system

Abstract

We provide the system. [Solution] A data acquisition means for acquiring sales history and related data, A demand forecasting means that predicts the demand for each product based on acquired data, An inventory adjustment method that generates inventory adjustment proposals using predicted demand data, An information presentation means that presents the generated inventory adjustment plan, 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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, 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] While there is a demand for improving inventory management, shift management, and campaign planning efficiency in retail stores, conventional manual work and simple digital tools have problems in that it is difficult to achieve accurate demand forecasting, optimal resource allocation, and effective promotion implementation. In particular, problems include overstocking and out-of-stock situations due to low prediction accuracy, and insufficient customer service due to inappropriate shift arrangements. As a result, there are concerns about a decrease in customer satisfaction and an increase in operating costs.

Means for Solving the Problems

[0005] This invention solves the above problems by providing a system that acquires sales history and related data to perform demand forecasting. Specifically, it includes a demand forecasting means that uses acquired sales history and related information to predict the demand for each product with high accuracy. Furthermore, it maintains appropriate inventory levels by automatically generating and presenting inventory adjustment plans based on this forecast data. In addition, it improves the efficiency of shift management by analyzing customer data and enabling optimal staff allocation. Furthermore, it supports the automation of effective sales promotion plans by performing analysis based on past data in campaign planning. Through these means, it achieves operational efficiency, cost reduction, and improved customer satisfaction.

[0006] "Data acquisition means" refers to a device or program that has the function of automatically collecting relevant data such as sales history and the number of customers.

[0007] "Demand forecasting means" refers to algorithms or models used to analyze collected sales data and predict future demand for each product.

[0008] An "inventory adjustment tool" is a function that automatically generates suggestions or plans for efficiently adjusting product inventory based on demand forecasts.

[0009] "Information presentation means" refers to an interface or program that visually displays the generated inventory adjustment plan or shift assignment plan to the user.

[0010] A "customer visitor analysis tool" is a device or program that analyzes customer data to identify patterns and trends, and uses this information to improve store operations.

[0011] "Staff allocation optimization means" refers to an algorithm or program that makes decisions to optimize the number and allocation of staff for each time slot based on customer visit analysis. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0013] An example of an embodiment of the system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0014] First, the terms used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] 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).

[0019] 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."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] 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.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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".

[0033] This invention is a system designed to streamline inventory management, shift management, and campaign planning in retail stores. This system primarily consists of a server, terminals, and users, and its specific embodiments are described below.

[0034] First, the server automatically collects and stores diverse information, such as sales history and customer data. This allows it to always have access to the latest business environment information. Next, the server uses advanced algorithms to forecast demand based on the collected data. Through this process, the server can accurately estimate the future demand for each product.

[0035] Furthermore, the server utilizes the predicted demand data to create efficient inventory adjustment plans. These plans are presented to the user via a terminal, allowing the user to manage ordering appropriately based on them. As a result, users can prevent problems such as excess inventory and stockouts, and reduce operating costs.

[0036] The analysis of customer data is also performed automatically by the server. By understanding customer patterns, the server can plan optimal staffing during expected busy times and propose shift plans to users via terminals. This function improves the efficiency of staffing in store operations, making it possible to reduce the burden on staff while maintaining service quality.

[0037] Furthermore, the server analyzes past campaign data to develop the most effective promotional methods. This system automatically suggests appropriate campaigns via the terminal and presents an implementation schedule to the user. Based on the suggested strategies, users can then develop more effective marketing activities.

[0038] For example, if the server predicts a surge in demand for a particular product, the terminal will notify the user early and urge them to secure the necessary stock. Also, if the number of visitors is expected to peak on weekends, the server will suggest a shift plan to the user, such as allocating additional staff. Furthermore, if a particular campaign proves highly successful, the server will leverage that knowledge to automatically optimize the next promotional strategy.

[0039] These functions enable the present invention to comprehensively support the operation of retail stores, thereby improving operational efficiency and customer satisfaction.

[0040] The following describes the processing flow.

[0041] Step 1:

[0042] The server automatically acquires sales history data, customer count data, and other related data from various sensors and input systems. This step involves collecting and storing the latest information in the database.

[0043] Step 2:

[0044] The server analyzes the acquired data and uses machine learning models to predict future demand for each product. This involves techniques such as time series analysis and regression analysis. Based on the results of this analysis, demand forecast data is generated.

[0045] Step 3:

[0046] The server generates inventory adjustment plans based on demand forecast data. Specifically, it calculates order quantities according to the predicted demand and optimizes inventory levels. These adjustment plans are used in subsequent steps.

