system

Abstract

We provide the system. [Solution] A detection means for collecting environmental information, Measurement means for analyzing user information, A calculation means for predicting demand based on the aforementioned environmental information and user information, An ordering means that automatically purchases goods based on the aforementioned demand, A visualization means for displaying information on the aforementioned articles and demands, A notification mechanism for providing personalized purchase information to users, 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, it is difficult to accurately predict fluctuations in demand, and there are problems such as overstocking or understocking in inventory management. In addition, it is difficult to quickly analyze the purchasing tendencies of users and appropriately reflect the impact of the environment on sales, and the shortage of human resources has become an issue. In such a situation, it is required to achieve both efficient store operations and high customer satisfaction.

Means for Solving the Problems

[0005] This invention achieves accurate and efficient inventory management by providing detection means for collecting environmental information, measurement means for analyzing user information, and calculation means for predicting demand based on this information. Furthermore, it enables real-time management of store conditions by including ordering means for automatically purchasing goods based on demand forecasts and visualization means for visually displaying the information. In addition, it optimizes sales strategies by providing generation means for generating sales promotion information based on user attributes and creation means for creating reports based on the information.

[0006] "Environmental information" refers to data related to the physical environment, such as ambient temperature, humidity, and weather.

[0007] "Detection means" refers to devices or functions for collecting environmental information.

[0008] "User information" refers to data about customers who visit the store.

[0009] "Measurement means" refers to devices and functions used to acquire and analyze user information.

[0010] "Demand" refers to the expected volume of demand for goods or services over a specific period.

[0011] "Computational means" refers to devices and functions that perform the data processing necessary to forecast demand.

[0012] "Ordering method" refers to the process or function for automatically purchasing goods based on demand forecasts.

[0013] "Visualization means" refers to devices or functions that visually display information in a way that is easy for humans to understand.

[0014] "Generation means" refers to devices or systems for creating sales promotion information based on user attributes.

[0015] "Creation means" refers to a device or function for automatically creating a report based on the collected data.

Brief Description of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It 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 an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a processor with a reference numeral (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.

[0020] In the following embodiments, a RAM (Random Access Memory) with a reference numeral is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a storage with a reference numeral 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, and the like.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention is a system for streamlining inventory management and customer service in retail stores. It primarily combines environmental and user information to predict demand and implement appropriate inventory management and sales promotion. The system operates as follows:

[0038] The server first collects environmental information from multiple IoT sensors installed in the store. For example, it periodically acquires data on temperature, humidity, and weather changes, and stores it in a database. This makes it possible to accurately understand the conditions of the store environment.

[0039] Next, the server acquires user information about customers from cameras using AI technology. The cameras analyze the number of customers, their gender, age group, and behavioral patterns in real time, and use this data to analyze trends in store visits. This information is also stored in the server's database and used for calculations to forecast demand.

[0040] Based on this data, the server executes advanced algorithms to forecast demand. Demand forecasting is performed using a model that combines past sales history, current environment, and user information, enabling highly accurate estimations of future demand. Based on these results, the server automatically places orders for goods through the ordering system. This ensures that optimal inventory levels are always maintained.

[0041] The terminal receives data from the server and visualizes it in a format easily accessible to store staff. Through the dashboard, they can check current inventory levels, customer traffic, and changes in the store environment in real time. This information contributes to improving the efficiency of store operations.

[0042] Furthermore, to implement targeted promotions tailored to user attributes, the server uses generation methods to create appropriate sales promotion information. This allows for the design of effective marketing strategies for specific customer segments.

[0043] As a concrete example, based on data analyzed by the server, additional orders can be automatically placed for products where a surge in demand is predicted. This allows for flexible responses to sudden fluctuations in demand.

[0044] Furthermore, the server automatically generates and delivers reports on store performance to users. This helps in developing long-term strategies based on detailed analysis results for each business day.

[0045] Thus, the system of the present invention efficiently utilizes environmental information and user information to optimize demand forecasting and inventory management, thereby improving operational efficiency and customer satisfaction in the retail industry.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] The server acquires environmental information in real time from IoT sensors installed in the store. This information includes temperature, humidity, and weather, and is recorded in a database. Data collection is performed at regular intervals, making it possible to appropriately understand changes in the environment.

[0049] Step 2:

[0050] The server acquires customer information through AI cameras. From the video data captured by the cameras, the server extracts attribute data such as the number of people, gender, and age group, and further analyzes their movement patterns within the store. This information is stored in a database as user data.

[0051] Step 3:

[0052] The server integrates collected environmental and customer information and uses this to execute a demand forecasting algorithm. This algorithm is designed to predict future demand with high accuracy, including historical sales data. The calculation results are immediately passed to the ordering system.

[0053] Step 4:

[0054] The server automatically orders goods through the ordering system based on the agreed-upon demand forecast. This process includes calculating order quantities to ensure appropriate inventory levels and sending electronic order emails to suppliers.

[0055] Step 5:

[0056] The terminal visualizes inventory status and environmental information received from the server and displays it on a dashboard. Store staff and managers can use this dashboard to check the store's status in real time, enabling quick decision-making.

[0057] Step 6:

[0058] The server uses a generation mechanism to create targeted promotional strategies based on customer attribute information. The generated promotional information is then distributed to customers via digital displays, SMS, email, etc.

[0059] Step 7:

[0060] The server periodically generates performance reports based on store operating data. These reports include sales trend analysis and evaluation of the accuracy of demand forecasts, and are delivered electronically to users. Users can use this information to develop strategic plans.

[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] In the retail industry, there is a growing need for more efficient inventory management and customer service. However, accurately analyzing environmental changes and customer characteristics, and quickly procuring goods and promoting sales based on demand, is challenging. In particular, if retailers cannot respond to rapid changes in demand, inventory shortages or excesses may occur. Given this situation, there is a growing need for systems that effectively utilize environmental and customer information to optimize inventory management and sales strategies.

[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 detection means for collecting environmental parameters, measurement means for analyzing user characteristics, and calculation means for predicting demand based on the environmental parameters and user characteristics. This enables effective automated procurement of goods based on demand and proper inventory management utilizing environmental and customer information.

[0066] "Environmental parameters" refer to data collected by quantitatively measuring factors such as temperature, humidity, illuminance, and weather changes inside and outside the store.

[0067] "Detection means" refers to devices such as sensors and other equipment installed to collect environmental parameters.

[0068] "User characteristics" refers to information such as the number of customers who visited the store, their age group, gender, and behavioral patterns.

[0069] "Measurement means" refers to devices and technologies designed to analyze user characteristics, specifically AI cameras and analysis algorithms.

[0070] "Computation means" refers to a computer program that runs a demand forecasting model and estimates demand based on collected environmental parameters and user characteristics.

[0071] "Means" refers to a set of devices or programs used to achieve a specific purpose.

[0072] "Merchandise" refers to products or items sold to customers in retail stores.

[0073] "Visualization means" refers to software or interfaces used to display data obtained from a server in an easily understandable format.

[0074] "Ordering methods" refer to online systems or APIs for automatically procuring goods based on demand forecasts.

[0075] "Generative means" refers to generative AI models or software used to create effective sales promotion information for specific user groups.

[0076] "Reporting means" refers to a system that automatically generates reports based on product and demand information and distributes them to stakeholders.

[0077] This invention is a system that streamlines inventory management and customer service in retail stores. This system uses multiple hardware and software components to collect environmental parameters and user characteristics, and utilizes this data to perform demand forecasting.

[0078] The server first uses IoT sensors installed within the store to collect environmental parameters. These include sensor devices that measure temperature, humidity, illuminance, and weather changes. This allows for a detailed understanding of the environmental conditions inside and outside the store, and this data is stored in a database on the server.

[0079] Next, the server analyzes the characteristics of customers via the AI ​​camera, obtaining information such as the number of people, age group, gender, and behavioral patterns. The AI ​​technology analyzes the video in real time, and this information is also stored in the database.

[0080] Furthermore, the server performs advanced computational measures to predict demand based on this collected data. Here, machine learning models are used to create predictions that integrate historical sales data with current environmental and customer information. This process enables highly accurate estimation of future demand and the maintenance of optimal inventory levels.

[0081] Automated product procurement is carried out through an ordering system managed by the server. Using an ordering API, products are automatically ordered online based on demand forecasts. This system ensures that inventory is always managed at the appropriate level, reducing the risk of stockouts or excess inventory.

[0082] The terminals serve to provide information to staff based on data sent from the server. A dashboard is provided as a display method, visually presenting inventory status, environmental data, and customer information. For example, it can display graphs showing the remaining stock levels of best-selling products and changes in the number of customers, supporting store operations.

[0083] Furthermore, as a generation method, the server creates targeted promotions for user groups. In this process, it uses a generation AI model and generates sales promotion information by inputting prompts such as the following: "Create promotional text for a new product aimed at women in their 20s." This allows for the development of effective promotional strategies targeting specific customer segments.

[0084] This system allows stores to effectively utilize environmental and user information to improve operational efficiency and customer satisfaction through demand forecasting and inventory management.

[0085] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0086] Step 1:

[0087] The server collects environmental parameters from IoT sensors installed within the store. Specifically, it periodically acquires data such as temperature, humidity, illuminance, and weather using detection methods. The input is data from the sensors, and the output is a database entry where the environmental parameters are stored.

[0088] Step 2:

[0089] The server acquires customer characteristics via an AI camera. The camera analyzes the video in real time, extracting information on the number of people, age group, gender, and behavioral patterns. The input is the camera's video data, and the output is the analysis results regarding customer characteristics.

[0090] Step 3:

[0091] The server integrates environmental parameters and user characteristics and executes computational means to predict demand. This is done using a machine learning model that combines historical sales history with current data. The input is integrated environmental and user data, and the output is the demand forecast result.

[0092] Step 4:

[0093] The server automatically places orders for goods based on demand forecasts. It uses an ordering method to call an external ordering API and place orders for the necessary goods. The input is the demand forecast, and the output is the order data recorded in the order history.

[0094] Step 5:

[0095] The terminal displays data received from the server, visualizing inventory status and customer information on a dashboard. This allows store staff to understand the current situation in real time. The input is data from the server, and the output is visual information on the screen.

[0096] Step 6:

[0097] The server uses a generative AI model to generate sales promotion information based on user groups. In this process, it takes prompt text as input and creates promotional text tailored to the target customer. The input is prompt text assuming a specific customer segment, and the output is the generated promotional text.

[0098] (Application Example 1)

[0099] 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."

[0100] In modern retail stores, proper inventory management and sales promotion are crucial for efficient operations and improved customer satisfaction. However, traditional systems struggle to forecast demand in line with fluctuating environmental conditions and the diverse attributes of customers, resulting in problems such as inventory shortages or excesses, and inefficient promotions.

[0101] 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.

[0102] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand based on the environmental information and user information, and notification means for providing personalized purchasing information to users. This enables real-time analysis of environmental and user information and demand prediction, optimizing inventory management and sales promotion, thereby improving the efficiency of store operations and enhancing customer satisfaction.

[0103] "Environmental information" refers to information about external conditions such as temperature, humidity, and weather changes, which are obtained through detection means.

[0104] "User information" refers to information about customer characteristics such as the number of customers, gender, age group, and behavioral patterns, collected using measurement methods.

[0105] "Predicting demand" means analyzing past sales data, current environmental information, and user information using computational methods to calculate future product demand.

[0106] An "ordering system" is a system that has the function of automatically placing orders for goods with suppliers based on the results of demand forecasts.

[0107] A "visualization method" is an interface that displays information from the server in a way that store staff can easily check.

[0108] A "notification method" is a means of communication that provides users with personalized purchase information in real time.

[0109] "Generation means" refers to means that have a process for generating efficient sales promotion information based on user attributes.

[0110] "Proposal methods" refer to means of making suggestions based on reports on goods and demand information in order to support long-term strategies.

[0111] The system based on this invention aims to improve inventory management and customer satisfaction in retail stores. The system consists of multiple IoT sensors, cameras using AI technology, a server, and user terminals.

[0112] The server collects environmental information such as temperature, humidity, and weather from IoT sensors installed in the store. This allows the store's external conditions to be stored in a database. Cameras using AI technology acquire user information such as the number of customers, gender, age group, and behavioral patterns, and analyze it in real time. The analyzed information is also stored in the server's database.

[0113] The server utilizes machine learning libraries such as TENSORFLOW® and PyTorch to forecast demand based on environmental and user information. The demand forecasting algorithm accurately estimates future demand by considering past sales history, current environmental data, and customer characteristic data. Based on these results, it automatically orders products using an ordering system to maintain optimal inventory levels at all times.

[0114] On the device, users can check real-time promotional information tailored to current inventory status, environmental conditions, and customer attributes via server-side logic using Django or Flask and a frontend built with React Native. Users can receive personalized purchase notifications and use them to guide their future purchasing decisions.

[0115] As a concrete example, if the server detects a sudden change in weather, for example, a sudden rise in temperature, the machine learning model predicts an increase in demand for beverages and immediately places an additional order for the relevant products. It also generates promotional information for specific customers based on past purchase data and notifies them through the app screen. An example of a prompt message using the generating AI model is: "The weather forecast for tomorrow is sunny, and the temperature is expected to exceed 27°C. Based on data from the past 5 years, please predict which beverages will see increased demand."

[0116] In this way, the entire system is expected to optimize the user's purchasing experience and improve store performance.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] The server collects environmental information from IoT sensors installed in the store. Specifically, it acquires data such as temperature, humidity, and weather provided by the sensors and stores this data in the server's database. The input is environmental data from the IoT sensors, and the output is the environmental information stored in the database.

