acquire visitor information.

[0277] "Information processing means" refers to a computer device and its software used to analyze collected data and generate information related to demand forecasting and inventory management.

[0278] "Product management means" refers to a device or system that places orders for products and adjusts inventory based on demand forecast results.

[0279] "Information display means" refers to devices such as displays that provide store operation information to staff visually.

[0280] "Store efficiency" is a concept that refers to the utilization of resources and the maximization of profits in store operations.

[0281] "Market trends" refer to information about changes and trends in the market viewed over time.

[0282] This invention is a comprehensive system to support retail operations. The server continuously collects environmental information using multiple sensors installed inside and outside the store. These include temperature sensors, humidity sensors, and weather sensors. These sensors work in conjunction with data loggers to transmit information to the server.

[0283] Simultaneously, cameras installed at the store entrance and inside the store are used as a means of acquiring image information to collect visitor information. This captures the number of visitors and their behavior patterns, which are then transmitted to the server in real time. The server stores the acquired environmental information and visitor information in a structured database. Here, MySQL, a relational database management system, is used.

[0284] The server performs analysis using data analysis software such as Python scripts, SciKit-Learn, and TensorFlow, and conducts demand forecasting. The demand forecasting is carried out by time series analysis and machine learning algorithms. The analysis results are displayed by the information display means via the terminal. This display is performed by digital signage or tablet terminals, and real-time inventory information and order quantity proposals are provided to the staff.

[0285] Based on this information, the user makes necessary decisions and formulates orders for required products and promotion strategies. As a specific example, when it is expected that the demand for warm beverages will increase in winter, the server makes a prediction based on past sales data and proposes an optimal inventory quantity in advance.

[0286] As an example of the prompt text for the generative AI model, "Please predict the demand for warm beverages in the next December based on the sales data for December in the past three years" can be cited. With this prompt, the user can obtain specific prediction data and formulate a sales strategy.

[0287] The flow of the specific process in Example 1 will be described using FIG. 11.

[0288] Step 1:

[0289] The server collects environmental information from multiple detectors. Specifically, temperature sensors and humidity sensors measure the physical conditions around the store and periodically send the data to the server. The input is the real-time data from each sensor, and the server stores this in the database to convert it into a format that can be used for future analysis. Through this process, environmental changes around the store are detected, and the basic data required for subsequent demand forecasting is provided.

[0290] Step 2:

[0291] The server collects visitor information using image information acquisition methods. Cameras installed in the store count the number of visitors and analyze customer behavior patterns, transmitting this data to the server in real time. The input is camera images, and the output is digital information such as the number of visitors and their behavior patterns. The server processes this data using image analysis software to understand visitor trends.

[0292] Step 3:

[0293] The server processes the collected environmental and visitor information and stores it in a database. Input is data from sensors and cameras, and output is structured database entries. MySQL is used for this database, and the data is stored with timestamps. This allows historical information to be referenced and used for subsequent data analysis.

[0294] Step 4:

[0295] The server performs data analysis using a Python program. This program retrieves environmental and visitor information from a database as input and uses machine learning algorithms to forecast demand. The output is the forecast result, which is generated as a graph representing demand fluctuations and as numerical forecast values. Libraries such as SciKit-Learn and TensorFlow are used for the analysis, generating a forecast model based on historical data.

[0296] Step 5:

[0297] The terminal displays analysis results in a user-friendly format for staff. Input is demand forecast data generated by the server, and output is demand forecast information and order suggestions displayed on the terminal's dashboard. The display device is designed to allow staff to instantly grasp inventory status, enabling them to efficiently plan orders.

[0298] Step 6:

[0299] Users make decisions based on the information displayed on their devices. The input is the displayed predictive data, and the output is specific ordering instructions and promotional plans. Using this data, users can effectively implement sales strategies while maintaining optimal inventory levels.

[0300] (Application Example 1)

[0301] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0302] To improve the efficiency of inventory management and sales promotion in retail stores, accurate demand forecasting based on environmental and visitor information is necessary. However, conventional systems lacked methods to properly acquire this data, analyze it in real time, and reflect it in efficient ordering systems and sales promotion measures. As a result, there were challenges such as excess inventory, stockout risks, and inefficient promotional measures, which reduced operational efficiency.

[0303] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0304] In this invention, the server includes multiple measuring device means for acquiring environmental information, image data acquisition means for acquiring visitor information, and analysis means for analyzing the environmental information and visitor information to perform demand forecasting. This enables efficient ordering of goods and optimization of sales promotion measures in stores.

[0305] "Environmental information" refers to data that shows external conditions such as temperature, humidity, and weather inside and outside the store.

[0306] "Measuring devices" refer to sensors and equipment installed to acquire environmental information.

[0307] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0308] The "image data acquisition means" is a device using a camera or image processing technology for collecting visitor information.

[0309] The "analysis means" refers to an analysis device or software for predicting demand based on the collected environmental information and visitor information.

[0310] "Goods" refer to products and items sold in the store.

[0311] The "ordering means" refers to a device or software for automatically ordering necessary goods based on demand prediction.

[0312] "Store operation information" refers to information regarding the inventory status and sales activities of the store.

[0313] The "display means" is a display device or interface for visually providing the analysis results and store operation information.

[0314] "Sales promotion measures" are strategic activities for arousing customers' purchase desire and promoting sales.

[0315] In this invention, a server installed in the store plays a central role. The server uses a plurality of measuring devices to acquire environmental information. This measuring device includes a temperature and humidity sensor and a weather sensor. This information is acquired in real time and stored in a database. Visitor information is collected using the image data acquisition means, that is, a camera installed in the store, and transmitted to the server.

[0316] The server uses analysis tools such as Python and TensorFlow to analyze this information. These tools generate multiple forecasting models based on a combination of historical and real-time data to predict demand. These forecasting models enable the prediction of demand for goods and products, allowing for timely ordering of items. This information is displayed as part of the store's operational information on display devices, specifically in-store terminals and staff mobile devices.

[0317] The terminal displays the analysis results, allowing store staff to quickly implement inventory management and sales promotion strategies based on this information. For example, if specific weather conditions are predicted, strategies to promote related products will be displayed on the screen. One practical application is a function that predicts increased demand for umbrellas during the rainy season and optimizes inventory accordingly.

[0318] Examples of prompts to input into a generative AI model are as follows:

[0319] "Based on the forecast for umbrella demand during the rainy season, please propose the optimal promotional strategy."

[0320] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0321] Step 1:

[0322] The server acquires environmental information from temperature, humidity, and weather sensors installed inside and outside the store. The input is sensor data, and the output is continuously updated environmental information data. The acquired data is stored in a database. This operation allows for real-time monitoring of weather conditions around the store.

[0323] Step 2:

[0324] The server acquires visitor information using cameras installed in the store. Specifically, it uses image processing technology to identify the number of customers and their behavioral patterns. The input is image data from the cameras, and the output is visitor information data. This operation provides basic data for analyzing the characteristics and trends of customers visiting the store.

[0325] Step 3:

[0326] The server analyzes collected environmental and visitor information. Machine learning algorithms using Python and TensorFlow are employed for the analysis. The input is information from a stored database, and the output is a forecast based on a demand forecasting model. This operation improves the accuracy of demand forecasting and makes it possible to predict future sales trends.

[0327] Step 4:

[0328] The server executes an automated process for ordering goods based on the prediction results. The input is the output of the prediction model, and the output is an optimized order list. This operation reduces the risk of stockouts and excess inventory and helps maintain an appropriate supply of goods.

[0329] Step 5:

[0330] The terminal displays forecast results and order information received from the server to the store staff. Inputs are order lists and demand forecast data from the server, and output is visualized store management information. This allows staff to understand the work situation in real time and respond quickly.

[0331] Step 6:

[0332] Users refer to the information displayed on their terminal and make necessary approvals or corrections. Input is the displayed store management information, and output is the approved order details or the revised sales plan. This process enables efficient inventory management and sales strategies.

[0333] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0334] This invention provides a system that enables more sophisticated store operations by recognizing the emotions of customers, in addition to forecasting demand from environmental and visitor data. By incorporating an emotion engine, this system grasps the emotional state of customers and optimizes store operations and customer service based on that information.

[0335] The server comprehensively manages environmental data such as temperature, humidity, and weather acquired from various sensor devices, as well as visitor data acquired from image data acquisition devices. In addition, the server also receives emotional data provided by the emotion engine and stores this data in its database.

[0336] The emotion engine analyzes visitors' facial expressions and voices to identify their emotional state (joy, anger, surprise, anxiety, etc.). This emotional data is then transmitted to a server. The analysis device uses this emotional data, in addition to conventional data, to more accurately predict visitors' purchasing intent and preferences, and to make appropriate product recommendations.

[0337] The terminal provides analyzed emotional data to store staff via a display device. This allows staff to respond according to each customer's emotional state, enabling them to provide more personalized service. The system can also automatically adjust store environment settings (music selection, lighting adjustments, etc.) based on emotions.

[0338] As a concrete example, suppose a visitor enters a store and the emotion engine detects signs of stress from the customer's facial expression. Based on this information, the server sends instructions to the terminal suggesting products with relaxing effects or creating a comfortable environment. Store staff can then use the displayed information to suggest appropriate products to the customer.

[0339] By using this system, stores can provide optimal service tailored to customers' emotions, thereby improving customer satisfaction.