[0047] Step 4:

[0048] The terminal receives inventory adjustment proposals sent from the server and presents them visually to the user. The user reviews the presented information and places orders as needed, thereby supporting inventory management.

[0049] Step 5:

[0050] The server uses customer data to analyze customer patterns and predict congestion levels. Based on the algorithms used, it predicts future congestion and plans optimal staffing arrangements.

[0051] Step 6:

[0052] The terminal receives shift proposals calculated by the server and presents them to the user, suggesting a shift management plan. The user reviews the proposed shifts and makes adjustments as needed to determine staff allocation.

[0053] Step 7:

[0054] The server analyzes campaign data and automatically generates a new campaign strategy based on the effectiveness of past promotions. This strategy includes details such as the products to be applied to, the discount rate, and the duration of the campaign.

[0055] Step 8:

[0056] The terminal presents the generated campaign plan to the user and suggests an implementation schedule. Based on the presented campaign strategy, the user develops efficient promotional activities.

[0057] This series of processing steps allows servers, terminals, and users to work together to streamline the operation of retail stores.

[0058] (Example 1)

[0059] 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."

[0060] Retail stores are required to effectively utilize sales history and customer data to streamline demand forecasting, inventory management, staffing, and campaign strategies. However, the lack of sufficient integration of this data is leading to problems such as lost sales opportunities, wasted staffing, and ineffective campaigns. It is necessary to address these issues to improve store operations efficiency and enhance customer satisfaction.

[0061] 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.

[0062] In this invention, the server includes information gathering means for acquiring sales history and related data, forecasting calculation means for predicting the demand for each product based on the acquired information, and personnel allocation means for analyzing customer trends and planning the optimal staffing arrangement. This improves the accuracy of demand forecasting and enables the optimization of inventory management and efficient personnel allocation planning.

[0063] "Information gathering means" refers to a function that efficiently acquires sales history and related data and stores that information on a server.

[0064] A "predictive calculation means" is a function that predicts future demand for each product based on acquired data and formulates optimal sales and inventory strategies based on the analysis results.

[0065] "Resource management tools" refer to functions that use predicted demand data to generate inventory adjustment plans and maintain appropriate inventory levels.

[0066] A "data presentation method" is a function that displays generated inventory adjustment proposals and personnel allocation plans, presenting them in a way that is easy for users to understand.

[0067] "Personnel allocation methods" refer to functions that improve the efficiency of store operations by analyzing customer trends and planning the optimal allocation of staff.

[0068] "Promotional activity support tools" refer to functions that analyze past sales promotion activity information and support the development and implementation of effective promotion strategies.

[0069] The "analysis and presentation means" is a function that creates a staffing plan based on the results of customer trends and provides information related to it.

[0070] The "activity suggestion tool" is a function that optimizes promotional activities based on analyzed sales and customer visitor information, and provides efficient suggestions to users.

[0071] This invention is a system aimed at improving the operational efficiency of retail stores. This system consists of a server, terminals, and users as its main components, and optimizes demand forecasting, inventory management, staffing, and campaign strategies by linking various data.

[0072] First, the server uses information gathering tools to collect store sales history, customer information, and other data. This data is retrieved via a RESTful API and stored in a data management system, which is a multi-purpose database software.

[0073] Next, the server uses predictive computation to forecast the future demand for each product based on the collected data. This process utilizes the data analysis library pandas and the machine learning library scikit-learn. By employing sophisticated algorithms, precise predictions become possible.

[0074] The server further analyzes customer trends using staffing methods and plans the optimal staffing arrangement. This analysis utilizes big data processing tools on a cloud service, and the analysis results are sent to terminals for the user to receive.

[0075] The terminal displays generated inventory adjustment proposals and shift plans to the user through a data presentation system. Based on the presented information, the user can place orders and adjust staff schedules.

[0076] Furthermore, the server's promotional support tools analyze past campaign results and formulate future promotional strategies. This function uses data visualization tools to analyze results and automatically derive effective strategies.

[0077] For example, if the server predicts an increase in sales of a particular product, the terminal will display a notification prompting the user to place an early order to secure inventory. Also, if an increase in the number of visitors is predicted during a specific time period, the server will plan the deployment of additional staff and propose this to the user via the terminal. Furthermore, if past campaigns have been highly successful, that data can be used to automatically adjust future promotional strategies.

[0078] An example of a prompt message is, "Please provide the results of a demand forecast based on historical sales data to determine if a particular product is suitable for the next campaign."