[0120] Step 2:

[0121] The server acquires user information from a camera using AI technology. This camera recognizes the number of customers, their gender, age group, and behavioral patterns, and performs real-time analysis. The input is video data from the camera, and the output is the analyzed user information.

[0122] Step 3:

[0123] The server uses machine learning algorithms to forecast demand based on collected environmental and user information. Historical sales data is also referenced, and TensorFlow or PyTorch are used. The inputs are environmental information, user information, and historical sales data, while the output is the forecasted demand data.

[0124] Step 4:

[0125] The server automatically orders goods using ordering methods based on the demand forecast results. Specifically, it issues instructions to suppliers to order goods according to the predicted demand. The input is the demand forecast results, and the output is the order instruction to the supplier.

[0126] Step 5:

[0127] The terminal displays real-time inventory status and promotional information based on information received from the server. This information is visualized through a user interface built with React Native. The input is inventory and promotional information from the server, and the output is the visual information provided to the user.

[0128] Step 6:

[0129] Users can view real-time information via their devices and reflect it in their purchasing decisions. Furthermore, personalized purchase suggestions are provided to enhance the user experience. The input is the information displayed on the device, and the output is the user's purchasing behavior.

[0130] Step 7:

[0131] The server generates a report based on the above data and makes suggestions for long-term strategic planning for the store. This may involve using a generative AI model to generate prompts and support data analysis. The input is the entire dataset, and the output is strategic suggestions.

[0132] 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.

[0133] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. This system predicts demand by combining environmental information, user information, and user emotion data, and optimizes inventory management and sales promotion based on that prediction.

[0134] The server collects environmental information from IoT sensors installed in the store, including temperature, humidity, and weather. This data is stored in the server's database in real time and is continuously updated.

[0135] Furthermore, the server uses AI-powered cameras to acquire data on customers. The cameras analyze user attribute data such as the number of people, gender, and age group, and also identify behavioral patterns. This information is recorded in a user database and used to forecast demand.

[0136] Furthermore, the server uses an emotion engine to recognize emotions from the customer's facial expressions and voice. This allows it to understand the customer's emotional state and respond accordingly.

[0137] Based on all this data, the server performs demand forecasting. Based on the forecast results, the server automatically places orders and takes proactive measures to maintain optimal inventory levels.

[0138] The terminal uses data retrieved from the server to display current inventory levels, customer sentiment analysis results, and demand forecasts on the in-store dashboard. Store staff can use this information to easily manage operations.

[0139] The emotion engine adjusts sales promotion strategies based on the user's emotions. For example, if a customer shows signs of happiness, it can offer additional incentives. Conversely, if stress or dissatisfaction is detected, it provides information to enable store staff to respond quickly.

[0140] For example, a server could use an emotion engine to recognize a customer's smile and use that as a trigger to offer a coupon for a specific product. This process strengthens personalized strategies and improves customer satisfaction.

[0141] Therefore, this system not only performs demand forecasting and inventory management, but also analyzes customer sentiment and provides an innovative solution that brings about operational improvements that reflect this.

[0142] The following describes the processing flow.

[0143] Step 1:

[0144] The server acquires environmental information from IoT sensors placed in the store. Specifically, it receives temperature, humidity, and weather data from the sensors in real time and stores this information in a database.

[0145] Step 2:

[0146] The server uses AI cameras to collect data on customers. From the camera footage, it analyzes the number of customers, their gender, age group, and behavioral patterns, and records this data in a user database.

[0147] Step 3:

[0148] The server analyzes customers' emotions from their faces and voices through an emotion engine. The recognized emotions are recorded as labels such as "happy," "surprised," and "dissatisfied," and used in each customer engagement strategy.

[0149] Step 4:

[0150] The server integrates collected environmental, user, and sentiment information to run a demand forecasting algorithm. Based on the forecasted data, it calculates the appropriate quantity for the next shipment and initiates the automated ordering process.

[0151] Step 5:

[0152] The terminal updates the dashboard in real time based on data from the server, displaying current inventory status, customer trends, and sentiment analysis results to store staff. Staff use this information to optimize daily operations.

[0153] Step 6:

[0154] Based on sentiment analysis results, the server generates personalized sales promotion information for individual customers and automatically sends coupons and special offers to them. It also adjusts marketing strategies as needed.

[0155] Step 7:

[0156] The server generates reports on the overall operating performance of stores on a daily or weekly basis. These reports include inventory turnover, customer sentiment statistics, and promotional effectiveness, and are sent to users via email. This information serves as a crucial basis for future planning.

[0157] (Example 2)

[0158] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0159] Traditional inventory management systems suffered from low demand forecasting accuracy, leading to problems such as excess inventory and stockouts. Furthermore, they struggled to provide personalized service that reflected customer sentiment and attribute information, limiting the effectiveness of sales promotion measures. As a result, improving customer satisfaction and achieving efficient inventory management remain challenges.

[0160] 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.

[0161] In this invention, the server includes collection means for collecting environmental data, analysis means for analyzing user characteristics, and emotion recognition means for determining emotional states. This enables highly accurate demand forecasting that comprehensively utilizes environmental data, user characteristics, and emotional states, as well as the provision of sales promotion measures tailored to individual users.

[0162] "Collection means" refers to a device or method that has the function of efficiently acquiring environmental data and providing it to a system in real time.

[0163] "Analysis means" refers to a device or method that analyzes user attribute information and derives useful insights through pattern recognition or statistical methods.

[0164] An "emotion recognition tool" is a device or method that identifies an emotional state from inputs such as a user's facial expressions and voice, and utilizes the analysis results.

[0165] A "predictive means" is a device or method that estimates future demand based on collected data and optimizes related resources.

[0166] "Ordering device" refers to a device or method that automatically purchases products to maintain optimal inventory levels based on predicted demand.

[0167] "Display means" refers to a device or method that visually displays collected and analyzed data and provides information in a format that is easily understandable to users.

[0168] "Means of provision" refers to a device or method for generating and effectively communicating sales promotion information based on user characteristics and emotional states.

[0169] "Creation means" refers to a device or method that automatically generates a report based on relevant data and compiles the information in a predetermined format.

[0170] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. The system is configured as follows:

[0171] Server Role

[0172] The server collects environmental data using various sensing technologies installed within the store. This includes IoT sensors to acquire data such as temperature and humidity. This information is stored in the server's database in real time and is constantly updated.

[0173] The server also collects customer data using AI-equipped cameras. These cameras provide data for analyzing customer frequency and movement patterns, and use facial recognition technology to identify gender, age group, and behavioral patterns. This information is stored in a database for use in demand forecasting.

[0174] Furthermore, using an emotion engine, the server analyzes the customer's facial expressions and tone of voice to identify their emotional state. This analysis is then used to generate promotional information aimed at improving customer satisfaction.

[0175] Terminal role

[0176] The terminal displays inventory status and customer sentiment analysis results on digital displays within the store, based on information obtained from the server. This allows store staff to quickly take appropriate action, such as reviewing product placement or adjusting customer service policies.

[0177] Examples

[0178] As a concrete example, a server can use an emotion engine to recognize a customer's smile and automatically issue coupons for specific products based on the results. This process can enhance sales strategies and stimulate customer purchasing intent.

[0179] Example of a prompt

[0180] "Analyze customer behavior patterns using AI cameras, and based on the emotional information recognized by the emotion engine, propose what kind of sales promotion strategies can be applied."

[0181] This system improves store operational efficiency by providing accurate demand forecasts based on collected data, enabling appropriate inventory management and personalized customer experiences.

[0182] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0183] Step 1:

[0184] The server collects environmental data such as temperature and humidity from environmental sensors. This data is input into the server and stored in a database in real time. The server analyzes the collected environmental data to obtain basic information for understanding the current state of the store.

[0185] Step 2:

[0186] The server uses AI cameras to collect data such as the number of users, gender, and age group. This attribute data is used to analyze customer trends and behavioral patterns and is recorded in a user database. Using a generative AI model, the server processes the data based on customer attributes to prepare for future demand forecasting.

[0187] Step 3:

[0188] The server uses an emotion engine to analyze the customer's facial expressions and voice to identify their emotional state. It processes the input facial and voice data to determine whether the customer is happy, surprised, or dissatisfied. This output is used to develop emotion-based response strategies.

[0189] Step 4:

[0190] The server integrates environmental data, customer attribute data, and sentiment data to forecast demand. This data is then fed into an AI model to predict future demand with high accuracy. These forecast results are used for inventory management and automated ordering decisions.

[0191] Step 5:

[0192] The terminal displays demand forecasts and customer sentiment analysis results provided by the server on in-store displays. Store staff refer to this information and receive output to make appropriate customer service decisions and product placement.

[0193] Step 6:

[0194] The server develops individual sales promotion strategies based on the results of sentiment analysis. For example, if a customer is smiling, it automatically issues a specific product coupon and applies the strategy indicated in the prompt message. Through this process, the goal is to improve the customer experience and increase sales.

[0195] (Application Example 2)

[0196] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0197] While retail stores need to optimize inventory management and customer service, traditional systems have struggled to provide real-time demand forecasts and appropriate responses tailored to customer sentiment. Therefore, system improvements are needed to enhance customer satisfaction and boost sales promotion effectiveness.

[0198] 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.

[0199] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand, ordering means for automatically purchasing goods, visualization means for displaying information on goods and demand, recognition means for understanding the emotional state of the user, and extended display means for dynamically displaying information during customer service. This enables real-time demand forecasting and emotion-based customer service in retail stores.

[0200] "Detection means" refers to devices or systems for collecting environmental information, which have the function of understanding conditions such as temperature and humidity.

[0201] "Measurement means" refers to devices or processes for acquiring and analyzing user information, enabling the understanding of the attributes and behavior of customers.

[0202] "Computational means" refers to processes and algorithms that provide a basis for predicting demand based on collected data.

[0203] A "procurement system" is a system that includes a function to automatically purchase goods based on predicted demand.

[0204] "Visualization means" refers to methods and technologies for visually displaying information, such as inventory status and demand forecasts within a store.

[0205] "Recognition means" refers to technologies for understanding the emotional state of a user, such as identifying emotions from facial expressions and voice.

[0206] "Extended display means" refers to devices or software for dynamically displaying information during customer service based on the customer's emotional state.

[0207] The server provides a system to optimize inventory management and customer service in retail stores. First, IoT sensors are used to collect environmental information, gathering data such as temperature, humidity, and weather within the store. This data is transmitted to the server in real time and continuously stored in a database.

[0208] Next, cameras equipped with AI technology acquire information about customers. This includes not only user attributes such as the number of people, gender, and age group, but also their behavioral patterns. This information is then analyzed as data necessary for demand forecasting.

[0209] Furthermore, the server uses an emotion engine to recognize the customer's emotional state from their facial expressions and voice. This allows for analysis of the customer's emotions and is then used to inform sales promotion strategies.

[0210] The server is equipped with a mechanism to forecast demand based on the various data mentioned above and automatically order appropriate items. To maintain optimal inventory levels, these orders are placed in real time. Additionally, terminals are installed in the store, where inventory status, demand forecasts, and customer sentiment analysis results are displayed on a dashboard.

[0211] The terminal displays information such as the customer's emotional state and age group in augmented reality to store employees wearing smart glasses upon arrival. The AR framework used is Vuforia, and the analysis is performed using a system combining TensorFlow and cloud services.

[0212] For example, when the smart glasses recognize the smile of a parent who has come into the store with their child, a prompt will appear saying, "Would you like us to show you our new products for children?" and an appropriate offer can be provided based on this.

[0213] An example of a prompt message is, "Analyze the customer's facial expression data captured by the camera and send their emotional state (joy, dissatisfaction, etc.) to the cloud in real time for analysis." Such a system enables personalized customer service for each individual customer, leading to improved customer satisfaction.

[0214] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0215] Step 1:

[0216] The server acquires environmental data from IoT sensors installed within the store. This includes temperature, humidity, and weather data, which are received directly from the sensors. This data is recorded in a database in real time and prepared for use in demand forecasting using various algorithms.

[0217] Step 2:

[0218] The server uses AI-equipped cameras to collect image data of customers. Camera footage is used as input and is analyzed using image processing technology. After extracting attribute data such as the number of people, gender, and age group, behavioral patterns are identified, and this output data is stored in a database.

[0219] Step 3:

[0220] The server uses an emotion engine to acquire customer facial expressions and voice data as input and recognize their emotional state. Here, voice recognition and facial expression analysis are performed to extract emotional data such as whether the customer is happy or stressed. This data is output and stored in the user database.

[0221] Step 4:

[0222] The server integrates collected environmental information, user attribute data, and emotional state data, and calculates demand using a demand forecasting model. The input includes the aforementioned data, and the forecasting algorithm calculates the next required inventory quantity, sending the result as output to the ordering function.

[0223] Step 5:

[0224] The server automatically places orders based on the demand forecast results. Here, it directly places orders with suppliers for goods according to the predicted demand volume, based on the output of the previous step. As a result, it becomes possible to maintain an optimal inventory level.

[0225] Step 6:

[0226] The terminal displays information about the customer's emotional state and age group on smart glasses worn by the store staff. In this process, customer data sent from the server is output to the glasses' display using an AR framework. Specifically, this involves displaying customer-specific prompts to support customized customer service.