[0340] The following describes the processing flow.

[0341] Step 1:

[0342] The server acquires environmental data such as temperature, humidity, and weather from multiple sensor devices installed in the store at regular intervals and stores it in a database.

[0343] Step 2:

[0344] The server performs facial recognition of visitors through an image data acquisition device, collects data on the number of visitors, their attributes, and behavioral patterns, and stores it in a database.

[0345] Step 3:

[0346] The emotion engine analyzes the visitor's facial expressions and voice to identify emotional states such as joy, anger, surprise, and anxiety, and sends that data to the server.

[0347] Step 4:

[0348] The server integrates and preprocesses the collected environmental data, visitor data, and sentiment data before passing it on to the analysis device. This includes noise reduction and standardization of data formats.

[0349] Step 5:

[0350] The analysis device uses pre-processed data to build a demand forecasting model in combination with historical sales data. It takes sentiment data into account to predict the popularity of specific products and customers' selection intentions.

[0351] Step 6:

[0352] Based on the demand forecast results, the server initiates the ordering process for the necessary goods through the automated ordering system. It generates order information and sends order instructions to the supplier system.

[0353] Step 7:

[0354] The terminal receives demand forecast results and sentiment data from the server, generates a real-time dashboard, and displays it to store staff.

[0355] Step 8:

[0356] The terminal displays alerts and suggestions to store staff based on the customer's emotional state. Specifically, if a customer is seeking relaxation, it provides information suggesting relevant products.

[0357] Step 9:

[0358] Users make decisions regarding customer service and store operations based on the information displayed on their devices, and provide feedback to the system to be used for future improvements.

[0359] (Example 2)

[0360] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0361] Traditional store management systems make it difficult to offer product suggestions and services that take into account the emotions of visitors, resulting in limited improvements in customer satisfaction. Furthermore, the inability to reflect visitors' feelings in real time hinders more personalized service and effective marketing.

[0362] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0363] In this invention, the server includes multiple detection means for acquiring environmental information, video information acquisition means for acquiring visitor information, and emotion recognition means for analyzing the visitor's emotional state and making product suggestions based on that information. This enables personalized and effective product suggestions tailored to the customer's emotions and optimizes store operations.

[0364] "Environmental information" refers to data related to the physical conditions of the store's exterior and interior, such as temperature, humidity, and weather.

[0365] A "detection device" refers to various sensor devices used to acquire environmental information, which allows for real-time monitoring of environmental changes.

[0366] "Visitor information" refers to data on the attributes and trends of customers who visit a store, including the time of visit, the number of people, and their behavioral patterns.

[0367] A "video information acquisition device" refers to cameras and other optical equipment used to acquire visitor information, recording the movements and actions of visitors.

[0368] "Analysis means" refers to system functions that integrate and analyze acquired environmental and visitor information to support business decision-making.

[0369] "Emotion recognition means" refers to technological means for analyzing a visitor's facial expressions and voice to identify their emotional state.

[0370] "Ordering method" refers to a function that automatically places orders for necessary products based on demand forecasts and customer sentiment, thereby optimizing inventory management.

[0371] "Display means" refers to screens, monitors, etc., used to visually present analysis results and store operation information.

[0372] "Store operation information" refers to data related to store operations, such as store performance, market trends, and customer sentiment.

[0373] To implement this invention, a server plays a central role. The server works in conjunction with various sensor devices to collect environmental data such as temperature, humidity, and weather in real time. It also uses a video information acquisition device to acquire image data of visitors. At this time, the server centrally manages the collected data and stores it in a database as environmental information and visitor information.

[0374] Emotion recognition technology utilizes software called an emotion engine. This software leverages deep learning to analyze the visitor's facial expressions and voice data to estimate their emotional state. The emotional data is then sent to a server and stored in a database.

[0375] An AI model will be implemented as an analytical tool. This AI model will analyze environmental information, visitor information, and sentiment data within the server to predict visitors' purchasing intent and preferences. Based on these analysis results, the server will send appropriate product suggestions to the terminals.

[0376] The terminal acts as a display device, showing the analyzed data to store staff. Using this information, store staff can provide personalized service to each visitor. Furthermore, the system can automatically adjust the music and lighting within the store according to the customer's mood.

[0377] For example, if the server recognizes that a visitor's emotional state is "stressed," it can display product suggestions with relaxation effects on the terminal, allowing store staff to make appropriate suggestions to the customer. This allows customers to enjoy their experience in the store with peace of mind, and as a result, it is possible to improve customer satisfaction at the store.

[0378] An example of a prompt message would be: "Please explain how this system analyzes visitors' emotions and optimizes store operations based on that analysis."

[0379] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0380] Step 1:

[0381] The server collects data such as temperature, humidity, and weather using various sensor devices to acquire environmental data. This input data is accumulated on the server and stored in a database as environmental information. The server performs operations such as acquiring data sent from sensors at regular intervals, correcting for abnormal or missing values, and then saving the data.

[0382] Step 2:

[0383] The server acquires image data of visitors using a video information acquisition device. This image data is converted into visitor information and stored in a database. The server analyzes the images and extracts data such as the number of visitors, their movements, and the time they entered the store.

[0384] Step 3:

[0385] The emotion engine generates emotion data by analyzing facial expressions and voices based on acquired visitor image data. Using image and voice data as input, a deep learning model extracts features from this data to estimate the emotional state. The emotion data is then labeled with categories such as "joy," "anger," "surprise," and "anxiety," and sent to the server.

[0386] Step 4:

[0387] The server processes integrated environmental information, visitor information, and sentiment data using an AI model as an analytical tool. This model predicts visitors' purchasing intent and product preferences, and generates analysis results. All integrated data is supplied to the AI ​​model as input, and the analysis results output product purchase recommendations and demand forecasts.

[0388] Step 5:

[0389] Based on the analyzed results, the server sends appropriate product suggestions and instructions to store staff to the terminal. The server formats the analysis results and sends and outputs specific suggestions for optimizing performance (e.g., relaxation products) to the terminal.

[0390] Step 6:

[0391] The terminal displays information sent from the server. Store staff use the information displayed on the terminal to provide personalized service and suggest the most suitable products and services to visitors. This allows visitors to receive services tailored to their emotional state. The terminal uses a display to show the analysis results in an easy-to-read format.

[0392] Step 7:

[0393] The system automatically adjusts the store's music and lighting settings based on emotional state data obtained from the server. This provides the optimal atmosphere according to the visitor's emotional state. Changes to the environment settings are carried out by an automated process based on specific scenarios.

[0394] (Application Example 2)

[0395] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] In modern retail operations, it is common practice to forecast demand using environmental and visitor information. However, there is a growing need to consider visitors' emotional states in addition to these factors to provide more personalized and effective customer service. Existing systems do not adequately optimize store operations and customer service based on emotional changes, hindering improvements in customer satisfaction.

[0397] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0398] In this invention, the server includes multiple sensor means for acquiring environmental information, image information acquisition means for acquiring visitor information, analysis means for analyzing environmental information and visitor information and performing demand forecasting, and means for recognizing the emotional state of visitors and optimizing customer service, which includes an emotion analysis engine. This enables advanced store management based on visitor emotion information.

[0399] "Environmental information" refers to data that represents the state of the external environment, and includes various elements such as temperature, humidity, and weather.

[0400] "Sensing means" refers to equipment used to acquire environmental information, and includes devices that measure the physical environment, such as thermometers and hygrometers.

[0401] "Visitor information" refers to data about people who visit a store, and is information obtained through images, audio, and other means.

[0402] "Image information acquisition means" refers to a device used to collect image data of visitors using cameras, video cameras, etc.

[0403] "Analysis means" refers to a device that has the function of performing demand forecasting by analyzing data based on acquired environmental information and visitor information.

[0404] "Demand forecasting" refers to information used to predict customer purchasing choices and product demand, enabling efficient inventory management and sales planning.

[0405] An "ordering device" is a device or system that places orders with suppliers in order to automatically supply goods based on demand forecasts.

[0406] "Display means" refers to devices used to visually present analysis results and store management information, and includes displays and projectors.

[0407] An "emotion analysis engine" is software that analyzes a visitor's facial expressions and voice to identify their emotional state and use that information to optimize customer service.

[0408] "Optimizing customer service" is the process of providing personalized services based on the customer's emotional state in order to improve customer satisfaction.

[0409] The system for carrying out this invention includes multiple sensor devices, an image information acquisition device, an analysis device, an ordering device, a display device, and an emotion analysis engine. A server plays a role in comprehensively managing these hardware and software components.

[0410] Specifically, sensor devices collect environmental information, and image information acquisition devices collect visitor information. A server receives this collected information and uses analysis devices to analyze the environmental information, visitor information, and sentiment data. Software such as Microsoft Azure Cognitive Services or Google Cloud Vision AI can be used for the analysis.

[0411] Based on the analysis results, the server performs demand forecasting and sends ordering instructions for appropriate items to the ordering system. Furthermore, it visually provides the analyzed data to store staff through the display system, instantly conveying the information necessary for customer service.

[0412] For example, when a customer enters a store, a camera captures the customer's facial expression, and a server analyzes that information. If the analysis identifies that the customer is expressing "joy," the server provides guidance to the staff on how to present appropriate products.