[0079] This system provides comprehensive support for retail store operations, resulting in a significant improvement in operational efficiency and maximizing customer satisfaction.

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

[0081] Step 1:

[0082] The server uses data collection tools to retrieve sales history and customer information from the POS systems of retail stores. This input data is aggregated via a RESTful API and stored in a data management system. This ensures that the necessary information is always up-to-date.

[0083] Step 2:

[0084] The server uses predictive computation methods to forecast demand based on collected sales history data and customer information. The input data is formatted using the pandas library and fed into a machine learning model using scikit-learn. The output is the predicted demand value for each product. The predicted data is updated periodically to improve accuracy.

[0085] Step 3:

[0086] The server uses resource management tools to generate inventory adjustment proposals from predicted demand data. Based on the demand data as input, a linear programming algorithm calculates the optimal order quantity. The output of this process is the recommended inventory level for each product.

[0087] Step 4:

[0088] The terminal displays inventory adjustment proposals sent from the server to the user via a data presentation mechanism. Specifically, a pop-up notification appears on the terminal's display, allowing the user to place an order based on it.

[0089] Step 5:

[0090] The server uses staffing methods to analyze customer data and plan the optimal staffing arrangement. The input data is processed by a big data processing tool, and congestion predictions are output as analysis results. This ensures that the appropriate number of staff are allocated during the necessary time periods.

[0091] Step 6:

[0092] The terminal presents the user with specific shift plans based on analysis results from the server. The user can then use this as a reference to adjust staff schedules.

[0093] Step 7:

[0094] The server uses promotional support tools to analyze past campaign data and develop effective promotional strategies. Based on the collected campaign data, data analysis is performed using visualization tools, and new campaign proposals are generated as output.

[0095] Step 8:

[0096] Users can improve operational efficiency and increase customer satisfaction by reviewing proposed inventory adjustments and campaign plans through their devices and making necessary changes.

[0097] (Application Example 1)

[0098] 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."

[0099] In modern sales operations, inventory management, customer visit pattern analysis, and staffing are crucial, but their efficient implementation requires significant time and effort. Furthermore, traditional methods fail to fully utilize sales history and visit patterns, making rapid response difficult. Additionally, stores struggle to grasp the current situation in real time, posing a major obstacle to determining appropriate inventory levels and staffing.

[0100] 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.

[0101] In this invention, the server includes data acquisition means for acquiring sales history and related information, demand forecasting means for predicting demand for each product group based on the acquired information, inventory adjustment means for generating an inventory adjustment plan using the predicted demand information, information presentation means for presenting and guiding customers through the generated inventory adjustment plan, and image analysis means for analyzing photographic data and evaluating the current situation. This improves the efficiency of inventory management, visitor analysis, and staff allocation, enabling rapid decision-making in physical store operations.

[0102] "Sales history" refers to information about all sales activities that have taken place at a store in the past, and includes data such as the type of product, quantity, and date of sale.

[0103] "Relevant information" refers to all data that affects inventory management and store operations, in addition to sales history, and includes, for example, weather information and local event information.

[0104] "Data acquisition means" refers to a mechanism for collecting necessary information and data, and includes a system that incorporates methods for obtaining information from sensors and databases.

[0105] "Demand forecasting tools" refer to algorithms and processes for analyzing past data to estimate and predict future demand.

[0106] "Inventory adjustment measures" refer to the function of determining the appropriate inventory level based on predicted demand and formulating plans to prevent excess inventory and stockouts.

[0107] "Information presentation means" refers to user interfaces and devices that display important information to store staff in an easy-to-understand manner and support decision-making.

[0108] "Photo data" refers to visual information acquired as an image, and is a digital image file used to check the condition of products, their display, etc.

[0109] "Image analysis means" refers to the process of extracting meaningful information from a photograph, and is a technology for recognizing features within an image and deriving analysis results.

[0110] The system that realizes this invention consists of a server, a terminal, and a user.

[0111] The server is built using the Flask framework in Python and uses PostgreSQL as its database. The server automatically collects sales history and visitor information and analyzes it to forecast demand. A demand forecasting model trained with Scikit-learn is used for demand forecasting. This model is based on a random forest and uses sales history and related information as input to predict future demand with high accuracy.

[0112] The device is used as a smartphone or tablet and provides an interface for user access. The device receives inventory adjustment proposals and campaign suggestions sent from the server and presents them to the user. Since the user interface is represented through a web browser, the device can utilize all the functions of the present invention simply by opening a specific web page.

[0113] Users can receive information from the server via their terminals, allowing them to, for example, check inventory levels and determine optimal order quantities. Users can also manage store shifts and optimize staff allocation based on customer traffic forecast data from the server.