[0227] Step 7:

[0228] The store staff, acting as users, use the information provided by the smart glasses to make appropriate offers and engage in conversations with customers. Prompts may include suggestions such as, "Would you like me to show you our new children's products?", thereby facilitating smooth customer interaction.

[0229] 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.

[0230] Data generation model 58 is a type of 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.

[0231] 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.

[0232] [Second Embodiment]

[0233] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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.

[0244] 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".

[0245] This invention is a system for streamlining inventory management and customer service in retail stores. It primarily combines environmental and user information to predict demand and implement appropriate inventory management and sales promotion. The system operates as follows:

[0246] The server first collects environmental information from multiple IoT sensors installed in the store. For example, it periodically acquires data on temperature, humidity, and weather changes, and stores it in a database. This makes it possible to accurately understand the conditions of the store environment.

[0247] Next, the server acquires user information about customers from cameras using AI technology. The cameras analyze the number of customers, their gender, age group, and behavioral patterns in real time, and use this data to analyze trends in store visits. This information is also stored in the server's database and used for calculations to forecast demand.

[0248] Based on this data, the server executes advanced algorithms to forecast demand. Demand forecasting is performed using a model that combines past sales history, current environment, and user information, enabling highly accurate estimations of future demand. Based on these results, the server automatically places orders for goods through the ordering system. This ensures that optimal inventory levels are always maintained.

[0249] The terminal receives data from the server and visualizes it in a format easily accessible to store staff. Through the dashboard, they can check current inventory levels, customer traffic, and changes in the store environment in real time. This information contributes to improving the efficiency of store operations.

[0250] Furthermore, to implement targeted promotions tailored to user attributes, the server uses generation methods to create appropriate sales promotion information. This allows for the design of effective marketing strategies for specific customer segments.

[0251] As a concrete example, based on data analyzed by the server, additional orders can be automatically placed for products where a surge in demand is predicted. This allows for flexible responses to sudden fluctuations in demand.

[0252] Furthermore, the server automatically generates and delivers reports on store performance to users. This helps in developing long-term strategies based on detailed analysis results for each business day.

[0253] Thus, the system of the present invention efficiently utilizes environmental information and user information to optimize demand forecasting and inventory management, thereby improving operational efficiency and customer satisfaction in the retail industry.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server acquires environmental information in real time from IoT sensors installed in the store. This information includes temperature, humidity, and weather, and is recorded in a database. Data collection is performed at regular intervals, making it possible to appropriately understand changes in the environment.

[0257] Step 2:

[0258] The server acquires customer information through AI cameras. From the video data captured by the cameras, the server extracts attribute data such as the number of people, gender, and age group, and further analyzes their movement patterns within the store. This information is stored in a database as user data.

[0259] Step 3:

[0260] The server integrates collected environmental and customer information and uses this to execute a demand forecasting algorithm. This algorithm is designed to predict future demand with high accuracy, including historical sales data. The calculation results are immediately passed to the ordering system.

[0261] Step 4:

[0262] The server automatically orders goods through the ordering system based on the agreed-upon demand forecast. This process includes calculating order quantities to ensure appropriate inventory levels and sending electronic order emails to suppliers.

[0263] Step 5:

[0264] The terminal visualizes inventory status and environmental information received from the server and displays it on a dashboard. Store staff and managers can use this dashboard to check the store's status in real time, enabling quick decision-making.

[0265] Step 6:

[0266] The server uses a generation mechanism to create targeted promotional strategies based on customer attribute information. The generated promotional information is then distributed to customers via digital displays, SMS, email, etc.

[0267] Step 7:

[0268] The server periodically generates performance reports based on store operating data. These reports include sales trend analysis and evaluation of the accuracy of demand forecasts, and are delivered electronically to users. Users can use this information to develop strategic plans.

[0269] (Example 1)

[0270] 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."

[0271] In the retail industry, there is a growing need for more efficient inventory management and customer service. However, accurately analyzing environmental changes and customer characteristics, and quickly procuring goods and promoting sales based on demand, is challenging. In particular, if retailers cannot respond to rapid changes in demand, inventory shortages or excesses may occur. Given this situation, there is a growing need for systems that effectively utilize environmental and customer information to optimize inventory management and sales strategies.

[0272] 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.

[0273] In this invention, the server includes detection means for collecting environmental parameters, measurement means for analyzing user characteristics, and calculation means for predicting demand based on the environmental parameters and user characteristics. This enables effective automated procurement of goods based on demand and proper inventory management utilizing environmental and customer information.

[0274] "Environmental parameters" refer to data collected by quantitatively measuring factors such as temperature, humidity, illuminance, and weather changes inside and outside the store.

[0275] "Detection means" refers to devices such as sensors and other equipment installed to collect environmental parameters.

[0276] "User characteristics" refers to information such as the number of customers who visited the store, their age group, gender, and behavioral patterns.

[0277] "Measurement means" refers to devices and technologies designed to analyze user characteristics, specifically AI cameras and analysis algorithms.

[0278] "Computation means" refers to a computer program that runs a demand forecasting model and estimates demand based on collected environmental parameters and user characteristics.

[0279] "Means" refers to a set of devices or programs used to achieve a specific purpose.

[0280] "Merchandise" refers to products or items sold to customers in retail stores.

[0281] "Visualization means" refers to software or interfaces used to display data obtained from a server in an easily understandable format.

[0282] "Ordering methods" refer to online systems or APIs for automatically procuring goods based on demand forecasts.

[0283] The "generation means" refers to a generation AI model or software for creating effective sales promotion information for a specific user group.

[0284] The "reporting means" refers to a system for automatically creating a report based on product and demand information and distributing it to stakeholders.

[0285] The present invention is a system for streamlining inventory management and customer service in a retail store. This system uses multiple hardware and software components to collect environmental parameters and user characteristics, and performs demand forecasting using these data.

[0286] First, the server uses IoT sensors installed in the store to collect environmental parameters. This includes sensor devices that measure temperature, humidity, illuminance, and weather changes. This allows for a detailed understanding of the environmental conditions inside and outside the store, and the data is stored in a database within the server.

[0287] Next, the server analyzes the user characteristics of customers visiting the store via an AI camera to obtain the number of people, age group, gender, and behavior patterns. The video is analyzed in real time using AI technology, and this information is also stored in the database.

[0288] Furthermore, the server executes advanced computing means for predicting demand based on these collected data. Here, a machine learning model is used to make a prediction by integrating past sales history and current environmental and customer information. This process enables an accurate estimate of future demand and the maintenance of an optimal inventory level.

[0289] Automatic procurement of products is carried out through the ordering means managed by the server. Using an ordering API, products are automatically ordered online based on demand forecasting. By using this mechanism, inventory is always managed at an appropriate level, reducing the risk of out-of-stock and overstock.

[0290] The terminals serve to provide information to staff based on data sent from the server. A dashboard is provided as a display method, visually presenting inventory status, environmental data, and customer information. For example, it can display graphs showing the remaining stock levels of best-selling products and changes in the number of customers, supporting store operations.

[0291] Furthermore, as a generation method, the server creates targeted promotions for user groups. In this process, it uses a generation AI model and generates sales promotion information by inputting prompts such as the following: "Create promotional text for a new product aimed at women in their 20s." This allows for the development of effective promotional strategies targeting specific customer segments.

[0292] This system allows stores to effectively utilize environmental and user information to improve operational efficiency and customer satisfaction through demand forecasting and inventory management.

[0293] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0294] Step 1:

[0295] The server collects environmental parameters from IoT sensors installed within the store. Specifically, it periodically acquires data such as temperature, humidity, illuminance, and weather using detection methods. The input is data from the sensors, and the output is a database entry where the environmental parameters are stored.

[0296] Step 2:

[0297] The server acquires customer characteristics via an AI camera. The camera analyzes the video in real time, extracting information on the number of people, age group, gender, and behavioral patterns. The input is the camera's video data, and the output is the analysis results regarding customer characteristics.

[0298] Step 3:

[0299] The server integrates environmental parameters and user characteristics and executes computing means for predicting demand. This is executed by a machine learning model that combines past sales history and current data. The input is the integrated environmental and user data, and the output is the demand prediction result.

[0300] Step 4:

[0301] The server automatically places orders for products based on the demand prediction result. Using the order placement means, a process is carried out to call an external order API to order the required products. The input is the demand prediction result, and the output is the order data recorded in the order history.

[0302] Step 5:

[0303] The terminal displays the data received from the server and visualizes inventory status and customer information on the dashboard. This enables store staff to grasp the current situation in real time. The input is the server's data, and the output is the visual information on the screen.

[0304] Step 6:

[0305] The server uses a generative AI model to generate sales promotion information based on user groups. In this process, a prompt sentence is input, and a promotion sentence corresponding to the target customers is created. The input is a prompt sentence assuming a specific customer segment, and the output is the generated promotion sentence.

[0306] (Application Example 1)

[0307] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0308] In modern retail stores, proper inventory management and sales promotion are crucial for efficient operations and improved customer satisfaction. However, traditional systems struggle to forecast demand in line with fluctuating environmental conditions and the diverse attributes of customers, resulting in problems such as inventory shortages or excesses, and inefficient promotions.

[0309] 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.

[0310] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand based on the environmental information and user information, and notification means for providing personalized purchasing information to users. This enables real-time analysis of environmental and user information and demand prediction, optimizing inventory management and sales promotion, thereby improving the efficiency of store operations and enhancing customer satisfaction.

[0311] "Environmental information" refers to information about external conditions such as temperature, humidity, and weather changes, which are obtained through detection means.

[0312] "User information" refers to information about customer characteristics such as the number of customers, gender, age group, and behavioral patterns, collected using measurement methods.

[0313] "Predicting demand" means analyzing past sales data, current environmental information, and user information using computational methods to calculate future product demand.

[0314] An "ordering system" is a system that has the function of automatically placing orders for goods with suppliers based on the results of demand forecasts.

[0315] A "visualization method" is an interface that displays information from the server in a way that store staff can easily check.

[0316] A "notification method" is a means of communication that provides users with personalized purchase information in real time.

[0317] "Generation means" refers to means that have a process for generating efficient sales promotion information based on user attributes.

[0318] "Proposal methods" refer to means of making suggestions based on reports on goods and demand information in order to support long-term strategies.

[0319] The system based on this invention aims to improve inventory management and customer satisfaction in retail stores. The system consists of multiple IoT sensors, cameras using AI technology, a server, and user terminals.

[0320] The server collects environmental information such as temperature, humidity, and weather from IoT sensors installed in the store. This allows the store's external conditions to be stored in a database. Cameras using AI technology acquire user information such as the number of customers, gender, age group, and behavioral patterns, and analyze it in real time. The analyzed information is also stored in the server's database.

[0321] The server utilizes machine learning libraries such as TensorFlow and PyTorch to forecast demand based on environmental and user information. The demand forecasting algorithm accurately estimates future demand by considering past sales history, current environmental data, and customer characteristic data. Based on these results, it automatically orders products using an ordering system to maintain optimal inventory levels at all times.

[0322] On the device, users can check real-time promotional information tailored to current inventory status, environmental conditions, and customer attributes via server-side logic using Django or Flask and a frontend built with React Native. Users can receive personalized purchase notifications and use them to guide their future purchasing decisions.

[0323] As a concrete example, if the server detects a sudden change in weather, for example, a sudden rise in temperature, the machine learning model predicts an increase in demand for beverages and immediately places an additional order for the relevant products. It also generates promotional information for specific customers based on past purchase data and notifies them through the app screen. An example of a prompt message using the generating AI model is: "The weather forecast for tomorrow is sunny, and the temperature is expected to exceed 27°C. Based on data from the past 5 years, please predict which beverages will see increased demand."

[0324] In this way, the entire system is expected to optimize the user's purchasing experience and improve store performance.

[0325] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0326] Step 1:

[0327] The server collects environmental information from IoT sensors installed in the store. Specifically, it acquires data such as temperature, humidity, and weather provided by the sensors and stores this data in the server's database. The input is environmental data from the IoT sensors, and the output is the environmental information stored in the database.

[0328] Step 2:

[0329] The server acquires user information from a camera using AI technology. This camera recognizes the number of customers, their gender, age group, and behavioral patterns, and performs real-time analysis. The input is video data from the camera, and the output is the analyzed user information.

[0330] Step 3:

[0331] The server uses machine learning algorithms to forecast demand based on collected environmental and user information. Historical sales data is also referenced, and TensorFlow or PyTorch are used. The inputs are environmental information, user information, and historical sales data, while the output is the forecasted demand data.

[0332] Step 4:

[0333] The server automatically orders goods using ordering methods based on the demand forecast results. Specifically, it issues instructions to suppliers to order goods according to the predicted demand. The input is the demand forecast results, and the output is the order instruction to the supplier.

[0334] Step 5:

[0335] The terminal displays real-time inventory status and promotional information based on information received from the server. This information is visualized through a user interface built with React Native. The input is inventory and promotional information from the server, and the output is the visual information provided to the user.

[0336] Step 6:

[0337] Users can view real-time information via their devices and reflect it in their purchasing decisions. Furthermore, personalized purchase suggestions are provided to enhance the user experience. The input is the information displayed on the device, and the output is the user's purchasing behavior.

[0338] Step 7:

[0339] The server generates a report based on the above data and makes suggestions for long-term strategic planning for the store. This may involve using a generative AI model to generate prompts and support data analysis. The input is the entire dataset, and the output is strategic suggestions.

[0340] 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.

[0341] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. This system predicts demand by combining environmental information, user information, and user emotion data, and optimizes inventory management and sales promotion based on that prediction.