[0413] Furthermore, when generating programs, a generation AI model can be used to form prompt statements. For example, the prompt "Generate suggestions for relaxing products to recommend to customers who are feeling stressed" can be input to the system, and the results can be used.

[0414] This system enables the provision of personalized service based on customer emotions, leading to increased efficiency in store operations and improved customer satisfaction.

[0415] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0416] Step 1:

[0417] The sensor device collects environmental information.

[0418] The server acquires environmental information such as temperature, humidity, and weather from multiple sensor devices. This allows detailed environmental data to be input into the server. The server then standardizes this data and temporarily stores it for the next analysis step.

[0419] Step 2:

[0420] The image information acquisition device acquires visitor information.

[0421] The server receives images of visitors transmitted from the camera. Using this image data as input, the server analyzes the visitor's facial expressions using facial recognition software. Audio data is also processed simultaneously as needed to identify the visitor's emotional state. The analyzed emotional data is processed by an emotion analysis engine, and the identified emotional state is output to the server.

[0422] Step 3:

[0423] The analysis tool uses the acquired data to perform demand forecasting.

[0424] The server integrates collected environmental information, visitor information, and sentiment data, and applies a demand forecasting model. This uses machine learning algorithms to predict consumer purchasing behavior. Based on the input data, it outputs a list of items that will be needed in the near future.

[0425] Step 4:

[0426] The system automatically orders the necessary items based on the ordering method.

[0427] The server issues instructions to suppliers to order goods based on demand forecasts. This is done via an e-commerce platform, and order information is output. Specific quantities and items are specified, enabling efficient inventory management.

[0428] Step 5:

[0429] Provide information to staff through display means.

[0430] Users receive analysis results from the display device, including store performance, visitor sentiment, and recommended actions. The display device provides staff with visualized data to quickly personalize customer interactions. Based on the output information, staff can take specific actions.

[0431] Step 6:

[0432] Generates prompt messages and adjusts the system's response.

[0433] The server uses a generative AI model to create prompt messages. For example, it might generate a prompt message such as, "Generate suggestions for relaxing products to recommend to customers who are feeling stressed." Using this prompt as input data, appropriate information and product suggestions are generated and fed back into store operations.

[0434] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0435] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0436] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0437] [Third Embodiment]

[0438] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0439] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0440] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0441] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0442] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0443] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0444] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0445] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0446] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0447] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0448] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0449] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0450] This invention is a system aimed at improving the efficiency of retail operations, automating a series of processes including environmental data collection, visitor analysis, demand forecasting, inventory management, and information display.

[0451] The server first continuously collects environmental data such as temperature, humidity, and weather through multiple sensor devices installed inside and outside the store. In parallel, an image data acquisition device monitors the number of customers visiting the store and their behavior patterns, and transmits this data to the server in real time.

[0452] The server stores the collected data in a database and processes it further using an analysis device. The analysis device uses a combination of historical and current real-time data to run an algorithm that predicts future demand, forecasting when specific products will need to be ordered. This demand forecasting utilizes machine learning techniques to continuously update the model and improve data accuracy.

[0453] The terminal uses analysis results to present inventory management information to store staff. The display shows order quantity suggestions based on demand forecasts, as well as alerts regarding the risks of insufficient or excess inventory. This allows store staff to understand the store's inventory status in real time and make quick decisions.

[0454] Users can use the displayed information to confirm any necessary approvals and develop campaigns and marketing strategies tailored to their specific needs. In particular, optimizing product displays and promotions to reflect demand forecasts can aim to improve customer satisfaction.

[0455] As a concrete example, considering fluctuations in product demand based on season and weather, demand for hot beverages and soups increases during the winter. A server can predict this based on past sales data and secure sufficient inventory in advance. This prevents lost opportunities and maximizes sales.

[0456] The following describes the processing flow.

[0457] Step 1:

[0458] The server periodically acquires environmental data such as temperature, humidity, and weather from sensor devices placed inside and outside the store and stores it in a database.

[0459] Step 2:

[0460] The server receives data on the number of visitors, their attributes, and their behavioral patterns, captured by the image data acquisition device, and stores it in a database.

[0461] Step 3:

[0462] The server preprocesses the collected environmental and visitor data, removing noise and organizing the necessary information.

[0463] Step 4:

[0464] The server passes the pre-processed data to an analysis device, which then combines it with historical sales data to build a demand forecasting model. This model uses machine learning algorithms to estimate future demand.

[0465] Step 5:

[0466] Based on the results of the demand forecasting model, the server evaluates the inventory status of each product and identifies which products need to be ordered.

[0467] Step 6:

[0468] The server automatically sends order instructions to suppliers via the ordering device for products it determines require ordering. At this time, it generates order information including product name, quantity, and delivery date.

[0469] Step 7:

[0470] The terminal generates a real-time dashboard based on demand forecasts and inventory information provided by the server, and displays it visually to the store manager.

[0471] Step 8:

[0472] The terminal displays an alert and notifies the store manager if there is a risk of insufficient or excessive inventory.

[0473] Step 9:

[0474] Based on the information displayed on the dashboard, users can provide feedback to the system as needed to help improve future models.

[0475] (Example 1)

[0476] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0477] Efficiently forecasting demand and managing inventory in retail operations is crucial for maximizing sales and preventing lost opportunities. However, traditional systems struggle with accurate demand forecasting and rapid inventory management, relying on human judgment and posing a high risk of misfortunes and inventory shortages.

[0478] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0479] In this invention, the server includes a plurality of detector means for acquiring environmental information, an image information acquisition means for acquiring visitor information, and an information processing means for analyzing the environmental information and visitor information and performing demand forecasting. This enables highly accurate demand forecasting based on environmental changes and visitor behavior patterns, and allows for automated product management and efficient inventory control.

[0480] "Environmental information" refers to data about the physical conditions surrounding the store, such as temperature, humidity, and weather.

[0481] A "detector means" is a collection of devices or sensors for measuring and collecting environmental information.

[0482] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0483] "Image information acquisition means" refers to devices such as cameras used to acquire visitor information.

[0484] "Information processing means" refers to a computer device and its software used to analyze collected data and generate information related to demand forecasting and inventory management.

[0485] "Product management means" refers to a device or system that places orders for products and adjusts inventory based on demand forecast results.

[0486] "Information display means" refers to devices such as displays that provide store operation information to staff visually.

[0487] "Store efficiency" is a concept that refers to the utilization of resources and the maximization of profits in store operations.

[0488] "Market trends" refer to information about changes and trends in the market viewed over time.

[0489] This invention is a comprehensive system to support retail operations. The server continuously collects environmental information using multiple sensors installed inside and outside the store. These include temperature sensors, humidity sensors, and weather sensors. These sensors work in conjunction with data loggers to transmit information to the server.

[0490] Simultaneously, cameras installed at the store entrance and inside the store are used as a means of acquiring image information to collect visitor information. This captures the number of visitors and their behavior patterns, which are then transmitted to the server in real time. The server stores the acquired environmental information and visitor information in a structured database. Here, MySQL, a relational database management system, is used.

[0491] The server performs analysis and demand forecasting using Python scripts and data analysis software including SciKit-Learn and TensorFlow. Demand forecasting is performed using time series analysis and machine learning algorithms. The analysis results are displayed via terminals using information display devices. This display is done via digital signage and tablet devices, providing staff with real-time inventory information and order quantity suggestions.

[0492] Based on this information, users make necessary decisions and formulate orders for required products and promotional strategies. For example, if increased demand for hot beverages is expected during the winter, the server will make a forecast based on past sales data and suggest the optimal inventory level in advance.

[0493] An example of a prompt for a generating AI model is, "Based on sales data for December over the past three years, predict the demand for hot beverages in the next December." This prompt allows the user to obtain specific predictive data and develop a sales strategy.

[0494] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0495] Step 1:

[0496] The server collects environmental information from multiple sensors. Specifically, temperature and humidity sensors measure the physical conditions around the store and periodically send this data to the server. The input is real-time data from each sensor, which the server stores in a database, converting it into a format usable for future analysis. This process allows for the detection of environmental changes around the store and provides the basic data necessary for subsequent demand forecasting.

[0497] Step 2:

[0498] The server collects visitor information using image information acquisition methods. Cameras installed in the store count the number of visitors and analyze customer behavior patterns, transmitting this data to the server in real time. The input is camera images, and the output is digital information such as the number of visitors and their behavior patterns. The server processes this data using image analysis software to understand visitor trends.

[0499] Step 3:

[0500] The server processes the collected environmental and visitor information and stores it in a database. Input is data from sensors and cameras, and output is structured database entries. MySQL is used for this database, and the data is stored with timestamps. This allows historical information to be referenced and used for subsequent data analysis.

[0501] Step 4:

[0502] The server performs data analysis using a Python program. This program retrieves environmental and visitor information from a database as input and uses machine learning algorithms to forecast demand. The output is the forecast result, which is generated as a graph representing demand fluctuations and as numerical forecast values. Libraries such as SciKit-Learn and TensorFlow are used for the analysis, generating a forecast model based on historical data.

[0503] Step 5:

[0504] The terminal displays analysis results in a user-friendly format for staff. Input is demand forecast data generated by the server, and output is demand forecast information and order suggestions displayed on the terminal's dashboard. The display device is designed to allow staff to instantly grasp inventory status, enabling them to efficiently plan orders.