[0114] As a concrete example, a user can take a picture of the current inventory status with their device and send the photo to the server. The server analyzes this photo data and makes demand forecasts based on the image. An example of a prompt message might be: "The inventory of product A is decreasing. Send a photo to check inventory and receive order suggestions."

[0115] As a result, inventory management, shift management, and campaign planning in physical stores can be carried out efficiently, leading to optimized operations and improved customer service.

[0116] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0117] Step 1:

[0118] The server acquires sales history and related information. Using data acquisition methods, it automatically collects necessary information from databases and sensors and stores it. The acquired data is used as input for a predictive model.

[0119] Step 2:

[0120] The server uses the acquired data to perform demand forecasting using a generative AI model. Using Scikit-learn's Random Forest, it analyzes sales history and related information to predict future demand for each product group. These forecast results serve as the basis for generating inventory adjustment proposals.

[0121] Step 3:

[0122] The server develops an inventory adjustment plan based on predicted demand data. Using inventory adjustment tools, it calculates the order quantities needed to prevent excess inventory and stockouts, and sends the results to the terminal. This plan serves as a guideline to streamline the user's ordering process.

[0123] Step 4:

[0124] The terminal presents the user with inventory adjustment proposals sent from the server. Using an information presentation system, it clearly displays the necessary information through a user-friendly interface. Based on this information, the user can make quick decisions.

[0125] Step 5:

[0126] The user sends current inventory information to the server via a photograph through their device. The device's built-in camera captures the information, and the photograph is sent to the server as digital data. This data is then analyzed using image analysis tools.

[0127] Step 6:

[0128] The server performs image analysis based on the transmitted photo data. Using an image analysis model, it analyzes the number of products, their display status, etc., and evaluates the current inventory status based on this. The results are used as a reference for more detailed inventory adjustments.

[0129] Step 7:

[0130] Users can check visitor information via their devices and optimize shifts. The system analyzes visitor data and forecast data provided by the server to plan optimal staffing. This enables efficient staffing while maintaining the store's service level.

[0131] 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.

[0132] This invention combines a system that utilizes sales history and customer data to improve the efficiency of inventory management and staff allocation with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user.

[0133] First, the server uses various sensors and input systems to acquire sales history data and customer data, and simultaneously acquires user emotion data through terminals. Next, the server integrates this data to create a dataset for analysis. For emotion recognition, a specific algorithm is used to analyze the user's facial expressions and tone of voice and classify their emotional state.

[0134] Based on the acquired data, the server performs demand forecasting and optimizes inventory management. By incorporating user sentiment data into the analysis, more precise demand forecasting is achieved. In this process, it is estimated that demand may increase if a large number of positive emotions are recognized.

[0135] The server also analyzes customer visit data and generates optimized staffing plans based on customer patterns. It uses emotional data to evaluate customer satisfaction during specific time periods and suggests adjustments to staffing accordingly.

[0136] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server to the user. Based on this, the user can efficiently perform tasks such as ordering, shift management, and customer service. Furthermore, by providing communication and services tailored to the user's emotions, the system aims to improve customer satisfaction.

[0137] As a concrete example, if the server detects a customer's negative emotions during peak hours, it will alert the user via their terminal and suggest improvements such as assigning additional staff. In this way, the system of the present invention enables increased efficiency and improved service in all aspects of store operations by integrating data-driven approaches with emotional data.

[0138] The following describes the processing flow.

[0139] Step 1:

[0140] The server collects sales history data and customer visitor data. Furthermore, it collects customer sentiment data through audio and video data acquired from users' devices.

[0141] Step 2:

[0142] The server builds a demand forecasting model based on collected sales history and customer data. This model includes analytical parameters that use positive customer sentiment as an indicator of increased demand.

[0143] Step 3:

[0144] The server generates inventory adjustment plans based on demand forecasts. In this process, if customer satisfaction is high based on sentiment data, it predicts increased demand and creates an adjustment plan to secure more inventory.

[0145] Step 4:

[0146] The terminal presents the generated inventory adjustment proposal to the user. The user reviews the proposal and places orders for products as needed.

[0147] Step 5:

[0148] The server analyzes visitor data and emotional data, optimizing staff allocation based on visit patterns and customer emotional states. If the emotional state is negative, it suggests additional staff allocation.

[0149] Step 6:

[0150] The terminal receives the calculated staffing plan and presents it to the user. The user adjusts staff shifts based on the presented plan to ensure optimal staffing.