[0342] The server collects environmental information from IoT sensors installed in the store, including temperature, humidity, and weather. This data is stored in the server's database in real time and is continuously updated.

[0343] Furthermore, the server uses AI-powered cameras to acquire data on customers. The cameras analyze user attribute data such as the number of people, gender, and age group, and also identify behavioral patterns. This information is recorded in a user database and used to forecast demand.

[0344] Furthermore, the server uses an emotion engine to recognize emotions from the customer's facial expressions and voice. This allows it to understand the customer's emotional state and respond accordingly.

[0345] Based on all this data, the server performs demand forecasting. Based on the forecast results, the server automatically places orders and takes proactive measures to maintain optimal inventory levels.

[0346] The terminal uses data retrieved from the server to display current inventory levels, customer sentiment analysis results, and demand forecasts on the in-store dashboard. Store staff can use this information to easily manage operations.

[0347] The emotion engine adjusts sales promotion strategies based on the user's emotions. For example, if a customer shows signs of happiness, it can offer additional incentives. Conversely, if stress or dissatisfaction is detected, it provides information to enable store staff to respond quickly.

[0348] For example, a server could use an emotion engine to recognize a customer's smile and use that as a trigger to offer a coupon for a specific product. This process strengthens personalized strategies and improves customer satisfaction.

[0349] Therefore, this system not only performs demand forecasting and inventory management, but also analyzes customer sentiment and provides an innovative solution that brings about operational improvements that reflect this.

[0350] The following describes the processing flow.

[0351] Step 1:

[0352] The server acquires environmental information from IoT sensors placed in the store. Specifically, it receives temperature, humidity, and weather data from the sensors in real time and stores this information in a database.

[0353] Step 2:

[0354] The server uses AI cameras to collect data on customers. From the camera footage, it analyzes the number of customers, their gender, age group, and behavioral patterns, and records this data in a user database.

[0355] Step 3:

[0356] The server analyzes customers' emotions from their faces and voices through an emotion engine. The recognized emotions are recorded as labels such as "happy," "surprised," and "dissatisfied," and used in each customer engagement strategy.

[0357] Step 4:

[0358] The server integrates collected environmental, user, and sentiment information to run a demand forecasting algorithm. Based on the forecasted data, it calculates the appropriate quantity for the next shipment and initiates the automated ordering process.

[0359] Step 5:

[0360] The terminal updates the dashboard in real time based on data from the server, displaying current inventory status, customer trends, and sentiment analysis results to store staff. Staff use this information to optimize daily operations.

[0361] Step 6:

[0362] Based on sentiment analysis results, the server generates personalized sales promotion information for individual customers and automatically sends coupons and special offers to them. It also adjusts marketing strategies as needed.

[0363] Step 7:

[0364] The server generates reports on the overall operating performance of stores on a daily or weekly basis. These reports include inventory turnover, customer sentiment statistics, and promotional effectiveness, and are sent to users via email. This information serves as a crucial basis for future planning.

[0365] (Example 2)

[0366] 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".

[0367] Traditional inventory management systems suffered from low demand forecasting accuracy, leading to problems such as excess inventory and stockouts. Furthermore, they struggled to provide personalized service that reflected customer sentiment and attribute information, limiting the effectiveness of sales promotion measures. As a result, improving customer satisfaction and achieving efficient inventory management remain challenges.

[0368] 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.

[0369] In this invention, the server includes collection means for collecting environmental data, analysis means for analyzing user characteristics, and emotion recognition means for determining emotional states. This enables highly accurate demand forecasting that comprehensively utilizes environmental data, user characteristics, and emotional states, as well as the provision of sales promotion measures tailored to individual users.

[0370] "Collection means" refers to a device or method that has the function of efficiently acquiring environmental data and providing it to a system in real time.

[0371] "Analysis means" refers to a device or method that analyzes user attribute information and derives useful insights through pattern recognition or statistical methods.

[0372] An "emotion recognition tool" is a device or method that identifies an emotional state from inputs such as a user's facial expressions and voice, and utilizes the analysis results.

[0373] A "predictive means" is a device or method that estimates future demand based on collected data and optimizes related resources.

[0374] "Ordering device" refers to a device or method that automatically purchases products to maintain optimal inventory levels based on predicted demand.

[0375] "Display means" refers to a device or method that visually displays collected and analyzed data and provides information in a format that is easily understandable to users.

[0376] "Means of provision" refers to a device or method for generating and effectively communicating sales promotion information based on user characteristics and emotional states.

[0377] "Creation means" refers to a device or method that automatically generates a report based on relevant data and compiles the information in a predetermined format.

[0378] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. The system is configured as follows:

[0379] Server Role

[0380] The server collects environmental data using various sensing technologies installed within the store. This includes IoT sensors to acquire data such as temperature and humidity. This information is stored in the server's database in real time and is constantly updated.

[0381] The server also collects customer data using AI-equipped cameras. These cameras provide data for analyzing customer frequency and movement patterns, and use facial recognition technology to identify gender, age group, and behavioral patterns. This information is stored in a database for use in demand forecasting.

[0382] Furthermore, using an emotion engine, the server analyzes the customer's facial expressions and tone of voice to identify their emotional state. This analysis is then used to generate promotional information aimed at improving customer satisfaction.

[0383] Terminal role

[0384] The terminal displays inventory status and customer sentiment analysis results on digital displays within the store, based on information obtained from the server. This allows store staff to quickly take appropriate action, such as reviewing product placement or adjusting customer service policies.

[0385] Examples

[0386] As a concrete example, a server can use an emotion engine to recognize a customer's smile and automatically issue coupons for specific products based on the results. This process can enhance sales strategies and stimulate customer purchasing intent.

[0387] Example of a prompt

[0388] "Analyze customer behavior patterns using AI cameras, and based on the emotional information recognized by the emotion engine, propose what kind of sales promotion strategies can be applied."

[0389] This system improves store operational efficiency by providing accurate demand forecasts based on collected data, enabling appropriate inventory management and personalized customer experiences.

[0390] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0391] Step 1:

[0392] The server collects environmental data such as temperature and humidity from environmental sensors. This data is input into the server and stored in a database in real time. The server analyzes the collected environmental data to obtain basic information for understanding the current state of the store.

[0393] Step 2:

[0394] The server uses AI cameras to collect data such as the number of users, gender, and age group. This attribute data is used to analyze customer trends and behavioral patterns and is recorded in a user database. Using a generative AI model, the server processes the data based on customer attributes to prepare for future demand forecasting.

[0395] Step 3:

[0396] The server uses an emotion engine to analyze the customer's facial expressions and voice to identify their emotional state. It processes the input facial and voice data to determine whether the customer is happy, surprised, or dissatisfied. This output is used to develop emotion-based response strategies.

[0397] Step 4:

[0398] The server integrates environmental data, customer attribute data, and sentiment data to forecast demand. This data is then fed into an AI model to predict future demand with high accuracy. These forecast results are used for inventory management and automated ordering decisions.

[0399] Step 5:

[0400] The terminal displays demand forecasts and customer sentiment analysis results provided by the server on in-store displays. Store staff refer to this information and receive output to make appropriate customer service decisions and product placement.

[0401] Step 6:

[0402] The server develops individual sales promotion strategies based on the results of sentiment analysis. For example, if a customer is smiling, it automatically issues a specific product coupon and applies the strategy indicated in the prompt message. Through this process, the goal is to improve the customer experience and increase sales.

[0403] (Application Example 2)

[0404] 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."

[0405] While retail stores need to optimize inventory management and customer service, traditional systems have struggled to provide real-time demand forecasts and appropriate responses tailored to customer sentiment. Therefore, system improvements are needed to enhance customer satisfaction and boost sales promotion effectiveness.

[0406] 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.

[0407] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand, ordering means for automatically purchasing goods, visualization means for displaying information on goods and demand, recognition means for understanding the emotional state of the user, and extended display means for dynamically displaying information during customer service. This enables real-time demand forecasting and emotion-based customer service in retail stores.

[0408] "Detection means" refers to devices or systems for collecting environmental information, which have the function of understanding conditions such as temperature and humidity.

[0409] "Measurement means" refers to devices or processes for acquiring and analyzing user information, enabling the understanding of the attributes and behavior of customers.

[0410] "Computational means" refers to processes and algorithms that provide a basis for predicting demand based on collected data.

[0411] A "procurement system" is a system that includes a function to automatically purchase goods based on predicted demand.

[0412] "Visualization means" refers to methods and technologies for visually displaying information, such as inventory status and demand forecasts within a store.

[0413] "Recognition means" refers to technologies for understanding the emotional state of a user, such as identifying emotions from facial expressions and voice.

[0414] "Extended display means" refers to devices or software for dynamically displaying information during customer service based on the customer's emotional state.

[0415] The server provides a system to optimize inventory management and customer service in retail stores. First, IoT sensors are used to collect environmental information, gathering data such as temperature, humidity, and weather within the store. This data is transmitted to the server in real time and continuously stored in a database.

[0416] Next, cameras equipped with AI technology acquire information about customers. This includes not only user attributes such as the number of people, gender, and age group, but also their behavioral patterns. This information is then analyzed as data necessary for demand forecasting.

[0417] Furthermore, the server uses an emotion engine to recognize the customer's emotional state from their facial expressions and voice. This allows for analysis of the customer's emotions and is then used to inform sales promotion strategies.

[0418] The server is equipped with a mechanism to forecast demand based on the various data mentioned above and automatically order appropriate items. To maintain optimal inventory levels, these orders are placed in real time. Additionally, terminals are installed in the store, where inventory status, demand forecasts, and customer sentiment analysis results are displayed on a dashboard.

[0419] The terminal displays information such as the customer's emotional state and age group in augmented reality to store employees wearing smart glasses upon arrival. The AR framework used is Vuforia, and the analysis is performed using a system combining TensorFlow and cloud services.

[0420] For example, when the smart glasses recognize the smile of a parent who has come into the store with their child, a prompt will appear saying, "Would you like us to show you our new products for children?" and an appropriate offer can be provided based on this.

[0421] An example of a prompt message is, "Analyze the customer's facial expression data captured by the camera and send their emotional state (joy, dissatisfaction, etc.) to the cloud in real time for analysis." Such a system enables personalized customer service for each individual customer, leading to improved customer satisfaction.

[0422] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0423] Step 1:

[0424] The server acquires environmental data from IoT sensors installed within the store. This includes temperature, humidity, and weather data, which are received directly from the sensors. This data is recorded in a database in real time and prepared for use in demand forecasting using various algorithms.

[0425] Step 2:

[0426] The server uses AI-equipped cameras to collect image data of customers. Camera footage is used as input and is analyzed using image processing technology. After extracting attribute data such as the number of people, gender, and age group, behavioral patterns are identified, and this output data is stored in a database.

[0427] Step 3:

[0428] The server uses an emotion engine to acquire customer facial expressions and voice data as input and recognize their emotional state. Here, voice recognition and facial expression analysis are performed to extract emotional data such as whether the customer is happy or stressed. This data is output and stored in the user database.

[0429] Step 4:

[0430] The server integrates collected environmental information, user attribute data, and emotional state data, and calculates demand using a demand forecasting model. The input includes the aforementioned data, and the forecasting algorithm calculates the next required inventory quantity, sending the result as output to the ordering function.

[0431] Step 5:

[0432] The server automatically places orders based on the demand forecast results. Here, it directly places orders with suppliers for goods according to the predicted demand volume, based on the output of the previous step. As a result, it becomes possible to maintain an optimal inventory level.

[0433] Step 6:

[0434] The terminal displays information about the customer's emotional state and age group on smart glasses worn by the store staff. In this process, customer data sent from the server is output to the glasses' display using an AR framework. Specifically, this involves displaying customer-specific prompts to support customized customer service.

[0435] Step 7:

[0436] The store staff, acting as users, use the information provided by the smart glasses to make appropriate offers and engage in conversations with customers. Prompts may include suggestions such as, "Would you like me to show you our new children's products?", thereby facilitating smooth customer interaction.

[0437] 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.

[0438] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0439] 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.

[0440] [Third Embodiment]

[0441] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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.

[0450] 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.

[0451] 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.

[0452] 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".

[0453] This invention is a system for streamlining inventory management and customer service in retail stores. It primarily combines environmental and user information to predict demand and implement appropriate inventory management and sales promotion. The system operates as follows:

[0454] The server first collects environmental information from multiple IoT sensors installed in the store. For example, it periodically acquires data on temperature, humidity, and weather changes, and stores it in a database. This makes it possible to accurately understand the conditions of the store environment.

[0455] Next, the server acquires user information about customers from cameras using AI technology. The cameras analyze the number of customers, their gender, age group, and behavioral patterns in real time, and use this data to analyze trends in store visits. This information is also stored in the server's database and used for calculations to forecast demand.

[0456] Based on this data, the server executes advanced algorithms to forecast demand. Demand forecasting is performed using a model that combines past sales history, current environment, and user information, enabling highly accurate estimations of future demand. Based on these results, the server automatically places orders for goods through the ordering system. This ensures that optimal inventory levels are always maintained.

[0457] The terminal receives data from the server and visualizes it in a format easily accessible to store staff. Through the dashboard, they can check current inventory levels, customer traffic, and changes in the store environment in real time. This information contributes to improving the efficiency of store operations.

[0458] Furthermore, to implement targeted promotions tailored to user attributes, the server uses generation methods to create appropriate sales promotion information. This allows for the design of effective marketing strategies for specific customer segments.