[0505] Step 6:

[0506] Users make decisions based on the information displayed on their devices. The input is the displayed predictive data, and the output is specific ordering instructions and promotional plans. Using this data, users can effectively implement sales strategies while maintaining optimal inventory levels.

[0507] (Application Example 1)

[0508] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0509] To improve the efficiency of inventory management and sales promotion in retail stores, accurate demand forecasting based on environmental and visitor information is necessary. However, conventional systems lacked methods to properly acquire this data, analyze it in real time, and reflect it in efficient ordering systems and sales promotion measures. As a result, there were challenges such as excess inventory, stockout risks, and inefficient promotional measures, which reduced operational efficiency.

[0510] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0511] In this invention, the server includes multiple measuring device means for acquiring environmental information, image data acquisition means for acquiring visitor information, and analysis means for analyzing the environmental information and visitor information to perform demand forecasting. This enables efficient ordering of goods and optimization of sales promotion measures in stores.

[0512] "Environmental information" refers to data that shows external conditions such as temperature, humidity, and weather inside and outside the store.

[0513] "Measuring devices" refer to sensors and equipment installed to acquire environmental information.

[0514] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0515] "Image data acquisition means" refers to devices that use cameras and image processing technology to collect visitor information.

[0516] "Analysis means" refers to analytical devices and software used to predict demand based on collected environmental and visitor information.

[0517] "Goods" refers to merchandise or products sold in stores.

[0518] "Ordering method" refers to equipment or software that automatically orders necessary goods based on demand forecasts.

[0519] "Store operation information" refers to information regarding the store's inventory status and sales activities.

[0520] "Display means" refers to display devices or interfaces that visually provide analysis results and store operation information.

[0521] "Sales promotion measures" are strategic activities aimed at stimulating customer purchasing intent and boosting sales.

[0522] In this invention, a server installed in the store plays a central role. The server uses multiple measuring devices to acquire environmental information. These measuring devices include temperature and humidity sensors and weather sensors. This information is acquired in real time and stored in a database. Visitor information is collected using image data acquisition means, i.e., cameras installed in the store, and transmitted to the server.

[0523] The server uses analysis tools such as Python and TensorFlow to analyze this information. These tools generate multiple forecasting models based on a combination of historical and real-time data to predict demand. These forecasting models enable the prediction of demand for goods and products, allowing for timely ordering of items. This information is displayed as part of the store's operational information on display devices, specifically in-store terminals and staff mobile devices.

[0524] The terminal displays the analysis results, allowing store staff to quickly implement inventory management and sales promotion strategies based on this information. For example, if specific weather conditions are predicted, strategies to promote related products will be displayed on the screen. One practical application is a function that predicts increased demand for umbrellas during the rainy season and optimizes inventory accordingly.

[0525] Examples of prompts to input into a generative AI model are as follows:

[0526] "Based on the forecast for umbrella demand during the rainy season, please propose the optimal promotional strategy."

[0527] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0528] Step 1:

[0529] The server acquires environmental information from temperature, humidity, and weather sensors installed inside and outside the store. The input is sensor data, and the output is continuously updated environmental information data. The acquired data is stored in a database. This operation allows for real-time monitoring of weather conditions around the store.

[0530] Step 2:

[0531] The server acquires visitor information using cameras installed in the store. Specifically, it uses image processing technology to identify the number of customers and their behavioral patterns. The input is image data from the cameras, and the output is visitor information data. This operation provides basic data for analyzing the characteristics and trends of customers visiting the store.

[0532] Step 3:

[0533] The server analyzes collected environmental and visitor information. Machine learning algorithms using Python and TensorFlow are employed for the analysis. The input is information from a stored database, and the output is a forecast based on a demand forecasting model. This operation improves the accuracy of demand forecasting and makes it possible to predict future sales trends.

[0534] Step 4:

[0535] The server executes an automated process for ordering goods based on the prediction results. The input is the output of the prediction model, and the output is an optimized order list. This operation reduces the risk of stockouts and excess inventory and helps maintain an appropriate supply of goods.

[0536] Step 5:

[0537] The terminal displays forecast results and order information received from the server to the store staff. Inputs are order lists and demand forecast data from the server, and output is visualized store management information. This allows staff to understand the work situation in real time and respond quickly.

[0538] Step 6:

[0539] Users refer to the information displayed on their terminal and make necessary approvals or corrections. Input is the displayed store management information, and output is the approved order details or the revised sales plan. This process enables efficient inventory management and sales strategies.

[0540] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0541] This invention provides a system that enables more sophisticated store operations by recognizing the emotions of customers, in addition to forecasting demand from environmental and visitor data. By incorporating an emotion engine, this system grasps the emotional state of customers and optimizes store operations and customer service based on that information.

[0542] The server comprehensively manages environmental data such as temperature, humidity, and weather acquired from various sensor devices, as well as visitor data acquired from image data acquisition devices. In addition, the server also receives emotional data provided by the emotion engine and stores this data in its database.

[0543] The emotion engine analyzes visitors' facial expressions and voices to identify their emotional state (joy, anger, surprise, anxiety, etc.). This emotional data is then transmitted to a server. The analysis device uses this emotional data, in addition to conventional data, to more accurately predict visitors' purchasing intent and preferences, and to make appropriate product recommendations.

[0544] The terminal provides analyzed emotional data to store staff via a display device. This allows staff to respond according to each customer's emotional state, enabling them to provide more personalized service. The system can also automatically adjust store environment settings (music selection, lighting adjustments, etc.) based on emotions.

[0545] As a concrete example, suppose a visitor enters a store and the emotion engine detects signs of stress from the customer's facial expression. Based on this information, the server sends instructions to the terminal suggesting products with relaxing effects or creating a comfortable environment. Store staff can then use the displayed information to suggest appropriate products to the customer.

[0546] By using this system, stores can provide optimal service tailored to customers' emotions, thereby improving customer satisfaction.

[0547] The following describes the processing flow.

[0548] Step 1:

[0549] The server acquires environmental data such as temperature, humidity, and weather from multiple sensor devices installed in the store at regular intervals and stores it in a database.

[0550] Step 2:

[0551] The server performs facial recognition of visitors through an image data acquisition device, collects data on the number of visitors, their attributes, and behavioral patterns, and stores it in a database.

[0552] Step 3:

[0553] The emotion engine analyzes the visitor's facial expressions and voice to identify emotional states such as joy, anger, surprise, and anxiety, and sends that data to the server.

[0554] Step 4:

[0555] The server integrates and preprocesses the collected environmental data, visitor data, and sentiment data before passing it on to the analysis device. This includes noise reduction and standardization of data formats.

[0556] Step 5:

[0557] The analysis device uses pre-processed data to build a demand forecasting model in combination with historical sales data. It takes sentiment data into account to predict the popularity of specific products and customers' selection intentions.

[0558] Step 6:

[0559] Based on the demand forecast results, the server initiates the ordering process for the necessary goods through the automated ordering system. It generates order information and sends order instructions to the supplier system.

[0560] Step 7:

[0561] The terminal receives demand forecast results and sentiment data from the server, generates a real-time dashboard, and displays it to store staff.

[0562] Step 8:

[0563] The terminal displays alerts and suggestions to store staff based on the customer's emotional state. Specifically, if a customer is seeking relaxation, it provides information suggesting relevant products.

[0564] Step 9:

[0565] Users make decisions regarding customer service and store operations based on the information displayed on their devices, and provide feedback to the system to be used for future improvements.

[0566] (Example 2)

[0567] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0568] Traditional store management systems make it difficult to offer product suggestions and services that take into account the emotions of visitors, resulting in limited improvements in customer satisfaction. Furthermore, the inability to reflect visitors' feelings in real time hinders more personalized service and effective marketing.

[0569] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0570] In this invention, the server includes multiple detection means for acquiring environmental information, video information acquisition means for acquiring visitor information, and emotion recognition means for analyzing the visitor's emotional state and making product suggestions based on that information. This enables personalized and effective product suggestions tailored to the customer's emotions and optimizes store operations.

[0571] "Environmental information" refers to data related to the physical conditions of the store's exterior and interior, such as temperature, humidity, and weather.

[0572] A "detection device" refers to various sensor devices used to acquire environmental information, which allows for real-time monitoring of environmental changes.

[0573] "Visitor information" refers to data on the attributes and trends of customers who visit a store, including the time of visit, the number of people, and their behavioral patterns.

[0574] A "video information acquisition device" refers to cameras and other optical equipment used to acquire visitor information, recording the movements and actions of visitors.

[0575] "Analysis means" refers to system functions that integrate and analyze acquired environmental and visitor information to support business decision-making.

[0576] "Emotion recognition means" refers to technological means for analyzing a visitor's facial expressions and voice to identify their emotional state.

[0577] "Ordering method" refers to a function that automatically places orders for necessary products based on demand forecasts and customer sentiment, thereby optimizing inventory management.

[0578] "Display means" refers to screens, monitors, etc., used to visually present analysis results and store operation information.

[0579] "Store operation information" refers to data related to store operations, such as store performance, market trends, and customer sentiment.

[0580] To implement this invention, a server plays a central role. The server works in conjunction with various sensor devices to collect environmental data such as temperature, humidity, and weather in real time. It also uses a video information acquisition device to acquire image data of visitors. At this time, the server centrally manages the collected data and stores it in a database as environmental information and visitor information.