[0151] Step 7:

[0152] The server analyzes customer sentiment data and, if there are many negative emotions, generates suggestions that include specific measures for service improvement.

[0153] Step 8:

[0154] The terminal provides users with service improvement suggestions, which users then use to modify their customer service and store management strategies.

[0155] In this way, the server integrates and analyzes diverse data, and presents appropriate operational strategies to users through terminals, thereby improving the efficiency of store operations and enhancing customer service.

[0156] (Example 2)

[0157] 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".

[0158] In store operations, relying solely on sales history and customer data is insufficient to accurately capture fluctuating consumer needs and customer emotional states, making it difficult to optimize inventory management and staffing. Furthermore, there is a lack of specific information needed to streamline customer service and improve customer satisfaction.

[0159] 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.

[0160] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing user emotions, and inventory adjustment means for generating inventory adjustment proposals using predicted demand data and sentiment data. This enables optimization of inventory management and staff allocation that takes into account fluctuations in consumer needs and customer emotional states, thereby improving the efficiency of store operations and enhancing service.

[0161] "Data acquisition means" refers to methods for collecting store-related information such as sales history and customer data.

[0162] A "demand forecasting tool" is a means of predicting the future demand for each product based on acquired data.

[0163] An "emotion analysis tool" is a method for analyzing a user's facial expressions and tone of voice to classify their emotional state.

[0164] "Inventory adjustment tools" are means of generating suggestions for adjusting inventory to optimal levels using predicted demand data and sentiment data.

[0165] "Information presentation means" refers to means for displaying generated inventory adjustment proposals and other data to the user.

[0166] A "customer visitor analysis method" is a means of acquiring customer data and analyzing that data to reveal customer visit patterns.

[0167] "Staff allocation optimization methods" are means of optimizing staff allocation based on customer visit data and emotional data, in order to achieve efficient personnel management.

[0168] "Information provision means" are means to support users in using the provided data to improve the efficiency of their work.

[0169] The embodiments for carrying out the present invention will now be described. This system is built to improve the efficiency of store operations by utilizing sales history and customer data, and consists of three elements: a server, a terminal, and a user.

[0170] The server collects sales history data and customer information through various sensors and input devices. Hardware includes, for example, cameras and microphones, while software algorithms such as "OpenFace" and "Prosody" are used. The data is first aggregated on the server, where it analyzes the user's facial expressions and voice tone to generate emotion data.

[0171] The server performs demand forecasting based on the acquired data. The demand forecasting algorithm utilizes machine learning models on "PyTorch" and "TENSORFLOW®," which calculate the demand for products according to the time of year and generate inventory optimization plans. For example, if many positive emotions are recognized, demand is predicted to increase. This information is presented to the user via their terminal.

[0172] Furthermore, the server analyzes customer visit patterns and creates optimal staffing plans. Based on emotional data, it evaluates customer satisfaction during specific time periods and suggests staffing changes as needed. This information is also provided to users through their terminals, supporting them in making decisions regarding store operations.

[0173] As a concrete example, if the server detects negative customer emotions during peak hours, the terminal will issue a warning and recommend that the user allocate additional staff. This enables data-driven and emotion-based decision-making, contributing to more efficient store operations and improved service.

[0174] Examples of prompts for a generative AI model include, "Please provide details on demand forecasting using sales history and visit data," and "How can sentiment data be used to optimize staffing?" These prompts demonstrate the AI's ability to suggest specific information that the user needs.

[0175] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0176] Step 1:

[0177] The server collects sales history data and customer data through various sensors and input devices. Specifically, it obtains sales history from the POS system and records customer behavior using cameras installed in the store. Inputs include product sales information and the number of customers, and outputs that store this information in an integrated database.

[0178] Step 2:

[0179] The server receives and analyzes user emotion data transmitted from the terminal. Specifically, it uses data captured by cameras and audio sensors to analyze facial expressions and voice using algorithms such as "OpenFace" and "Prosody" to classify the emotional state. The input is the user's video and audio data, and the output is a score indicating the emotional state.

[0180] Step 3:

[0181] The server combines sales history data and sentiment data to forecast demand. This process utilizes machine learning algorithms, such as a model on TensorFlow, to analyze the data. The input is integrated sales history and sentiment data, and the output is the predicted demand for each product. Based on this forecast, the server generates inventory adjustment plans for the next period.

[0182] Step 4:

[0183] The server analyzes customer behavior patterns and generates optimal staffing plans. It combines customer visit data and sentiment data to provide staffing recommendations. Using customer visit time and frequency data as input, it provides suggestions on how staff should be allocated during specific time periods as output.