[0459] As a concrete example, based on data analyzed by the server, additional orders can be automatically placed for products where a surge in demand is predicted. This allows for flexible responses to sudden fluctuations in demand.

[0460] Furthermore, the server automatically generates and delivers reports on store performance to users. This helps in developing long-term strategies based on detailed analysis results for each business day.

[0461] Thus, the system of the present invention efficiently utilizes environmental information and user information to optimize demand forecasting and inventory management, thereby improving operational efficiency and customer satisfaction in the retail industry.

[0462] The following describes the processing flow.

[0463] Step 1:

[0464] The server acquires environmental information in real time from IoT sensors installed in the store. This information includes temperature, humidity, and weather, and is recorded in a database. Data collection is performed at regular intervals, making it possible to appropriately understand changes in the environment.

[0465] Step 2:

[0466] The server acquires customer information through AI cameras. From the video data captured by the cameras, the server extracts attribute data such as the number of people, gender, and age group, and further analyzes their movement patterns within the store. This information is stored in a database as user data.

[0467] Step 3:

[0468] The server integrates collected environmental and customer information and uses this to execute a demand forecasting algorithm. This algorithm is designed to predict future demand with high accuracy, including historical sales data. The calculation results are immediately passed to the ordering system.

[0469] Step 4:

[0470] The server automatically orders goods through the ordering system based on the agreed-upon demand forecast. This process includes calculating order quantities to ensure appropriate inventory levels and sending electronic order emails to suppliers.

[0471] Step 5:

[0472] The terminal visualizes inventory status and environmental information received from the server and displays it on a dashboard. Store staff and managers can use this dashboard to check the store's status in real time, enabling quick decision-making.

[0473] Step 6:

[0474] The server uses a generation mechanism to create targeted promotional strategies based on customer attribute information. The generated promotional information is then distributed to customers via digital displays, SMS, email, etc.

[0475] Step 7:

[0476] The server periodically generates performance reports based on store operating data. These reports include sales trend analysis and evaluation of the accuracy of demand forecasts, and are delivered electronically to users. Users can use this information to develop strategic plans.

[0477] (Example 1)

[0478] 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."

[0479] In the retail industry, there is a growing need for more efficient inventory management and customer service. However, accurately analyzing environmental changes and customer characteristics, and quickly procuring goods and promoting sales based on demand, is challenging. In particular, if retailers cannot respond to rapid changes in demand, inventory shortages or excesses may occur. Given this situation, there is a growing need for systems that effectively utilize environmental and customer information to optimize inventory management and sales strategies.

[0480] 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.

[0481] In this invention, the server includes detection means for collecting environmental parameters, measurement means for analyzing user characteristics, and calculation means for predicting demand based on the environmental parameters and user characteristics. This enables effective automated procurement of goods based on demand and proper inventory management utilizing environmental and customer information.

[0482] "Environmental parameters" refer to data collected by quantitatively measuring factors such as temperature, humidity, illuminance, and weather changes inside and outside the store.

[0483] "Detection means" refers to devices such as sensors and other equipment installed to collect environmental parameters.

[0484] "User characteristics" refers to information such as the number of customers who visited the store, their age group, gender, and behavioral patterns.

[0485] "Measurement means" refers to devices and technologies designed to analyze user characteristics, specifically AI cameras and analysis algorithms.

[0486] "Computation means" refers to a computer program that runs a demand forecasting model and estimates demand based on collected environmental parameters and user characteristics.

[0487] "Means" refers to a set of devices or programs used to achieve a specific purpose.

[0488] "Merchandise" refers to products or items sold to customers in retail stores.

[0489] "Visualization means" refers to software or interfaces used to display data obtained from a server in an easily understandable format.

[0490] "Ordering methods" refer to online systems or APIs for automatically procuring goods based on demand forecasts.

[0491] "Generative means" refers to generative AI models or software used to create effective sales promotion information for specific user groups.

[0492] "Reporting means" refers to a system that automatically generates reports based on product and demand information and distributes them to stakeholders.

[0493] This invention is a system that streamlines inventory management and customer service in retail stores. This system uses multiple hardware and software components to collect environmental parameters and user characteristics, and utilizes this data to perform demand forecasting.

[0494] The server first uses IoT sensors installed within the store to collect environmental parameters. These include sensor devices that measure temperature, humidity, illuminance, and weather changes. This allows for a detailed understanding of the environmental conditions inside and outside the store, and this data is stored in a database on the server.

[0495] Next, the server analyzes the characteristics of customers via the AI ​​camera, obtaining information such as the number of people, age group, gender, and behavioral patterns. The AI ​​technology analyzes the video in real time, and this information is also stored in the database.

[0496] Furthermore, the server performs advanced computational measures to predict demand based on this collected data. Here, machine learning models are used to create predictions that integrate historical sales data with current environmental and customer information. This process enables highly accurate estimation of future demand and the maintenance of optimal inventory levels.

[0497] Automated product procurement is carried out through an ordering system managed by the server. Using an ordering API, products are automatically ordered online based on demand forecasts. This system ensures that inventory is always managed at the appropriate level, reducing the risk of stockouts or excess inventory.

[0498] The terminals serve to provide information to staff based on data sent from the server. A dashboard is provided as a display method, visually presenting inventory status, environmental data, and customer information. For example, it can display graphs showing the remaining stock levels of best-selling products and changes in the number of customers, supporting store operations.

[0499] Furthermore, as a generation method, the server creates targeted promotions for user groups. In this process, it uses a generation AI model and generates sales promotion information by inputting prompts such as the following: "Create promotional text for a new product aimed at women in their 20s." This allows for the development of effective promotional strategies targeting specific customer segments.

[0500] This system allows stores to effectively utilize environmental and user information to improve operational efficiency and customer satisfaction through demand forecasting and inventory management.

[0501] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0502] Step 1:

[0503] The server collects environmental parameters from IoT sensors installed within the store. Specifically, it periodically acquires data such as temperature, humidity, illuminance, and weather using detection methods. The input is data from the sensors, and the output is a database entry where the environmental parameters are stored.

[0504] Step 2:

[0505] The server acquires customer characteristics via an AI camera. The camera analyzes the video in real time, extracting information on the number of people, age group, gender, and behavioral patterns. The input is the camera's video data, and the output is the analysis results regarding customer characteristics.

[0506] Step 3:

[0507] The server integrates environmental parameters and user characteristics and executes computational means to predict demand. This is done using a machine learning model that combines historical sales history with current data. The input is integrated environmental and user data, and the output is the demand forecast result.

[0508] Step 4:

[0509] The server automatically places orders for goods based on demand forecasts. It uses an ordering method to call an external ordering API and place orders for the necessary goods. The input is the demand forecast, and the output is the order data recorded in the order history.

[0510] Step 5:

[0511] The terminal displays data received from the server, visualizing inventory status and customer information on a dashboard. This allows store staff to understand the current situation in real time. The input is data from the server, and the output is visual information on the screen.

[0512] Step 6:

[0513] The server uses a generative AI model to generate sales promotion information based on user groups. In this process, it takes prompt text as input and creates promotional text tailored to the target customer. The input is prompt text assuming a specific customer segment, and the output is the generated promotional text.

[0514] (Application Example 1)

[0515] 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."

[0516] In modern retail stores, proper inventory management and sales promotion are crucial for efficient operations and improved customer satisfaction. However, traditional systems struggle to forecast demand in line with fluctuating environmental conditions and the diverse attributes of customers, resulting in problems such as inventory shortages or excesses, and inefficient promotions.

[0517] 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.

[0518] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand based on the environmental information and user information, and notification means for providing personalized purchasing information to users. This enables real-time analysis of environmental and user information and demand prediction, optimizing inventory management and sales promotion, thereby improving the efficiency of store operations and enhancing customer satisfaction.

[0519] "Environmental information" refers to information about external conditions such as temperature, humidity, and weather changes, which are obtained through detection means.

[0520] "User information" refers to information about customer characteristics such as the number of customers, gender, age group, and behavioral patterns, collected using measurement methods.

[0521] "Predicting demand" means analyzing past sales data, current environmental information, and user information using computational methods to calculate future product demand.

[0522] An "ordering system" is a system that has the function of automatically placing orders for goods with suppliers based on the results of demand forecasts.

[0523] A "visualization method" is an interface that displays information from the server in a way that store staff can easily check.

[0524] A "notification method" is a means of communication that provides users with personalized purchase information in real time.

[0525] "Generation means" refers to means that have a process for generating efficient sales promotion information based on user attributes.

[0526] "Proposal methods" refer to means of making suggestions based on reports on goods and demand information in order to support long-term strategies.

[0527] The system based on this invention aims to improve inventory management and customer satisfaction in retail stores. The system consists of multiple IoT sensors, cameras using AI technology, a server, and user terminals.

[0528] The server collects environmental information such as temperature, humidity, and weather from IoT sensors installed in the store. This allows the store's external conditions to be stored in a database. Cameras using AI technology acquire user information such as the number of customers, gender, age group, and behavioral patterns, and analyze it in real time. The analyzed information is also stored in the server's database.

[0529] The server utilizes machine learning libraries such as TensorFlow and PyTorch to forecast demand based on environmental and user information. The demand forecasting algorithm accurately estimates future demand by considering past sales history, current environmental data, and customer characteristic data. Based on these results, it automatically orders products using an ordering system to maintain optimal inventory levels at all times.

[0530] On the device, users can check real-time promotional information tailored to current inventory status, environmental conditions, and customer attributes via server-side logic using Django or Flask and a frontend built with React Native. Users can receive personalized purchase notifications and use them to guide their future purchasing decisions.

[0531] As a concrete example, if the server detects a sudden change in weather, for example, a sudden rise in temperature, the machine learning model predicts an increase in demand for beverages and immediately places an additional order for the relevant products. It also generates promotional information for specific customers based on past purchase data and notifies them through the app screen. An example of a prompt message using the generating AI model is: "The weather forecast for tomorrow is sunny, and the temperature is expected to exceed 27°C. Based on data from the past 5 years, please predict which beverages will see increased demand."

[0532] In this way, the entire system is expected to optimize the user's purchasing experience and improve store performance.

[0533] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0534] Step 1:

[0535] The server collects environmental information from IoT sensors installed in the store. Specifically, it acquires data such as temperature, humidity, and weather provided by the sensors and stores this data in the server's database. The input is environmental data from the IoT sensors, and the output is the environmental information stored in the database.

[0536] Step 2:

[0537] The server acquires user information from a camera using AI technology. This camera recognizes the number of customers, their gender, age group, and behavioral patterns, and performs real-time analysis. The input is video data from the camera, and the output is the analyzed user information.

[0538] Step 3:

[0539] The server uses machine learning algorithms to forecast demand based on collected environmental and user information. Historical sales data is also referenced, and TensorFlow or PyTorch are used. The inputs are environmental information, user information, and historical sales data, while the output is the forecasted demand data.

[0540] Step 4:

[0541] The server automatically orders goods using ordering methods based on the demand forecast results. Specifically, it issues instructions to suppliers to order goods according to the predicted demand. The input is the demand forecast results, and the output is the order instruction to the supplier.

[0542] Step 5:

[0543] The terminal displays real-time inventory status and promotional information based on information received from the server. This information is visualized through a user interface built with React Native. The input is inventory and promotional information from the server, and the output is the visual information provided to the user.

[0544] Step 6:

[0545] Users can view real-time information via their devices and reflect it in their purchasing decisions. Furthermore, personalized purchase suggestions are provided to enhance the user experience. The input is the information displayed on the device, and the output is the user's purchasing behavior.

[0546] Step 7:

[0547] The server generates a report based on the above data and makes suggestions for long-term strategic planning for the store. This may involve using a generative AI model to generate prompts and support data analysis. The input is the entire dataset, and the output is strategic suggestions.

[0548] 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.

[0549] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. This system predicts demand by combining environmental information, user information, and user emotion data, and optimizes inventory management and sales promotion based on that prediction.

[0550] The server collects environmental information from IoT sensors installed in the store, including temperature, humidity, and weather. This data is stored in the server's database in real time and is continuously updated.

[0551] Furthermore, the server uses AI-powered cameras to acquire data on customers. The cameras analyze user attribute data such as the number of people, gender, and age group, and also identify behavioral patterns. This information is recorded in a user database and used to forecast demand.

[0552] Furthermore, the server uses an emotion engine to recognize emotions from the customer's facial expressions and voice. This allows it to understand the customer's emotional state and respond accordingly.

[0553] Based on all this data, the server performs demand forecasting. Based on the forecast results, the server automatically places orders and takes proactive measures to maintain optimal inventory levels.

[0554] The terminal uses data retrieved from the server to display current inventory levels, customer sentiment analysis results, and demand forecasts on the in-store dashboard. Store staff can use this information to easily manage operations.

[0555] The emotion engine adjusts sales promotion strategies based on the user's emotions. For example, if a customer shows signs of happiness, it can offer additional incentives. Conversely, if stress or dissatisfaction is detected, it provides information to enable store staff to respond quickly.

[0556] For example, a server could use an emotion engine to recognize a customer's smile and use that as a trigger to offer a coupon for a specific product. This process strengthens personalized strategies and improves customer satisfaction.

[0557] Therefore, this system not only performs demand forecasting and inventory management, but also analyzes customer sentiment and provides an innovative solution that brings about operational improvements that reflect this.

[0558] The following describes the processing flow.

[0559] Step 1:

[0560] The server acquires environmental information from IoT sensors placed in the store. Specifically, it receives temperature, humidity, and weather data from the sensors in real time and stores this information in a database.