[0581] Emotion recognition technology utilizes software called an emotion engine. This software leverages deep learning to analyze the visitor's facial expressions and voice data to estimate their emotional state. The emotional data is then sent to a server and stored in a database.

[0582] An AI model will be implemented as an analytical tool. This AI model will analyze environmental information, visitor information, and sentiment data within the server to predict visitors' purchasing intent and preferences. Based on these analysis results, the server will send appropriate product suggestions to the terminals.

[0583] The terminal acts as a display device, showing the analyzed data to store staff. Using this information, store staff can provide personalized service to each visitor. Furthermore, the system can automatically adjust the music and lighting within the store according to the customer's mood.

[0584] For example, if the server recognizes that a visitor's emotional state is "stressed," it can display product suggestions with relaxation effects on the terminal, allowing store staff to make appropriate suggestions to the customer. This allows customers to enjoy their experience in the store with peace of mind, and as a result, it is possible to improve customer satisfaction at the store.

[0585] An example of a prompt message would be: "Please explain how this system analyzes visitors' emotions and optimizes store operations based on that analysis."

[0586] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0587] Step 1:

[0588] The server collects data such as temperature, humidity, and weather using various sensor devices to acquire environmental data. This input data is accumulated on the server and stored in a database as environmental information. The server performs operations such as acquiring data sent from sensors at regular intervals, correcting for abnormal or missing values, and then saving the data.

[0589] Step 2:

[0590] The server acquires image data of visitors using a video information acquisition device. This image data is converted into visitor information and stored in a database. The server analyzes the images and extracts data such as the number of visitors, their movements, and the time they entered the store.

[0591] Step 3:

[0592] The emotion engine generates emotion data by analyzing facial expressions and voices based on acquired visitor image data. Using image and voice data as input, a deep learning model extracts features from this data to estimate the emotional state. The emotion data is then labeled with categories such as "joy," "anger," "surprise," and "anxiety," and sent to the server.

[0593] Step 4:

[0594] The server processes integrated environmental information, visitor information, and sentiment data using an AI model as an analytical tool. This model predicts visitors' purchasing intent and product preferences, and generates analysis results. All integrated data is supplied to the AI ​​model as input, and the analysis results output product purchase recommendations and demand forecasts.

[0595] Step 5:

[0596] Based on the analyzed results, the server sends appropriate product suggestions and instructions to store staff to the terminal. The server formats the analysis results and sends and outputs specific suggestions for optimizing performance (e.g., relaxation products) to the terminal.

[0597] Step 6:

[0598] The terminal displays information sent from the server. Store staff use the information displayed on the terminal to provide personalized service and suggest the most suitable products and services to visitors. This allows visitors to receive services tailored to their emotional state. The terminal uses a display to show the analysis results in an easy-to-read format.

[0599] Step 7:

[0600] The system automatically adjusts the store's music and lighting settings based on emotional state data obtained from the server. This provides the optimal atmosphere according to the visitor's emotional state. Changes to the environment settings are carried out by an automated process based on specific scenarios.

[0601] (Application Example 2)

[0602] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0603] In modern retail operations, it is common practice to forecast demand using environmental and visitor information. However, there is a growing need to consider visitors' emotional states in addition to these factors to provide more personalized and effective customer service. Existing systems do not adequately optimize store operations and customer service based on emotional changes, hindering improvements in customer satisfaction.

[0604] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0605] In this invention, the server includes multiple sensor means for acquiring environmental information, image information acquisition means for acquiring visitor information, analysis means for analyzing environmental information and visitor information and performing demand forecasting, and means for recognizing the emotional state of visitors and optimizing customer service, which includes an emotion analysis engine. This enables advanced store management based on visitor emotion information.

[0606] "Environmental information" refers to data that represents the state of the external environment, and includes various elements such as temperature, humidity, and weather.

[0607] "Sensing means" refers to equipment used to acquire environmental information, and includes devices that measure the physical environment, such as thermometers and hygrometers.

[0608] "Visitor information" refers to data about people who visit a store, and is information obtained through images, audio, and other means.

[0609] "Image information acquisition means" refers to a device used to collect image data of visitors using cameras, video cameras, etc.

[0610] "Analysis means" refers to a device that has the function of performing demand forecasting by analyzing data based on acquired environmental information and visitor information.

[0611] "Demand forecasting" refers to information used to predict customer purchasing choices and product demand, enabling efficient inventory management and sales planning.

[0612] An "ordering device" is a device or system that places orders with suppliers in order to automatically supply goods based on demand forecasts.

[0613] "Display means" refers to devices used to visually present analysis results and store management information, and includes displays and projectors.

[0614] An "emotion analysis engine" is software that analyzes a visitor's facial expressions and voice to identify their emotional state and use that information to optimize customer service.

[0615] "Optimizing customer service" is the process of providing personalized services based on the customer's emotional state in order to improve customer satisfaction.

[0616] The system for carrying out this invention includes multiple sensor devices, an image information acquisition device, an analysis device, an ordering device, a display device, and an emotion analysis engine. A server plays a role in comprehensively managing these hardware and software components.

[0617] Specifically, sensor devices collect environmental information, and image information acquisition devices collect visitor information. A server receives this collected information and uses analysis devices to analyze the environmental information, visitor information, and sentiment data. Software such as Microsoft Azure Cognitive Services or Google Cloud Vision AI can be used for the analysis.

[0618] Based on the analysis results, the server performs demand forecasting and sends ordering instructions for appropriate items to the ordering system. Furthermore, it visually provides the analyzed data to store staff through the display system, instantly conveying the information necessary for customer service.

[0619] For example, when a customer enters a store, a camera captures the customer's facial expression, and a server analyzes that information. If the analysis identifies that the customer is expressing "joy," the server provides guidance to the staff on how to present appropriate products.

[0620] Furthermore, when generating programs, a generation AI model can be used to form prompt statements. For example, the prompt "Generate suggestions for relaxing products to recommend to customers who are feeling stressed" can be input to the system, and the results can be used.

[0621] This system enables the provision of personalized service based on customer emotions, leading to increased efficiency in store operations and improved customer satisfaction.

[0622] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0623] Step 1:

[0624] The sensor device collects environmental information.

[0625] The server acquires environmental information such as temperature, humidity, and weather from multiple sensor devices. This allows detailed environmental data to be input into the server. The server then standardizes this data and temporarily stores it for the next analysis step.

[0626] Step 2:

[0627] The image information acquisition device acquires visitor information.

[0628] The server receives images of visitors transmitted from the camera. Using this image data as input, the server analyzes the visitor's facial expressions using facial recognition software. Audio data is also processed simultaneously as needed to identify the visitor's emotional state. The analyzed emotional data is processed by an emotion analysis engine, and the identified emotional state is output to the server.

[0629] Step 3:

[0630] The analysis tool uses the acquired data to perform demand forecasting.

[0631] The server integrates collected environmental information, visitor information, and sentiment data, and applies a demand forecasting model. This uses machine learning algorithms to predict consumer purchasing behavior. Based on the input data, it outputs a list of items that will be needed in the near future.

[0632] Step 4:

[0633] The system automatically orders the necessary items based on the ordering method.

[0634] The server issues instructions to suppliers to order goods based on demand forecasts. This is done via an e-commerce platform, and order information is output. Specific quantities and items are specified, enabling efficient inventory management.

[0635] Step 5:

[0636] Provide information to staff through display means.

[0637] Users receive analysis results from the display device, including store performance, visitor sentiment, and recommended actions. The display device provides staff with visualized data to quickly personalize customer interactions. Based on the output information, staff can take specific actions.

[0638] Step 6:

[0639] Generates prompt messages and adjusts the system's response.

[0640] The server uses a generative AI model to create prompt messages. For example, it might generate a prompt message such as, "Generate suggestions for relaxing products to recommend to customers who are feeling stressed." Using this prompt as input data, appropriate information and product suggestions are generated and fed back into store operations.

[0641] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0642] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0643] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0644] [Fourth Embodiment]

[0645] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0646] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0647] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0648] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0649] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0650] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0651] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0652] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0653] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0654] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0655] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0656] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0657] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0658] This invention is a system aimed at improving the efficiency of retail operations, automating a series of processes including environmental data collection, visitor analysis, demand forecasting, inventory management, and information display.

[0659] The server first continuously collects environmental data such as temperature, humidity, and weather through multiple sensor devices installed inside and outside the store. In parallel, an image data acquisition device monitors the number of customers visiting the store and their behavior patterns, and transmits this data to the server in real time.

[0660] The server stores the collected data in a database and processes it further using an analysis device. The analysis device uses a combination of historical and current real-time data to run an algorithm that predicts future demand, forecasting when specific products will need to be ordered. This demand forecasting utilizes machine learning techniques to continuously update the model and improve data accuracy.

[0661] The terminal uses analysis results to present inventory management information to store staff. The display shows order quantity suggestions based on demand forecasts, as well as alerts regarding the risks of insufficient or excess inventory. This allows store staff to understand the store's inventory status in real time and make quick decisions.

[0662] Users can use the displayed information to confirm any necessary approvals and develop campaigns and marketing strategies tailored to their specific needs. In particular, optimizing product displays and promotions to reflect demand forecasts can aim to improve customer satisfaction.