[0184] Step 5:

[0185] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results received from the server to the user. Based on this, the user can optimize orders and shifts, and revise customer service strategies. It receives information from the server as input and displays visual information on the terminal screen as output.

[0186] Step 6:

[0187] Users perform their actual tasks based on feedback from their devices. For example, if data indicates that customer sentiment deteriorates during peak hours, additional staff will be assigned to strengthen customer service. In this way, practical countermeasures can be taken by utilizing information from the server.

[0188] (Application Example 2)

[0189] 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".

[0190] In the modern real world, many brick-and-mortar stores are striving to improve the efficiency of inventory management and staffing, but systems that take customer emotions into account are not yet widespread. As a result, they face problems such as inaccurate demand forecasts and decreased customer satisfaction. To improve the customer experience while maximizing operational efficiency, it is necessary to optimize store operations by considering the emotional state of customers.

[0191] 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.

[0192] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing and classifying the emotional state of users, and business optimization means for dynamically adjusting staff allocation and service content using the sentiment analysis results. This makes it possible to optimize operations in accordance with customer emotions, thereby simultaneously achieving improved customer satisfaction and operational efficiency.

[0193] "Data acquisition means" refers to a device or process for collecting sales history, customer information, etc.

[0194] A "demand forecasting tool" is a device or process that has the function of calculating and forecasting future demand based on acquired data.

[0195] An "inventory adjustment device" is a device or process that has the function of appropriately adjusting inventory levels based on predicted demand.

[0196] An "emotional analysis tool" is a device or process that has the function of recognizing a user's emotional state, analyzing that information, and classifying it.

[0197] A "business optimization tool" is a device or process that has the function of dynamically adjusting staff allocation and service content using the results of sentiment analysis to optimize business efficiency.

[0198] "Information presentation means" refers to a device or process for displaying generated inventory adjustment proposals and business optimization details to the user.

[0199] "Visitor analysis means" refers to a device or process for analyzing visitor patterns based on visitor data.

[0200] A "means for reflecting emotional data" refers to a device or process that has the function of reflecting emotional data analyzed in real time into store operations.

[0201] A "staff allocation optimization method" is a device or process that has the function of achieving efficient staff allocation based on customer visit data and sentiment data.

[0202] To implement this invention, the server first utilizes data acquisition means to collect sales history and customer information. The data is acquired via hardware such as cameras, sensors, and register recording systems installed within the commercial store. This allows for the collection of information such as which products were sold and in what quantities, and which times of day see the most customers.

[0203] Next, the server uses emotion analysis software such as EmotionRecognizer to analyze the customer's facial expressions and tone of voice to determine their emotional state. Specifically, it captures the user's emotions in real time through smartphones and cameras and microphones on robots installed in the store, and processes this data using an analysis algorithm. This process analyzes that if there are many positive emotions, demand tends to increase.

[0204] Based on these analysis results, the server generates suggestions for dynamically adjusting staffing and service content using operational optimization tools. For example, if customer frustration is detected during peak hours, the server sends a notification to the terminal, prompting the deployment of additional staff or the provision of alternative services. The store terminal uses the inventory adjustment suggestions, staffing suggestions, and sentiment analysis results sent from the server to present users with instructions and options.

[0205] For example, if many customers are showing signs of frustration on a Friday afternoon, the server will analyze the emotional data, send notifications to staff, and suggest adding additional staff to improve customer satisfaction. In this way, the server can integrate data and emotional information and utilize it in all aspects of store operations.

[0206] An example of a prompt given to a generative AI model is, "If the majority of customers who visited on Friday afternoon showed signs of frustration, what measures would be effective?" It is expected that the AI ​​will then suggest appropriate actions based on this prompt.

[0207] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0208] Step 1:

[0209] The server collects sales history data and customer data from cameras, sensors, and cash registers installed within the store. Inputs include the number of items sold and time information of customers who visited the store, and the output is a dataset in which this data is organized.

[0210] Step 2:

[0211] The server uses EmotionRecognizer to perform emotion analysis using customer video and audio data acquired from smartphones and in-store robots. The input includes customer facial expressions and voice data, which are processed by an analysis algorithm to output evaluation results classifying the customer's emotional state.

[0212] Step 3:

[0213] The server integrates sales history data, customer data, and sentiment analysis results to forecast demand. All data is included as input, and statistical models and machine learning algorithms are used to predict demand, outputting forecast data useful for inventory management.