[0561] Step 2:

[0562] The server uses AI cameras to collect data on customers. From the camera footage, it analyzes the number of customers, their gender, age group, and behavioral patterns, and records this data in a user database.

[0563] Step 3:

[0564] The server analyzes customers' emotions from their faces and voices through an emotion engine. The recognized emotions are recorded as labels such as "happy," "surprised," and "dissatisfied," and used in each customer engagement strategy.

[0565] Step 4:

[0566] The server integrates collected environmental, user, and sentiment information to run a demand forecasting algorithm. Based on the forecasted data, it calculates the appropriate quantity for the next shipment and initiates the automated ordering process.

[0567] Step 5:

[0568] The terminal updates the dashboard in real time based on data from the server, displaying current inventory status, customer trends, and sentiment analysis results to store staff. Staff use this information to optimize daily operations.

[0569] Step 6:

[0570] Based on sentiment analysis results, the server generates personalized sales promotion information for individual customers and automatically sends coupons and special offers to them. It also adjusts marketing strategies as needed.

[0571] Step 7:

[0572] The server generates reports on the overall operating performance of stores on a daily or weekly basis. These reports include inventory turnover, customer sentiment statistics, and promotional effectiveness, and are sent to users via email. This information serves as a crucial basis for future planning.

[0573] (Example 2)

[0574] 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."

[0575] Traditional inventory management systems suffered from low demand forecasting accuracy, leading to problems such as excess inventory and stockouts. Furthermore, they struggled to provide personalized service that reflected customer sentiment and attribute information, limiting the effectiveness of sales promotion measures. As a result, improving customer satisfaction and achieving efficient inventory management remain challenges.

[0576] 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.

[0577] In this invention, the server includes collection means for collecting environmental data, analysis means for analyzing user characteristics, and emotion recognition means for determining emotional states. This enables highly accurate demand forecasting that comprehensively utilizes environmental data, user characteristics, and emotional states, as well as the provision of sales promotion measures tailored to individual users.

[0578] "Collection means" refers to a device or method that has the function of efficiently acquiring environmental data and providing it to a system in real time.

[0579] "Analysis means" refers to a device or method that analyzes user attribute information and derives useful insights through pattern recognition or statistical methods.

[0580] An "emotion recognition tool" is a device or method that identifies an emotional state from inputs such as a user's facial expressions and voice, and utilizes the analysis results.

[0581] A "predictive means" is a device or method that estimates future demand based on collected data and optimizes related resources.

[0582] "Ordering device" refers to a device or method that automatically purchases products to maintain optimal inventory levels based on predicted demand.

[0583] "Display means" refers to a device or method that visually displays collected and analyzed data and provides information in a format that is easily understandable to users.

[0584] "Means of provision" refers to a device or method for generating and effectively communicating sales promotion information based on user characteristics and emotional states.

[0585] "Creation means" refers to a device or method that automatically generates a report based on relevant data and compiles the information in a predetermined format.

[0586] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. The system is configured as follows:

[0587] Server Role

[0588] The server collects environmental data using various sensing technologies installed within the store. This includes IoT sensors to acquire data such as temperature and humidity. This information is stored in the server's database in real time and is constantly updated.

[0589] The server also collects customer data using AI-equipped cameras. These cameras provide data for analyzing customer frequency and movement patterns, and use facial recognition technology to identify gender, age group, and behavioral patterns. This information is stored in a database for use in demand forecasting.

[0590] Furthermore, using an emotion engine, the server analyzes the customer's facial expressions and tone of voice to identify their emotional state. This analysis is then used to generate promotional information aimed at improving customer satisfaction.

[0591] Terminal role

[0592] The terminal displays inventory status and customer sentiment analysis results on digital displays within the store, based on information obtained from the server. This allows store staff to quickly take appropriate action, such as reviewing product placement or adjusting customer service policies.

[0593] Examples

[0594] As a concrete example, a server can use an emotion engine to recognize a customer's smile and automatically issue coupons for specific products based on the results. This process can enhance sales strategies and stimulate customer purchasing intent.

[0595] Example of a prompt

[0596] "Analyze customer behavior patterns using AI cameras, and based on the emotional information recognized by the emotion engine, propose what kind of sales promotion strategies can be applied."

[0597] This system improves store operational efficiency by providing accurate demand forecasts based on collected data, enabling appropriate inventory management and personalized customer experiences.

[0598] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0599] Step 1:

[0600] The server collects environmental data such as temperature and humidity from environmental sensors. This data is input into the server and stored in a database in real time. The server analyzes the collected environmental data to obtain basic information for understanding the current state of the store.

[0601] Step 2:

[0602] The server uses AI cameras to collect data such as the number of users, gender, and age group. This attribute data is used to analyze customer trends and behavioral patterns and is recorded in a user database. Using a generative AI model, the server processes the data based on customer attributes to prepare for future demand forecasting.

[0603] Step 3:

[0604] The server uses an emotion engine to analyze the customer's facial expressions and voice to identify their emotional state. It processes the input facial and voice data to determine whether the customer is happy, surprised, or dissatisfied. This output is used to develop emotion-based response strategies.

[0605] Step 4:

[0606] The server integrates environmental data, customer attribute data, and sentiment data to forecast demand. This data is then fed into an AI model to predict future demand with high accuracy. These forecast results are used for inventory management and automated ordering decisions.

[0607] Step 5:

[0608] The terminal displays demand forecasts and customer sentiment analysis results provided by the server on in-store displays. Store staff refer to this information and receive output to make appropriate customer service decisions and product placement.

[0609] Step 6:

[0610] The server develops individual sales promotion strategies based on the results of sentiment analysis. For example, if a customer is smiling, it automatically issues a specific product coupon and applies the strategy indicated in the prompt message. Through this process, the goal is to improve the customer experience and increase sales.

[0611] (Application Example 2)

[0612] 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."

[0613] While retail stores need to optimize inventory management and customer service, traditional systems have struggled to provide real-time demand forecasts and appropriate responses tailored to customer sentiment. Therefore, system improvements are needed to enhance customer satisfaction and boost sales promotion effectiveness.

[0614] 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.

[0615] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand, ordering means for automatically purchasing goods, visualization means for displaying information on goods and demand, recognition means for understanding the emotional state of the user, and extended display means for dynamically displaying information during customer service. This enables real-time demand forecasting and emotion-based customer service in retail stores.

[0616] "Detection means" refers to devices or systems for collecting environmental information, which have the function of understanding conditions such as temperature and humidity.

[0617] "Measurement means" refers to devices or processes for acquiring and analyzing user information, enabling the understanding of the attributes and behavior of customers.

[0618] "Computational means" refers to processes and algorithms that provide a basis for predicting demand based on collected data.

[0619] A "procurement system" is a system that includes a function to automatically purchase goods based on predicted demand.

[0620] "Visualization means" refers to methods and technologies for visually displaying information, such as inventory status and demand forecasts within a store.

[0621] "Recognition means" refers to technologies for understanding the emotional state of a user, such as identifying emotions from facial expressions and voice.

[0622] "Extended display means" refers to devices or software for dynamically displaying information during customer service based on the customer's emotional state.

[0623] The server provides a system to optimize inventory management and customer service in retail stores. First, IoT sensors are used to collect environmental information, gathering data such as temperature, humidity, and weather within the store. This data is transmitted to the server in real time and continuously stored in a database.

[0624] Next, cameras equipped with AI technology acquire information about customers. This includes not only user attributes such as the number of people, gender, and age group, but also their behavioral patterns. This information is then analyzed as data necessary for demand forecasting.

[0625] Furthermore, the server uses an emotion engine to recognize the customer's emotional state from their facial expressions and voice. This allows for analysis of the customer's emotions and is then used to inform sales promotion strategies.

[0626] The server is equipped with a mechanism to forecast demand based on the various data mentioned above and automatically order appropriate items. To maintain optimal inventory levels, these orders are placed in real time. Additionally, terminals are installed in the store, where inventory status, demand forecasts, and customer sentiment analysis results are displayed on a dashboard.

[0627] The terminal displays information such as the customer's emotional state and age group in augmented reality to store employees wearing smart glasses upon arrival. The AR framework used is Vuforia, and the analysis is performed using a system combining TensorFlow and cloud services.

[0628] For example, when the smart glasses recognize the smile of a parent who has come into the store with their child, a prompt will appear saying, "Would you like us to show you our new products for children?" and an appropriate offer can be provided based on this.

[0629] An example of a prompt message is, "Analyze the customer's facial expression data captured by the camera and send their emotional state (joy, dissatisfaction, etc.) to the cloud in real time for analysis." Such a system enables personalized customer service for each individual customer, leading to improved customer satisfaction.

[0630] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0631] Step 1:

[0632] The server acquires environmental data from IoT sensors installed within the store. This includes temperature, humidity, and weather data, which are received directly from the sensors. This data is recorded in a database in real time and prepared for use in demand forecasting using various algorithms.

[0633] Step 2:

[0634] The server uses AI-equipped cameras to collect image data of customers. Camera footage is used as input and is analyzed using image processing technology. After extracting attribute data such as the number of people, gender, and age group, behavioral patterns are identified, and this output data is stored in a database.

[0635] Step 3:

[0636] The server uses an emotion engine to acquire customer facial expressions and voice data as input and recognize their emotional state. Here, voice recognition and facial expression analysis are performed to extract emotional data such as whether the customer is happy or stressed. This data is output and stored in the user database.

[0637] Step 4:

[0638] The server integrates collected environmental information, user attribute data, and emotional state data, and calculates demand using a demand forecasting model. The input includes the aforementioned data, and the forecasting algorithm calculates the next required inventory quantity, sending the result as output to the ordering function.

[0639] Step 5:

[0640] The server automatically places orders based on the demand forecast results. Here, it directly places orders with suppliers for goods according to the predicted demand volume, based on the output of the previous step. As a result, it becomes possible to maintain an optimal inventory level.

[0641] Step 6:

[0642] The terminal displays information about the customer's emotional state and age group on smart glasses worn by the store staff. In this process, customer data sent from the server is output to the glasses' display using an AR framework. Specifically, this involves displaying customer-specific prompts to support customized customer service.

[0643] Step 7:

[0644] The store staff, acting as users, use the information provided by the smart glasses to make appropriate offers and engage in conversations with customers. Prompts may include suggestions such as, "Would you like me to show you our new children's products?", thereby facilitating smooth customer interaction.

[0645] 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.

[0646] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0647] 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.

[0648] [Fourth Embodiment]

[0649] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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).

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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.

[0659] 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.

[0660] 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.

[0661] 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".

[0662] This invention is a system for streamlining inventory management and customer service in retail stores. It primarily combines environmental and user information to predict demand and implement appropriate inventory management and sales promotion. The system operates as follows:

[0663] The server first collects environmental information from multiple IoT sensors installed in the store. For example, it periodically acquires data on temperature, humidity, and weather changes, and stores it in a database. This makes it possible to accurately understand the conditions of the store environment.

[0664] Next, the server acquires user information about customers from cameras using AI technology. The cameras analyze the number of customers, their gender, age group, and behavioral patterns in real time, and use this data to analyze trends in store visits. This information is also stored in the server's database and used for calculations to forecast demand.

[0665] Based on this data, the server executes advanced algorithms to forecast demand. Demand forecasting is performed using a model that combines past sales history, current environment, and user information, enabling highly accurate estimations of future demand. Based on these results, the server automatically places orders for goods through the ordering system. This ensures that optimal inventory levels are always maintained.

[0666] The terminal receives data from the server and visualizes it in a format easily accessible to store staff. Through the dashboard, they can check current inventory levels, customer traffic, and changes in the store environment in real time. This information contributes to improving the efficiency of store operations.

[0667] Furthermore, to implement targeted promotions tailored to user attributes, the server uses generation methods to create appropriate sales promotion information. This allows for the design of effective marketing strategies for specific customer segments.

[0668] As a concrete example, based on data analyzed by the server, additional orders can be automatically placed for products where a surge in demand is predicted. This allows for flexible responses to sudden fluctuations in demand.

[0669] Furthermore, the server automatically generates and delivers reports on store performance to users. This helps in developing long-term strategies based on detailed analysis results for each business day.

[0670] Thus, the system of the present invention efficiently utilizes environmental information and user information to optimize demand forecasting and inventory management, thereby improving operational efficiency and customer satisfaction in the retail industry.

[0671] The following describes the processing flow.

[0672] Step 1:

[0673] The server acquires environmental information in real time from IoT sensors installed in the store. This information includes temperature, humidity, and weather, and is recorded in a database. Data collection is performed at regular intervals, making it possible to appropriately understand changes in the environment.

[0674] Step 2:

[0675] The server acquires customer information through AI cameras. From the video data captured by the cameras, the server extracts attribute data such as the number of people, gender, and age group, and further analyzes their movement patterns within the store. This information is stored in a database as user data.

[0676] Step 3:

[0677] The server integrates collected environmental and customer information and uses this to execute a demand forecasting algorithm. This algorithm is designed to predict future demand with high accuracy, including historical sales data. The calculation results are immediately passed to the ordering system.

[0678] Step 4:

[0679] The server automatically orders goods through the ordering system based on the agreed-upon demand forecast. This process includes calculating order quantities to ensure appropriate inventory levels and sending electronic order emails to suppliers.

[0680] Step 5:

[0681] The terminal visualizes inventory status and environmental information received from the server and displays it on a dashboard. Store staff and managers can use this dashboard to check the store's status in real time, enabling quick decision-making.