[0663] As a concrete example, considering fluctuations in product demand based on season and weather, demand for hot beverages and soups increases during the winter. A server can predict this based on past sales data and secure sufficient inventory in advance. This prevents lost opportunities and maximizes sales.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The server periodically acquires environmental data such as temperature, humidity, and weather from sensor devices placed inside and outside the store and stores it in a database.

[0667] Step 2:

[0668] The server receives data on the number of visitors, their attributes, and their behavioral patterns, captured by the image data acquisition device, and stores it in a database.

[0669] Step 3:

[0670] The server preprocesses the collected environmental and visitor data, removing noise and organizing the necessary information.

[0671] Step 4:

[0672] The server passes the pre-processed data to an analysis device, which then combines it with historical sales data to build a demand forecasting model. This model uses machine learning algorithms to estimate future demand.

[0673] Step 5:

[0674] Based on the results of the demand forecasting model, the server evaluates the inventory status of each product and identifies which products need to be ordered.

[0675] Step 6:

[0676] The server automatically sends order instructions to suppliers via the ordering device for products it determines require ordering. At this time, it generates order information including product name, quantity, and delivery date.

[0677] Step 7:

[0678] The terminal generates a real-time dashboard based on demand forecasts and inventory information provided by the server, and displays it visually to the store manager.

[0679] Step 8:

[0680] The terminal displays an alert and notifies the store manager if there is a risk of insufficient or excessive inventory.

[0681] Step 9:

[0682] Based on the information displayed on the dashboard, users can provide feedback to the system as needed to help improve future models.

[0683] (Example 1)

[0684] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0685] Efficiently forecasting demand and managing inventory in retail operations is crucial for maximizing sales and preventing lost opportunities. However, traditional systems struggle with accurate demand forecasting and rapid inventory management, relying on human judgment and posing a high risk of misfortunes and inventory shortages.

[0686] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0687] In this invention, the server includes a plurality of detector means for acquiring environmental information, an image information acquisition means for acquiring visitor information, and an information processing means for analyzing the environmental information and visitor information and performing demand forecasting. This enables highly accurate demand forecasting based on environmental changes and visitor behavior patterns, and allows for automated product management and efficient inventory control.

[0688] "Environmental information" refers to data about the physical conditions surrounding the store, such as temperature, humidity, and weather.

[0689] A "detector means" is a collection of devices or sensors for measuring and collecting environmental information.

[0690] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0691] "Image information acquisition means" refers to devices such as cameras used to acquire visitor information.

[0692] "Information processing means" refers to a computer device and its software used to analyze collected data and generate information related to demand forecasting and inventory management.

[0693] "Product management means" refers to a device or system that places orders for products and adjusts inventory based on demand forecast results.

[0694] "Information display means" refers to devices such as displays that provide store operation information to staff visually.

[0695] "Store efficiency" is a concept that refers to the utilization of resources and the maximization of profits in store operations.

[0696] "Market trends" refer to information about changes and trends in the market viewed over time.

[0697] This invention is a comprehensive system to support retail operations. The server continuously collects environmental information using multiple sensors installed inside and outside the store. These include temperature sensors, humidity sensors, and weather sensors. These sensors work in conjunction with data loggers to transmit information to the server.

[0698] Simultaneously, cameras installed at the store entrance and inside the store are used as a means of acquiring image information to collect visitor information. This captures the number of visitors and their behavior patterns, which are then transmitted to the server in real time. The server stores the acquired environmental information and visitor information in a structured database. Here, MySQL, a relational database management system, is used.

[0699] The server performs analysis and demand forecasting using Python scripts and data analysis software including SciKit-Learn and TensorFlow. Demand forecasting is performed using time series analysis and machine learning algorithms. The analysis results are displayed via terminals using information display devices. This display is done via digital signage and tablet devices, providing staff with real-time inventory information and order quantity suggestions.

[0700] Based on this information, users make necessary decisions and formulate orders for required products and promotional strategies. For example, if increased demand for hot beverages is expected during the winter, the server will make a forecast based on past sales data and suggest the optimal inventory level in advance.

[0701] An example of a prompt for a generating AI model is, "Based on sales data for December over the past three years, predict the demand for hot beverages in the next December." This prompt allows the user to obtain specific predictive data and develop a sales strategy.

[0702] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0703] Step 1:

[0704] The server collects environmental information from multiple sensors. Specifically, temperature and humidity sensors measure the physical conditions around the store and periodically send this data to the server. The input is real-time data from each sensor, which the server stores in a database, converting it into a format usable for future analysis. This process allows for the detection of environmental changes around the store and provides the basic data necessary for subsequent demand forecasting.

[0705] Step 2:

[0706] The server collects visitor information using image information acquisition methods. Cameras installed in the store count the number of visitors and analyze customer behavior patterns, transmitting this data to the server in real time. The input is camera images, and the output is digital information such as the number of visitors and their behavior patterns. The server processes this data using image analysis software to understand visitor trends.

[0707] Step 3:

[0708] The server processes the collected environmental and visitor information and stores it in a database. Input is data from sensors and cameras, and output is structured database entries. MySQL is used for this database, and the data is stored with timestamps. This allows historical information to be referenced and used for subsequent data analysis.

[0709] Step 4:

[0710] The server performs data analysis using a Python program. This program retrieves environmental and visitor information from a database as input and uses machine learning algorithms to forecast demand. The output is the forecast result, which is generated as a graph representing demand fluctuations and as numerical forecast values. Libraries such as SciKit-Learn and TensorFlow are used for the analysis, generating a forecast model based on historical data.

[0711] Step 5:

[0712] The terminal displays analysis results in a user-friendly format for staff. Input is demand forecast data generated by the server, and output is demand forecast information and order suggestions displayed on the terminal's dashboard. The display device is designed to allow staff to instantly grasp inventory status, enabling them to efficiently plan orders.

[0713] Step 6:

[0714] Users make decisions based on the information displayed on their devices. The input is the displayed predictive data, and the output is specific ordering instructions and promotional plans. Using this data, users can effectively implement sales strategies while maintaining optimal inventory levels.

[0715] (Application Example 1)

[0716] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0717] To improve the efficiency of inventory management and sales promotion in retail stores, accurate demand forecasting based on environmental and visitor information is necessary. However, conventional systems lacked methods to properly acquire this data, analyze it in real time, and reflect it in efficient ordering systems and sales promotion measures. As a result, there were challenges such as excess inventory, stockout risks, and inefficient promotional measures, which reduced operational efficiency.

[0718] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0719] In this invention, the server includes multiple measuring device means for acquiring environmental information, image data acquisition means for acquiring visitor information, and analysis means for analyzing the environmental information and visitor information to perform demand forecasting. This enables efficient ordering of goods and optimization of sales promotion measures in stores.

[0720] "Environmental information" refers to data that shows external conditions such as temperature, humidity, and weather inside and outside the store.

[0721] "Measuring devices" refer to sensors and equipment installed to acquire environmental information.

[0722] "Visitor information" refers to data about the number of customers who visit a store and their behavioral patterns.

[0723] "Image data acquisition means" refers to devices that use cameras and image processing technology to collect visitor information.

[0724] "Analysis means" refers to analytical devices and software used to predict demand based on collected environmental and visitor information.

[0725] "Goods" refers to merchandise or products sold in stores.

[0726] "Ordering method" refers to equipment or software that automatically orders necessary goods based on demand forecasts.

[0727] "Store operation information" refers to information regarding the store's inventory status and sales activities.

[0728] "Display means" refers to display devices or interfaces that visually provide analysis results and store operation information.

[0729] "Sales promotion measures" are strategic activities aimed at stimulating customer purchasing intent and boosting sales.

[0730] In this invention, a server installed in the store plays a central role. The server uses multiple measuring devices to acquire environmental information. These measuring devices include temperature and humidity sensors and weather sensors. This information is acquired in real time and stored in a database. Visitor information is collected using image data acquisition means, i.e., cameras installed in the store, and transmitted to the server.

[0731] The server uses analysis tools such as Python and TensorFlow to analyze this information. These tools generate multiple forecasting models based on a combination of historical and real-time data to predict demand. These forecasting models enable the prediction of demand for goods and products, allowing for timely ordering of items. This information is displayed as part of the store's operational information on display devices, specifically in-store terminals and staff mobile devices.

[0732] The terminal displays the analysis results, allowing store staff to quickly implement inventory management and sales promotion strategies based on this information. For example, if specific weather conditions are predicted, strategies to promote related products will be displayed on the screen. One practical application is a function that predicts increased demand for umbrellas during the rainy season and optimizes inventory accordingly.

[0733] Examples of prompts to input into a generative AI model are as follows:

[0734] "Based on the forecast for umbrella demand during the rainy season, please propose the optimal promotional strategy."

[0735] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0736] Step 1:

[0737] The server acquires environmental information from temperature, humidity, and weather sensors installed inside and outside the store. The input is sensor data, and the output is continuously updated environmental information data. The acquired data is stored in a database. This operation allows for real-time monitoring of weather conditions around the store.

[0738] Step 2:

[0739] The server acquires visitor information using cameras installed in the store. Specifically, it uses image processing technology to identify the number of customers and their behavioral patterns. The input is image data from the cameras, and the output is visitor information data. This operation provides basic data for analyzing the characteristics and trends of customers visiting the store.