[0214] Step 4:

[0215] Subsequently, the server optimizes operations based on the results of the sentiment analysis. In particular, it generates adjustments to staff allocation and suggestions for additional services. The inputs include customer sentiment data and visit patterns, and these are used to output the optimal staff allocation plan.

[0216] Step 5:

[0217] The terminal presents the user with inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server. Based on the input, it provides visual information to the user on the user interface, and the output is information designed to facilitate the user's decision-making.

[0218] Step 6:

[0219] Users efficiently perform tasks such as taking orders, managing shifts, and handling customer service based on suggestions provided through the terminal. Input consists of suggested ideas and instructions, and by performing practical operations based on these, the system outputs results that improve the overall operational efficiency of the store.

[0220] 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.

[0221] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0222] 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.

[0223] [Second Embodiment]

[0224] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0225] 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.

[0226] 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).

[0227] 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.

[0228] 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.

[0229] 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).

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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".

[0236] This invention is a system designed to streamline inventory management, shift management, and campaign planning in retail stores. This system primarily consists of a server, terminals, and users, and its specific embodiments are described below.

[0237] First, the server automatically collects and stores diverse information, such as sales history and customer data. This allows it to always have access to the latest business environment information. Next, the server uses advanced algorithms to forecast demand based on the collected data. Through this process, the server can accurately estimate the future demand for each product.

[0238] Furthermore, the server utilizes the predicted demand data to create efficient inventory adjustment plans. These plans are presented to the user via a terminal, allowing the user to manage ordering appropriately based on them. As a result, users can prevent problems such as excess inventory and stockouts, and reduce operating costs.

[0239] The analysis of customer data is also performed automatically by the server. By understanding customer patterns, the server can plan optimal staffing during expected busy times and propose shift plans to users via terminals. This function improves the efficiency of staffing in store operations, making it possible to reduce the burden on staff while maintaining service quality.

[0240] Furthermore, the server analyzes past campaign data to develop the most effective promotional methods. This system automatically suggests appropriate campaigns via the terminal and presents an implementation schedule to the user. Based on the suggested strategies, users can then develop more effective marketing activities.

[0241] For example, if the server predicts a surge in demand for a particular product, the terminal will notify the user early and urge them to secure the necessary stock. Also, if the number of visitors is expected to peak on weekends, the server will suggest a shift plan to the user, such as allocating additional staff. Furthermore, if a particular campaign proves highly successful, the server will leverage that knowledge to automatically optimize the next promotional strategy.

[0242] These functions enable the present invention to comprehensively support the operation of retail stores, thereby improving operational efficiency and customer satisfaction.

[0243] The following describes the processing flow.

[0244] Step 1:

[0245] The server automatically acquires sales history data, customer count data, and other related data from various sensors and input systems. This step involves collecting and storing the latest information in the database.

[0246] Step 2:

[0247] The server analyzes the acquired data and uses machine learning models to predict future demand for each product. This involves techniques such as time series analysis and regression analysis. Based on the results of this analysis, demand forecast data is generated.

[0248] Step 3:

[0249] The server generates inventory adjustment plans based on demand forecast data. Specifically, it calculates order quantities according to the predicted demand and optimizes inventory levels. These adjustment plans are used in subsequent steps.

[0250] Step 4:

[0251] The terminal receives inventory adjustment proposals sent from the server and presents them visually to the user. The user reviews the presented information and places orders as needed, thereby supporting inventory management.

[0252] Step 5:

[0253] The server uses customer data to analyze customer patterns and predict congestion levels. Based on the algorithms used, it predicts future congestion and plans optimal staffing arrangements.

[0254] Step 6:

[0255] The terminal receives shift proposals calculated by the server and presents them to the user, suggesting a shift management plan. The user reviews the proposed shifts and makes adjustments as needed to determine staff allocation.

[0256] Step 7:

[0257] The server analyzes campaign data and automatically generates a new campaign strategy based on the effectiveness of past promotions. This strategy includes details such as the products to be applied to, the discount rate, and the duration of the campaign.

[0258] Step 8:

[0259] The terminal presents the generated campaign plan to the user and suggests an implementation schedule. Based on the presented campaign strategy, the user develops efficient promotional activities.

[0260] This series of processing steps allows servers, terminals, and users to work together to streamline the operation of retail stores.

[0261] (Example 1)

[0262] 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."

[0263] Retail stores are required to effectively utilize sales history and customer data to streamline demand forecasting, inventory management, staffing, and campaign strategies. However, the lack of sufficient integration of this data is leading to problems such as lost sales opportunities, wasted staffing, and ineffective campaigns. It is necessary to address these issues to improve store operations efficiency and enhance customer satisfaction.