[0682] Step 6:

[0683] The server uses a generation mechanism to create targeted promotional strategies based on customer attribute information. The generated promotional information is then distributed to customers via digital displays, SMS, email, etc.

[0684] Step 7:

[0685] The server periodically generates performance reports based on store operating data. These reports include sales trend analysis and evaluation of the accuracy of demand forecasts, and are delivered electronically to users. Users can use this information to develop strategic plans.

[0686] (Example 1)

[0687] 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".

[0688] In the retail industry, there is a growing need for more efficient inventory management and customer service. However, accurately analyzing environmental changes and customer characteristics, and quickly procuring goods and promoting sales based on demand, is challenging. In particular, if retailers cannot respond to rapid changes in demand, inventory shortages or excesses may occur. Given this situation, there is a growing need for systems that effectively utilize environmental and customer information to optimize inventory management and sales strategies.

[0689] 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.

[0690] In this invention, the server includes detection means for collecting environmental parameters, measurement means for analyzing user characteristics, and calculation means for predicting demand based on the environmental parameters and user characteristics. This enables effective automated procurement of goods based on demand and proper inventory management utilizing environmental and customer information.

[0691] "Environmental parameters" refer to data collected by quantitatively measuring factors such as temperature, humidity, illuminance, and weather changes inside and outside the store.

[0692] "Detection means" refers to devices such as sensors and other equipment installed to collect environmental parameters.

[0693] "User characteristics" refers to information such as the number of customers who visited the store, their age group, gender, and behavioral patterns.

[0694] "Measurement means" refers to devices and technologies designed to analyze user characteristics, specifically AI cameras and analysis algorithms.

[0695] "Computation means" refers to a computer program that runs a demand forecasting model and estimates demand based on collected environmental parameters and user characteristics.

[0696] "Means" refers to a set of devices or programs used to achieve a specific purpose.

[0697] "Merchandise" refers to products or items sold to customers in retail stores.

[0698] "Visualization means" refers to software or interfaces used to display data obtained from a server in an easily understandable format.

[0699] "Ordering methods" refer to online systems or APIs for automatically procuring goods based on demand forecasts.

[0700] "Generative means" refers to generative AI models or software used to create effective sales promotion information for specific user groups.

[0701] "Reporting means" refers to a system that automatically generates reports based on product and demand information and distributes them to stakeholders.

[0702] This invention is a system that streamlines inventory management and customer service in retail stores. This system uses multiple hardware and software components to collect environmental parameters and user characteristics, and utilizes this data to perform demand forecasting.

[0703] The server first uses IoT sensors installed within the store to collect environmental parameters. These include sensor devices that measure temperature, humidity, illuminance, and weather changes. This allows for a detailed understanding of the environmental conditions inside and outside the store, and this data is stored in a database on the server.

[0704] Next, the server analyzes the characteristics of customers via the AI ​​camera, obtaining information such as the number of people, age group, gender, and behavioral patterns. The AI ​​technology analyzes the video in real time, and this information is also stored in the database.

[0705] Furthermore, the server performs advanced computational measures to predict demand based on this collected data. Here, machine learning models are used to create predictions that integrate historical sales data with current environmental and customer information. This process enables highly accurate estimation of future demand and the maintenance of optimal inventory levels.

[0706] Automated product procurement is carried out through an ordering system managed by the server. Using an ordering API, products are automatically ordered online based on demand forecasts. This system ensures that inventory is always managed at the appropriate level, reducing the risk of stockouts or excess inventory.

[0707] The terminals serve to provide information to staff based on data sent from the server. A dashboard is provided as a display method, visually presenting inventory status, environmental data, and customer information. For example, it can display graphs showing the remaining stock levels of best-selling products and changes in the number of customers, supporting store operations.

[0708] Furthermore, as a generation method, the server creates targeted promotions for user groups. In this process, it uses a generation AI model and generates sales promotion information by inputting prompts such as the following: "Create promotional text for a new product aimed at women in their 20s." This allows for the development of effective promotional strategies targeting specific customer segments.

[0709] This system allows stores to effectively utilize environmental and user information to improve operational efficiency and customer satisfaction through demand forecasting and inventory management.

[0710] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0711] Step 1:

[0712] The server collects environmental parameters from IoT sensors installed within the store. Specifically, it periodically acquires data such as temperature, humidity, illuminance, and weather using detection methods. The input is data from the sensors, and the output is a database entry where the environmental parameters are stored.

[0713] Step 2:

[0714] The server acquires customer characteristics via an AI camera. The camera analyzes the video in real time, extracting information on the number of people, age group, gender, and behavioral patterns. The input is the camera's video data, and the output is the analysis results regarding customer characteristics.

[0715] Step 3:

[0716] The server integrates environmental parameters and user characteristics and executes computational means to predict demand. This is done using a machine learning model that combines historical sales history with current data. The input is integrated environmental and user data, and the output is the demand forecast result.

[0717] Step 4:

[0718] The server automatically places orders for goods based on demand forecasts. It uses an ordering method to call an external ordering API and place orders for the necessary goods. The input is the demand forecast, and the output is the order data recorded in the order history.

[0719] Step 5:

[0720] The terminal displays data received from the server, visualizing inventory status and customer information on a dashboard. This allows store staff to understand the current situation in real time. The input is data from the server, and the output is visual information on the screen.

[0721] Step 6:

[0722] The server uses a generative AI model to generate sales promotion information based on user groups. In this process, it takes prompt text as input and creates promotional text tailored to the target customer. The input is prompt text assuming a specific customer segment, and the output is the generated promotional text.

[0723] (Application Example 1)

[0724] 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".

[0725] In modern retail stores, proper inventory management and sales promotion are crucial for efficient operations and improved customer satisfaction. However, traditional systems struggle to forecast demand in line with fluctuating environmental conditions and the diverse attributes of customers, resulting in problems such as inventory shortages or excesses, and inefficient promotions.

[0726] 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.

[0727] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand based on the environmental information and user information, and notification means for providing personalized purchasing information to users. This enables real-time analysis of environmental and user information and demand prediction, optimizing inventory management and sales promotion, thereby improving the efficiency of store operations and enhancing customer satisfaction.

[0728] "Environmental information" refers to information about external conditions such as temperature, humidity, and weather changes, which are obtained through detection means.

[0729] "User information" refers to information about customer characteristics such as the number of customers, gender, age group, and behavioral patterns, collected using measurement methods.

[0730] "Predicting demand" means analyzing past sales data, current environmental information, and user information using computational methods to calculate future product demand.

[0731] An "ordering system" is a system that has the function of automatically placing orders for goods with suppliers based on the results of demand forecasts.

[0732] A "visualization method" is an interface that displays information from the server in a way that store staff can easily check.

[0733] A "notification method" is a means of communication that provides users with personalized purchase information in real time.

[0734] "Generation means" refers to means that have a process for generating efficient sales promotion information based on user attributes.

[0735] "Proposal methods" refer to means of making suggestions based on reports on goods and demand information in order to support long-term strategies.

[0736] The system based on this invention aims to improve inventory management and customer satisfaction in retail stores. The system consists of multiple IoT sensors, cameras using AI technology, a server, and user terminals.

[0737] The server collects environmental information such as temperature, humidity, and weather from IoT sensors installed in the store. This allows the store's external conditions to be stored in a database. Cameras using AI technology acquire user information such as the number of customers, gender, age group, and behavioral patterns, and analyze it in real time. The analyzed information is also stored in the server's database.

[0738] The server utilizes machine learning libraries such as TensorFlow and PyTorch to forecast demand based on environmental and user information. The demand forecasting algorithm accurately estimates future demand by considering past sales history, current environmental data, and customer characteristic data. Based on these results, it automatically orders products using an ordering system to maintain optimal inventory levels at all times.

[0739] On the device, users can check real-time promotional information tailored to current inventory status, environmental conditions, and customer attributes via server-side logic using Django or Flask and a frontend built with React Native. Users can receive personalized purchase notifications and use them to guide their future purchasing decisions.

[0740] As a concrete example, if the server detects a sudden change in weather, for example, a sudden rise in temperature, the machine learning model predicts an increase in demand for beverages and immediately places an additional order for the relevant products. It also generates promotional information for specific customers based on past purchase data and notifies them through the app screen. An example of a prompt message using the generating AI model is: "The weather forecast for tomorrow is sunny, and the temperature is expected to exceed 27°C. Based on data from the past 5 years, please predict which beverages will see increased demand."

[0741] In this way, the entire system is expected to optimize the user's purchasing experience and improve store performance.

[0742] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0743] Step 1:

[0744] The server collects environmental information from IoT sensors installed in the store. Specifically, it acquires data such as temperature, humidity, and weather provided by the sensors and stores this data in the server's database. The input is environmental data from the IoT sensors, and the output is the environmental information stored in the database.

[0745] Step 2:

[0746] The server acquires user information from a camera using AI technology. This camera recognizes the number of customers, their gender, age group, and behavioral patterns, and performs real-time analysis. The input is video data from the camera, and the output is the analyzed user information.

[0747] Step 3:

[0748] The server uses machine learning algorithms to forecast demand based on collected environmental and user information. Historical sales data is also referenced, and TensorFlow or PyTorch are used. The inputs are environmental information, user information, and historical sales data, while the output is the forecasted demand data.

[0749] Step 4:

[0750] The server automatically orders goods using ordering methods based on the demand forecast results. Specifically, it issues instructions to suppliers to order goods according to the predicted demand. The input is the demand forecast results, and the output is the order instruction to the supplier.

[0751] Step 5:

[0752] The terminal displays real-time inventory status and promotional information based on information received from the server. This information is visualized through a user interface built with React Native. The input is inventory and promotional information from the server, and the output is the visual information provided to the user.

[0753] Step 6:

[0754] Users can view real-time information via their devices and reflect it in their purchasing decisions. Furthermore, personalized purchase suggestions are provided to enhance the user experience. The input is the information displayed on the device, and the output is the user's purchasing behavior.

[0755] Step 7:

[0756] The server generates a report based on the above data and makes suggestions for long-term strategic planning for the store. This may involve using a generative AI model to generate prompts and support data analysis. The input is the entire dataset, and the output is strategic suggestions.

[0757] 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.

[0758] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. This system predicts demand by combining environmental information, user information, and user emotion data, and optimizes inventory management and sales promotion based on that prediction.

[0759] The server collects environmental information from IoT sensors installed in the store, including temperature, humidity, and weather. This data is stored in the server's database in real time and is continuously updated.

[0760] Furthermore, the server uses AI-powered cameras to acquire data on customers. The cameras analyze user attribute data such as the number of people, gender, and age group, and also identify behavioral patterns. This information is recorded in a user database and used to forecast demand.

[0761] Furthermore, the server uses an emotion engine to recognize emotions from the customer's facial expressions and voice. This allows it to understand the customer's emotional state and respond accordingly.

[0762] Based on all this data, the server performs demand forecasting. Based on the forecast results, the server automatically places orders and takes proactive measures to maintain optimal inventory levels.

[0763] The terminal uses data retrieved from the server to display current inventory levels, customer sentiment analysis results, and demand forecasts on the in-store dashboard. Store staff can use this information to easily manage operations.

[0764] The emotion engine adjusts sales promotion strategies based on the user's emotions. For example, if a customer shows signs of happiness, it can offer additional incentives. Conversely, if stress or dissatisfaction is detected, it provides information to enable store staff to respond quickly.

[0765] For example, a server could use an emotion engine to recognize a customer's smile and use that as a trigger to offer a coupon for a specific product. This process strengthens personalized strategies and improves customer satisfaction.

[0766] Therefore, this system not only performs demand forecasting and inventory management, but also analyzes customer sentiment and provides an innovative solution that brings about operational improvements that reflect this.

[0767] The following describes the processing flow.

[0768] Step 1:

[0769] The server acquires environmental information from IoT sensors placed in the store. Specifically, it receives temperature, humidity, and weather data from the sensors in real time and stores this information in a database.

[0770] Step 2:

[0771] The server uses AI cameras to collect data on customers. From the camera footage, it analyzes the number of customers, their gender, age group, and behavioral patterns, and records this data in a user database.

[0772] Step 3:

[0773] The server analyzes customers' emotions from their faces and voices through an emotion engine. The recognized emotions are recorded as labels such as "happy," "surprised," and "dissatisfied," and used in each customer engagement strategy.

[0774] Step 4:

[0775] The server integrates collected environmental, user, and sentiment information to run a demand forecasting algorithm. Based on the forecasted data, it calculates the appropriate quantity for the next shipment and initiates the automated ordering process.

[0776] Step 5:

[0777] The terminal updates the dashboard in real time based on data from the server, displaying current inventory status, customer trends, and sentiment analysis results to store staff. Staff use this information to optimize daily operations.

[0778] Step 6:

[0779] Based on sentiment analysis results, the server generates personalized sales promotion information for individual customers and automatically sends coupons and special offers to them. It also adjusts marketing strategies as needed.

[0780] Step 7:

[0781] The server generates reports on the overall operating performance of stores on a daily or weekly basis. These reports include inventory turnover, customer sentiment statistics, and promotional effectiveness, and are sent to users via email. This information serves as a crucial basis for future planning.

[0782] (Example 2)

[0783] 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".

[0784] Traditional inventory management systems suffered from low demand forecasting accuracy, leading to problems such as excess inventory and stockouts. Furthermore, they struggled to provide personalized service that reflected customer sentiment and attribute information, limiting the effectiveness of sales promotion measures. As a result, improving customer satisfaction and achieving efficient inventory management remain challenges.