[0740] Step 3:

[0741] The server analyzes collected environmental and visitor information. Machine learning algorithms using Python and TensorFlow are employed for the analysis. The input is information from a stored database, and the output is a forecast based on a demand forecasting model. This operation improves the accuracy of demand forecasting and makes it possible to predict future sales trends.

[0742] Step 4:

[0743] The server executes an automated process for ordering goods based on the prediction results. The input is the output of the prediction model, and the output is an optimized order list. This operation reduces the risk of stockouts and excess inventory and helps maintain an appropriate supply of goods.

[0744] Step 5:

[0745] The terminal displays forecast results and order information received from the server to the store staff. Inputs are order lists and demand forecast data from the server, and output is visualized store management information. This allows staff to understand the work situation in real time and respond quickly.

[0746] Step 6:

[0747] Users refer to the information displayed on their terminal and make necessary approvals or corrections. Input is the displayed store management information, and output is the approved order details or the revised sales plan. This process enables efficient inventory management and sales strategies.

[0748] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0749] This invention provides a system that enables more sophisticated store operations by recognizing the emotions of customers, in addition to forecasting demand from environmental and visitor data. By incorporating an emotion engine, this system grasps the emotional state of customers and optimizes store operations and customer service based on that information.

[0750] The server comprehensively manages environmental data such as temperature, humidity, and weather acquired from various sensor devices, as well as visitor data acquired from image data acquisition devices. In addition, the server also receives emotional data provided by the emotion engine and stores this data in its database.

[0751] The emotion engine analyzes visitors' facial expressions and voices to identify their emotional state (joy, anger, surprise, anxiety, etc.). This emotional data is then transmitted to a server. The analysis device uses this emotional data, in addition to conventional data, to more accurately predict visitors' purchasing intent and preferences, and to make appropriate product recommendations.

[0752] The terminal provides analyzed emotional data to store staff via a display device. This allows staff to respond according to each customer's emotional state, enabling them to provide more personalized service. The system can also automatically adjust store environment settings (music selection, lighting adjustments, etc.) based on emotions.

[0753] As a concrete example, suppose a visitor enters a store and the emotion engine detects signs of stress from the customer's facial expression. Based on this information, the server sends instructions to the terminal suggesting products with relaxing effects or creating a comfortable environment. Store staff can then use the displayed information to suggest appropriate products to the customer.

[0754] By using this system, stores can provide optimal service tailored to customers' emotions, thereby improving customer satisfaction.

[0755] The following describes the processing flow.

[0756] Step 1:

[0757] The server acquires environmental data such as temperature, humidity, and weather from multiple sensor devices installed in the store at regular intervals and stores it in a database.

[0758] Step 2:

[0759] The server performs facial recognition of visitors through an image data acquisition device, collects data on the number of visitors, their attributes, and behavioral patterns, and stores it in a database.

[0760] Step 3:

[0761] The emotion engine analyzes the visitor's facial expressions and voice to identify emotional states such as joy, anger, surprise, and anxiety, and sends that data to the server.

[0762] Step 4:

[0763] The server integrates and preprocesses the collected environmental data, visitor data, and sentiment data before passing it on to the analysis device. This includes noise reduction and standardization of data formats.

[0764] Step 5:

[0765] The analysis device uses pre-processed data to build a demand forecasting model in combination with historical sales data. It takes sentiment data into account to predict the popularity of specific products and customers' selection intentions.

[0766] Step 6:

[0767] Based on the demand forecast results, the server initiates the ordering process for the necessary goods through the automated ordering system. It generates order information and sends order instructions to the supplier system.

[0768] Step 7:

[0769] The terminal receives demand forecast results and sentiment data from the server, generates a real-time dashboard, and displays it to store staff.

[0770] Step 8:

[0771] The terminal displays alerts and suggestions to store staff based on the customer's emotional state. Specifically, if a customer is seeking relaxation, it provides information suggesting relevant products.

[0772] Step 9:

[0773] Users make decisions regarding customer service and store operations based on the information displayed on their devices, and provide feedback to the system to be used for future improvements.

[0774] (Example 2)

[0775] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0776] Traditional store management systems make it difficult to offer product suggestions and services that take into account the emotions of visitors, resulting in limited improvements in customer satisfaction. Furthermore, the inability to reflect visitors' feelings in real time hinders more personalized service and effective marketing.

[0777] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0778] In this invention, the server includes multiple detection means for acquiring environmental information, video information acquisition means for acquiring visitor information, and emotion recognition means for analyzing the visitor's emotional state and making product suggestions based on that information. This enables personalized and effective product suggestions tailored to the customer's emotions and optimizes store operations.

[0779] "Environmental information" refers to data related to the physical conditions of the store's exterior and interior, such as temperature, humidity, and weather.

[0780] A "detection device" refers to various sensor devices used to acquire environmental information, which allows for real-time monitoring of environmental changes.

[0781] "Visitor information" refers to data on the attributes and trends of customers who visit a store, including the time of visit, the number of people, and their behavioral patterns.

[0782] A "video information acquisition device" refers to cameras and other optical equipment used to acquire visitor information, recording the movements and actions of visitors.

[0783] "Analysis means" refers to system functions that integrate and analyze acquired environmental and visitor information to support business decision-making.

[0784] "Emotion recognition means" refers to technological means for analyzing a visitor's facial expressions and voice to identify their emotional state.

[0785] "Ordering method" refers to a function that automatically places orders for necessary products based on demand forecasts and customer sentiment, thereby optimizing inventory management.

[0786] "Display means" refers to screens, monitors, etc., used to visually present analysis results and store operation information.

[0787] "Store operation information" refers to data related to store operations, such as store performance, market trends, and customer sentiment.

[0788] To implement this invention, a server plays a central role. The server works in conjunction with various sensor devices to collect environmental data such as temperature, humidity, and weather in real time. It also uses a video information acquisition device to acquire image data of visitors. At this time, the server centrally manages the collected data and stores it in a database as environmental information and visitor information.

[0789] Emotion recognition technology utilizes software called an emotion engine. This software leverages deep learning to analyze the visitor's facial expressions and voice data to estimate their emotional state. The emotional data is then sent to a server and stored in a database.

[0790] An AI model will be implemented as an analytical tool. This AI model will analyze environmental information, visitor information, and sentiment data within the server to predict visitors' purchasing intent and preferences. Based on these analysis results, the server will send appropriate product suggestions to the terminals.

[0791] The terminal acts as a display device, showing the analyzed data to store staff. Using this information, store staff can provide personalized service to each visitor. Furthermore, the system can automatically adjust the music and lighting within the store according to the customer's mood.

[0792] For example, if the server recognizes that a visitor's emotional state is "stressed," it can display product suggestions with relaxation effects on the terminal, allowing store staff to make appropriate suggestions to the customer. This allows customers to enjoy their experience in the store with peace of mind, and as a result, it is possible to improve customer satisfaction at the store.

[0793] An example of a prompt message would be: "Please explain how this system analyzes visitors' emotions and optimizes store operations based on that analysis."

[0794] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0795] Step 1:

[0796] The server collects data such as temperature, humidity, and weather using various sensor devices to acquire environmental data. This input data is accumulated on the server and stored in a database as environmental information. The server performs operations such as acquiring data sent from sensors at regular intervals, correcting for abnormal or missing values, and then saving the data.

[0797] Step 2:

[0798] The server acquires image data of visitors using a video information acquisition device. This image data is converted into visitor information and stored in a database. The server analyzes the images and extracts data such as the number of visitors, their movements, and the time they entered the store.

[0799] Step 3:

[0800] The emotion engine generates emotion data by analyzing facial expressions and voices based on acquired visitor image data. Using image and voice data as input, a deep learning model extracts features from this data to estimate the emotional state. The emotion data is then labeled with categories such as "joy," "anger," "surprise," and "anxiety," and sent to the server.

[0801] Step 4:

[0802] The server processes integrated environmental information, visitor information, and sentiment data using an AI model as an analytical tool. This model predicts visitors' purchasing intent and product preferences, and generates analysis results. All integrated data is supplied to the AI ​​model as input, and the analysis results output product purchase recommendations and demand forecasts.

[0803] Step 5:

[0804] Based on the analyzed results, the server sends appropriate product suggestions and instructions to store staff to the terminal. The server formats the analysis results and sends and outputs specific suggestions for optimizing performance (e.g., relaxation products) to the terminal.

[0805] Step 6:

[0806] The terminal displays information sent from the server. Store staff use the information displayed on the terminal to provide personalized service and suggest the most suitable products and services to visitors. This allows visitors to receive services tailored to their emotional state. The terminal uses a display to show the analysis results in an easy-to-read format.

[0807] Step 7:

[0808] The system automatically adjusts the store's music and lighting settings based on emotional state data obtained from the server. This provides the optimal atmosphere according to the visitor's emotional state. Changes to the environment settings are carried out by an automated process based on specific scenarios.

[0809] (Application Example 2)

[0810] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0811] In modern retail operations, it is common practice to forecast demand using environmental and visitor information. However, there is a growing need to consider visitors' emotional states in addition to these factors to provide more personalized and effective customer service. Existing systems do not adequately optimize store operations and customer service based on emotional changes, hindering improvements in customer satisfaction.

[0812] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0813] In this invention, the server includes multiple sensor means for acquiring environmental information, image information acquisition means for acquiring visitor information, analysis means for analyzing environmental information and visitor information and performing demand forecasting, and means for recognizing the emotional state of visitors and optimizing customer service, which includes an emotion analysis engine. This enables advanced store management based on visitor emotion information.

[0814] "Environmental information" refers to data that represents the state of the external environment, and includes various elements such as temperature, humidity, and weather.

[0815] "Sensing means" refers to equipment used to acquire environmental information, and includes devices that measure the physical environment, such as thermometers and hygrometers.

[0816] "Visitor information" refers to data about people who visit a store, and is information obtained through images, audio, and other means.

[0817] "Image information acquisition means" refers to a device used to collect image data of visitors using cameras, video cameras, etc.

[0818] "Analysis means" refers to a device that has the function of performing demand forecasting by analyzing data based on acquired environmental information and visitor information.

[0819] "Demand forecasting" refers to information used to predict customer purchasing choices and product demand, enabling efficient inventory management and sales planning.

[0820] An "ordering device" is a device or system that places orders with suppliers in order to automatically supply goods based on demand forecasts.

[0821] "Display means" refers to devices used to visually present analysis results and store management information, and includes displays and projectors.

[0822] An "emotion analysis engine" is software that analyzes a visitor's facial expressions and voice to identify their emotional state and use that information to optimize customer service.

[0823] "Optimizing customer service" is the process of providing personalized services based on the customer's emotional state in order to improve customer satisfaction.

[0824] The system for carrying out this invention includes multiple sensor devices, an image information acquisition device, an analysis device, an ordering device, a display device, and an emotion analysis engine. A server plays a role in comprehensively managing these hardware and software components.

[0825] Specifically, sensor devices collect environmental information, and image information acquisition devices collect visitor information. A server receives this collected information and uses analysis devices to analyze the environmental information, visitor information, and sentiment data. Software such as Microsoft Azure Cognitive Services or Google Cloud Vision AI can be used for the analysis.

[0826] Based on the analysis results, the server performs demand forecasting and sends ordering instructions for appropriate items to the ordering system. Furthermore, it visually provides the analyzed data to store staff through the display system, instantly conveying the information necessary for customer service.

[0827] For example, when a customer enters a store, a camera captures the customer's facial expression, and a server analyzes that information. If the analysis identifies that the customer is expressing "joy," the server provides guidance to the staff on how to present appropriate products.

[0828] Furthermore, when generating programs, a generation AI model can be used to form prompt statements. For example, the prompt "Generate suggestions for relaxing products to recommend to customers who are feeling stressed" can be input to the system, and the results can be used.

[0829] This system enables the provision of personalized service based on customer emotions, leading to increased efficiency in store operations and improved customer satisfaction.

[0830] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0831] Step 1:

[0832] The sensor device collects environmental information.

[0833] The server acquires environmental information such as temperature, humidity, and weather from multiple sensor devices. This allows detailed environmental data to be input into the server. The server then standardizes this data and temporarily stores it for the next analysis step.

[0834] Step 2:

[0835] The image information acquisition device acquires visitor information.

[0836] The server receives images of visitors transmitted from the camera. Using this image data as input, the server analyzes the visitor's facial expressions using facial recognition software. Audio data is also processed simultaneously as needed to identify the visitor's emotional state. The analyzed emotional data is processed by an emotion analysis engine, and the identified emotional state is output to the server.

[0837] Step 3:

[0838] The analysis tool uses the acquired data to perform demand forecasting.

[0839] The server integrates collected environmental information, visitor information, and sentiment data, and applies a demand forecasting model. This uses machine learning algorithms to predict consumer purchasing behavior. Based on the input data, it outputs a list of items that will be needed in the near future.

[0840] Step 4:

[0841] The system automatically orders the necessary items based on the ordering method.

[0842] The server issues instructions to suppliers to order goods based on demand forecasts. This is done via an e-commerce platform, and order information is output. Specific quantities and items are specified, enabling efficient inventory management.

[0843] Step 5:

[0844] Provide information to staff through display means.

[0845] Users receive analysis results from the display device, including store performance, visitor sentiment, and recommended actions. The display device provides staff with visualized data to quickly personalize customer interactions. Based on the output information, staff can take specific actions.

[0846] Step 6:

[0847] Generates prompt messages and adjusts the system's response.

[0848] The server uses a generative AI model to create prompt messages. For example, it might generate a prompt message such as, "Generate suggestions for relaxing products to recommend to customers who are feeling stressed." Using this prompt as input data, appropriate information and product suggestions are generated and fed back into store operations.

[0849] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0850] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0851] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0852] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0853] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0854] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0855] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0856] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0857] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0858] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0859] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0860] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0861] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0862] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0863] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0864] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0865] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0866] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0867] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0868] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0869] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0870] The following is further disclosed regarding the embodiments described above.

[0871] (Claim 1)

[0872] Multiple sensor devices for acquiring environmental data,

[0873] An image data acquisition device for obtaining visitor data,

[0874] An analysis device that analyzes the aforementioned environmental data and visitor data to perform demand forecasting,

[0875] An ordering device that automatically places orders for goods based on the aforementioned demand forecast,

[0876] A display device that visualizes store management information,

[0877] A system that includes this.

[0878] (Claim 2)

[0879] The system according to claim 1, wherein the analysis device constructs multiple predictive models based on environmental data and visitor data, and makes product suggestions based on these models.

[0880] (Claim 3)

[0881] The system according to claim 1, wherein the display device provides a report of store performance and market trends generated by the analysis device.

[0882] "Example 1"

[0883] (Claim 1)

[0884] Multiple detector means for acquiring environmental information,

[0885] A means for acquiring image information to obtain visitor information,

[0886] An information processing means that analyzes the aforementioned environmental information and visitor information to perform demand forecasting,

[0887] A product management means that automatically places orders for products based on the aforementioned demand forecast,

[0888] A means of displaying information to visualize store operation information,

[0889] The aforementioned information processing means includes means for presenting inventory status based on predictive data,

[0890] A system that includes this.

[0891] (Claim 2)

[0892] The system according to claim 1, wherein the information processing means constructs multiple predictive models based on environmental information and visitor information, continuously updates the models using machine learning techniques, and makes product suggestions.

[0893] (Claim 3)

[0894] The system according to claim 1, wherein the information display means provides a report of store efficiency and market trends generated by the information processing means.

[0895] "Application Example 1"

[0896] (Claim 1)

[0897] Multiple measuring devices for acquiring environmental information,

[0898] A means for acquiring image data to obtain visitor information,

[0899] An analytical means for analyzing the aforementioned environmental information and visitor information to perform demand forecasting,

[0900] A means for automatically ordering goods based on the aforementioned demand forecast,

[0901] Means for optimizing sales promotion measures,

[0902] A display method for visualizing store operation information,

[0903] A system that includes this.

[0904] (Claim 2)

[0905] The system according to claim 1, wherein the analysis means constructs multiple predictive models based on environmental information and visitor information, and makes suggestions to store staff regarding ordering goods and sales promotion based on these models.

[0906] (Claim 3)

[0907] The system according to claim 1, wherein the display means provides a report of store operation performance and market trends generated by the analysis means.

[0908] "Example 2 of combining an emotion engine"

[0909] (Claim 1)

[0910] Multiple detection devices for acquiring environmental information,

[0911] A video information acquisition device for obtaining visitor information,

[0912] An analytical means for analyzing the aforementioned environmental information and visitor information to perform demand forecasting,

[0913] An emotion recognition method that analyzes the emotional state of visitors and makes product suggestions based on that information,

[0914] An ordering means that automatically places orders for goods based on the aforementioned demand forecast and emotional state,

[0915] A display method for visualizing store operation information,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, wherein the analysis means constructs multiple predictive models based on environmental information, visitor information, and emotional information, and makes product suggestions based on these models.

[0919] (Claim 3)

[0920] The system according to claim 1, wherein the display means provides information on store performance, market trends, and customer emotional states generated by the analysis means.

[0921] "Application example 2 when combining with an emotional engine"

[0922] (Claim 1)

[0923] Multiple sensor means for acquiring environmental information,

[0924] A means for acquiring image information to obtain visitor information,

[0925] An analytical means for analyzing the aforementioned environmental information and visitor information and performing demand forecasting,

[0926] An ordering means that automatically places orders for goods based on the aforementioned demand forecast,

[0927] A display method for visualizing store management information,

[0928] Equipped with an emotion analysis engine, it provides a means to recognize the emotional state of visitors and optimize customer service,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, wherein the analysis means constructs a plurality of predictive models based on environmental information, visitor information, and sentiment data, and makes product suggestions based on these models.

[0932] (Claim 3)

[0933] The system according to claim 1, wherein the display means provides a report of store performance and market trends generated by the analysis means, and further provides response guidelines based on emotional state. [Explanation of symbols]

[0934] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Multiple sensor devices for acquiring environmental data, An image data acquisition device for obtaining visitor data, An analysis device that analyzes the aforementioned environmental data and visitor data to perform demand forecasting, An ordering device that automatically places orders for goods based on the aforementioned demand forecast, A display device that visualizes store management information, A system that includes this.

2. The system according to claim 1, wherein the analysis device constructs multiple predictive models based on environmental data and visitor data, and makes product suggestions based on these models.

3. The system according to claim 1, wherein the display device provides a report of store performance and market trends generated by the analysis device.

Images