[0785] 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.

[0786] In this invention, the server includes collection means for collecting environmental data, analysis means for analyzing user characteristics, and emotion recognition means for determining emotional states. This enables highly accurate demand forecasting that comprehensively utilizes environmental data, user characteristics, and emotional states, as well as the provision of sales promotion measures tailored to individual users.

[0787] "Collection means" refers to a device or method that has the function of efficiently acquiring environmental data and providing it to a system in real time.

[0788] "Analysis means" refers to a device or method that analyzes user attribute information and derives useful insights through pattern recognition or statistical methods.

[0789] An "emotion recognition tool" is a device or method that identifies an emotional state from inputs such as a user's facial expressions and voice, and utilizes the analysis results.

[0790] A "predictive means" is a device or method that estimates future demand based on collected data and optimizes related resources.

[0791] "Ordering device" refers to a device or method that automatically purchases products to maintain optimal inventory levels based on predicted demand.

[0792] "Display means" refers to a device or method that visually displays collected and analyzed data and provides information in a format that is easily understandable to users.

[0793] "Means of provision" refers to a device or method for generating and effectively communicating sales promotion information based on user characteristics and emotional states.

[0794] "Creation means" refers to a device or method that automatically generates a report based on relevant data and compiles the information in a predetermined format.

[0795] This invention is a system that integrates inventory management, customer service, and user emotion recognition in retail stores. The system is configured as follows:

[0796] Server Role

[0797] The server collects environmental data using various sensing technologies installed within the store. This includes IoT sensors to acquire data such as temperature and humidity. This information is stored in the server's database in real time and is constantly updated.

[0798] The server also collects customer data using AI-equipped cameras. These cameras provide data for analyzing customer frequency and movement patterns, and use facial recognition technology to identify gender, age group, and behavioral patterns. This information is stored in a database for use in demand forecasting.

[0799] Furthermore, using an emotion engine, the server analyzes the customer's facial expressions and tone of voice to identify their emotional state. This analysis is then used to generate promotional information aimed at improving customer satisfaction.

[0800] Terminal role

[0801] The terminal displays inventory status and customer sentiment analysis results on digital displays within the store, based on information obtained from the server. This allows store staff to quickly take appropriate action, such as reviewing product placement or adjusting customer service policies.

[0802] Examples

[0803] As a concrete example, a server can use an emotion engine to recognize a customer's smile and automatically issue coupons for specific products based on the results. This process can enhance sales strategies and stimulate customer purchasing intent.

[0804] Example of a prompt

[0805] "Analyze customer behavior patterns using AI cameras, and based on the emotional information recognized by the emotion engine, propose what kind of sales promotion strategies can be applied."

[0806] This system improves store operational efficiency by providing accurate demand forecasts based on collected data, enabling appropriate inventory management and personalized customer experiences.

[0807] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0808] Step 1:

[0809] The server collects environmental data such as temperature and humidity from environmental sensors. This data is input into the server and stored in a database in real time. The server analyzes the collected environmental data to obtain basic information for understanding the current state of the store.

[0810] Step 2:

[0811] The server uses AI cameras to collect data such as the number of users, gender, and age group. This attribute data is used to analyze customer trends and behavioral patterns and is recorded in a user database. Using a generative AI model, the server processes the data based on customer attributes to prepare for future demand forecasting.

[0812] Step 3:

[0813] The server uses an emotion engine to analyze the customer's facial expressions and voice to identify their emotional state. It processes the input facial and voice data to determine whether the customer is happy, surprised, or dissatisfied. This output is used to develop emotion-based response strategies.

[0814] Step 4:

[0815] The server integrates environmental data, customer attribute data, and sentiment data to forecast demand. This data is then fed into an AI model to predict future demand with high accuracy. These forecast results are used for inventory management and automated ordering decisions.

[0816] Step 5:

[0817] The terminal displays demand forecasts and customer sentiment analysis results provided by the server on in-store displays. Store staff refer to this information and receive output to make appropriate customer service decisions and product placement.

[0818] Step 6:

[0819] The server develops individual sales promotion strategies based on the results of sentiment analysis. For example, if a customer is smiling, it automatically issues a specific product coupon and applies the strategy indicated in the prompt message. Through this process, the goal is to improve the customer experience and increase sales.

[0820] (Application Example 2)

[0821] 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".

[0822] While retail stores need to optimize inventory management and customer service, traditional systems have struggled to provide real-time demand forecasts and appropriate responses tailored to customer sentiment. Therefore, system improvements are needed to enhance customer satisfaction and boost sales promotion effectiveness.

[0823] 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.

[0824] In this invention, the server includes detection means for collecting environmental information, measurement means for analyzing user information, calculation means for predicting demand, ordering means for automatically purchasing goods, visualization means for displaying information on goods and demand, recognition means for understanding the emotional state of the user, and extended display means for dynamically displaying information during customer service. This enables real-time demand forecasting and emotion-based customer service in retail stores.

[0825] "Detection means" refers to devices or systems for collecting environmental information, which have the function of understanding conditions such as temperature and humidity.

[0826] "Measurement means" refers to devices or processes for acquiring and analyzing user information, enabling the understanding of the attributes and behavior of customers.

[0827] "Computational means" refers to processes and algorithms that provide a basis for predicting demand based on collected data.

[0828] A "procurement system" is a system that includes a function to automatically purchase goods based on predicted demand.

[0829] "Visualization means" refers to methods and technologies for visually displaying information, such as inventory status and demand forecasts within a store.

[0830] "Recognition means" refers to technologies for understanding the emotional state of a user, such as identifying emotions from facial expressions and voice.

[0831] "Extended display means" refers to devices or software for dynamically displaying information during customer service based on the customer's emotional state.

[0832] The server provides a system to optimize inventory management and customer service in retail stores. First, IoT sensors are used to collect environmental information, gathering data such as temperature, humidity, and weather within the store. This data is transmitted to the server in real time and continuously stored in a database.

[0833] Next, cameras equipped with AI technology acquire information about customers. This includes not only user attributes such as the number of people, gender, and age group, but also their behavioral patterns. This information is then analyzed as data necessary for demand forecasting.

[0834] Furthermore, the server uses an emotion engine to recognize the customer's emotional state from their facial expressions and voice. This allows for analysis of the customer's emotions and is then used to inform sales promotion strategies.

[0835] The server is equipped with a mechanism to forecast demand based on the various data mentioned above and automatically order appropriate items. To maintain optimal inventory levels, these orders are placed in real time. Additionally, terminals are installed in the store, where inventory status, demand forecasts, and customer sentiment analysis results are displayed on a dashboard.

[0836] The terminal displays information such as the customer's emotional state and age group in augmented reality to store employees wearing smart glasses upon arrival. The AR framework used is Vuforia, and the analysis is performed using a system combining TensorFlow and cloud services.

[0837] For example, when the smart glasses recognize the smile of a parent who has come into the store with their child, a prompt will appear saying, "Would you like us to show you our new products for children?" and an appropriate offer can be provided based on this.

[0838] An example of a prompt message is, "Analyze the customer's facial expression data captured by the camera and send their emotional state (joy, dissatisfaction, etc.) to the cloud in real time for analysis." Such a system enables personalized customer service for each individual customer, leading to improved customer satisfaction.

[0839] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0840] Step 1:

[0841] The server acquires environmental data from IoT sensors installed within the store. This includes temperature, humidity, and weather data, which are received directly from the sensors. This data is recorded in a database in real time and prepared for use in demand forecasting using various algorithms.

[0842] Step 2:

[0843] The server uses AI-equipped cameras to collect image data of customers. Camera footage is used as input and is analyzed using image processing technology. After extracting attribute data such as the number of people, gender, and age group, behavioral patterns are identified, and this output data is stored in a database.

[0844] Step 3:

[0845] The server uses an emotion engine to acquire customer facial expressions and voice data as input and recognize their emotional state. Here, voice recognition and facial expression analysis are performed to extract emotional data such as whether the customer is happy or stressed. This data is output and stored in the user database.

[0846] Step 4:

[0847] The server integrates collected environmental information, user attribute data, and emotional state data, and calculates demand using a demand forecasting model. The input includes the aforementioned data, and the forecasting algorithm calculates the next required inventory quantity, sending the result as output to the ordering function.

[0848] Step 5:

[0849] The server automatically places orders based on the demand forecast results. Here, it directly places orders with suppliers for goods according to the predicted demand volume, based on the output of the previous step. As a result, it becomes possible to maintain an optimal inventory level.

[0850] Step 6:

[0851] The terminal displays information about the customer's emotional state and age group on smart glasses worn by the store staff. In this process, customer data sent from the server is output to the glasses' display using an AR framework. Specifically, this involves displaying customer-specific prompts to support customized customer service.

[0852] Step 7:

[0853] The store staff, acting as users, use the information provided by the smart glasses to make appropriate offers and engage in conversations with customers. Prompts may include suggestions such as, "Would you like me to show you our new children's products?", thereby facilitating smooth customer interaction.

[0854] 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.

[0855] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0856] 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 robot 414.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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.

[0861] 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.

[0862] 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."

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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.

[0875] The following is further disclosed regarding the embodiments described above.

[0876] (Claim 1)

[0877] A detection means for collecting environmental information,

[0878] Measurement means for analyzing user information,

[0879] A calculation means for predicting demand based on the aforementioned environmental information and user information,

[0880] An ordering means that automatically purchases goods based on the aforementioned demand,

[0881] A visualization means for displaying information on the aforementioned articles and demands,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, further comprising a means for generating sales promotion information based on user attributes.

[0885] (Claim 3)

[0886] The system according to claim 1, further comprising means for automatically generating a report relating to the aforementioned articles and demand information.

[0887] "Example 1"

[0888] (Claim 1)

[0889] A detection means for collecting environmental parameters,

[0890] Measurement means for analyzing user characteristics,

[0891] A calculation means for predicting demand based on the aforementioned environmental parameters and user characteristics,

[0892] A means of automatically procuring goods based on the aforementioned demand,

[0893] Display means for displaying information on the aforementioned products and demand,

[0894] An ordering method that automatically places additional orders when there is a shortage of goods,

[0895] A data integration method for combining acquired data and visualizing the analysis results,

[0896] A system that includes this.

[0897] (Claim 2)

[0898] The system according to claim 1, further comprising a means for generating sales promotion information based on user groups.

[0899] (Claim 3)

[0900] The system according to claim 1, further comprising reporting means for automatically creating and distributing reports concerning the aforementioned products and demand information to users.

[0901] "Application Example 1"

[0902] (Claim 1)

[0903] A detection means for collecting environmental information,

[0904] Measurement means for analyzing user information,

[0905] A calculation means for predicting demand based on the aforementioned environmental information and user information,

[0906] An ordering means that automatically purchases goods based on the aforementioned demand,

[0907] A visualization means for displaying information on the aforementioned articles and demands,

[0908] A notification mechanism for providing personalized purchase information to users,

[0909] A system that includes this.

[0910] (Claim 2)

[0911] The system according to claim 1, further comprising a generation means for generating and providing sales promotion information in real time based on user attributes.

[0912] (Claim 3)

[0913] The system according to claim 1, further comprising means for automatically generating reports relating to the aforementioned goods and demand information and for providing suggestions to support long-term strategies.

[0914] "Example 2 of combining an emotion engine"

[0915] (Claim 1)

[0916] Collection methods for collecting environmental data,

[0917] Analytical methods for analyzing user characteristics,

[0918] A means of recognizing emotions to determine emotional states,

[0919] Predictive means for predicting demand based on the aforementioned environmental data, user characteristics, and emotional state,

[0920] An ordering means that automatically purchases products based on the aforementioned demand,

[0921] Display means for displaying information on the aforementioned products and demand,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, further comprising means for providing sales promotion information based on user characteristics and emotional state.

[0925] (Claim 3)

[0926] The system according to claim 1, further comprising means for automatically generating reports relating to the aforementioned products and demand information.

[0927] "Application example 2 when combining with an emotional engine"

[0928] (Claim 1)

[0929] A detection means for collecting environmental information,

[0930] Measurement means for analyzing user information,

[0931] A calculation means for predicting demand based on the aforementioned environmental information and user information,

[0932] An ordering means that automatically purchases goods based on the aforementioned demand,

[0933] A visualization means for displaying information on the aforementioned articles and demands,

[0934] A means of understanding the emotional state of the user,

[0935] An extended display means for dynamically displaying information during customer service based on the aforementioned emotional state,

[0936] A system that includes this.

[0937] (Claim 2)

[0938] The system according to claim 1, further comprising a means for generating sales promotion information based on user attributes and emotional state.

[0939] (Claim 3)

[0940] The system according to claim 1, further comprising means for automatically generating a report that includes information on the aforementioned goods and demands, as well as action suggestions based on the emotional state of the user. [Explanation of Symbols]

[0941] 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. A detection means for collecting environmental information, Measurement means for analyzing user information, A calculation means for predicting demand based on the aforementioned environmental information and user information, An ordering means that automatically purchases goods based on the aforementioned demand, A visualization means for displaying information on the aforementioned articles and demands, A notification mechanism for providing personalized purchase information to users, A system that includes this.

2. The system according to claim 1, further comprising a generation means for generating and providing sales promotion information in real time based on user attributes.

3. The system according to claim 1, further comprising means for automatically generating reports relating to the aforementioned goods and demand information and for providing suggestions to support long-term strategies.

Images