[0264] 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.

[0265] In this invention, the server includes information gathering means for acquiring sales history and related data, forecasting calculation means for predicting the demand for each product based on the acquired information, and personnel allocation means for analyzing customer trends and planning the optimal staffing arrangement. This improves the accuracy of demand forecasting and enables the optimization of inventory management and efficient personnel allocation planning.

[0266] "Information gathering means" refers to a function that efficiently acquires sales history and related data and stores that information on a server.

[0267] A "predictive calculation means" is a function that predicts future demand for each product based on acquired data and formulates optimal sales and inventory strategies based on the analysis results.

[0268] "Resource management tools" refer to functions that use predicted demand data to generate inventory adjustment plans and maintain appropriate inventory levels.

[0269] A "data presentation method" is a function that displays generated inventory adjustment proposals and personnel allocation plans, presenting them in a way that is easy for users to understand.

[0270] "Personnel allocation methods" refer to functions that improve the efficiency of store operations by analyzing customer trends and planning the optimal allocation of staff.

[0271] "Promotional activity support tools" refer to functions that analyze past sales promotion activity information and support the development and implementation of effective promotion strategies.

[0272] The "analysis and presentation means" is a function that creates a staffing plan based on the results of customer trends and provides information related to it.

[0273] The "activity suggestion tool" is a function that optimizes promotional activities based on analyzed sales and customer visitor information, and provides efficient suggestions to users.

[0274] This invention is a system aimed at improving the operational efficiency of retail stores. This system consists of a server, terminals, and users as its main components, and optimizes demand forecasting, inventory management, staffing, and campaign strategies by linking various data.

[0275] First, the server uses information gathering tools to collect store sales history, customer information, and other data. This data is retrieved via a RESTful API and stored in a data management system, which is a multi-purpose database software.

[0276] Next, the server uses predictive computation to forecast the future demand for each product based on the collected data. This process utilizes the data analysis library pandas and the machine learning library scikit-learn. By employing sophisticated algorithms, precise predictions become possible.

[0277] The server further analyzes customer trends using staffing methods and plans the optimal staffing arrangement. This analysis utilizes big data processing tools on a cloud service, and the analysis results are sent to terminals for the user to receive.

[0278] The terminal displays generated inventory adjustment proposals and shift plans to the user through a data presentation system. Based on the presented information, the user can place orders and adjust staff schedules.

[0279] Furthermore, the server's promotional support tools analyze past campaign results and formulate future promotional strategies. This function uses data visualization tools to analyze results and automatically derive effective strategies.

[0280] For example, if the server predicts an increase in sales of a particular product, the terminal will display a notification prompting the user to place an early order to secure inventory. Also, if an increase in the number of visitors is predicted during a specific time period, the server will plan the deployment of additional staff and propose this to the user via the terminal. Furthermore, if past campaigns have been highly successful, that data can be used to automatically adjust future promotional strategies.

[0281] Examples of prompt texts include "Please show the results of demand forecasting based on past sales data to determine whether a specific product is optimal for the next campaign."

[0282] This system comprehensively supports the operation of retail stores, achieving a significant improvement in business efficiency and maximizing customer satisfaction.

[0283] The flow of the specific process in Example 1 will be described using FIG. 11.

[0284] Step 1:

[0285] The server uses information collection means to obtain sales history and visitor information from the POS system of the retail store. This input data is aggregated via a RESTful API and stored in the data management system. This enables the necessary information to always be kept up-to-date.

[0286] Step 2:

[0287] The server utilizes prediction calculation means to perform demand forecasting based on the collected sales history data and visitor information. The input data is formatted with the pandas library and input into a machine learning model using scikit-learn. The output obtained here is the demand prediction value for each product. The predicted data is updated regularly to improve accuracy.

[0288] Step 3:

[0289] The server uses resource management means to generate an inventory adjustment plan from the predicted demand data. Based on the demand data as input, the optimal order quantity is calculated using the linear programming algorithm. The output of this process is the recommended inventory level for each product.

[0290] Step 4:

[0291] The terminal displays inventory adjustment proposals sent from the server to the user via a data presentation mechanism. Specifically, a pop-up notification appears on the terminal's display, allowing the user to place an order based on it.

[0292] Step 5:

[0293] The server uses staffing methods to analyze customer data and plan the optimal staffing arrangement. The input data is processed by a big data processing tool, and congestion predictions are output as analysis results. This ensures that the appropriate number of staff are allocated during the necessary time periods.

[0294] Step 6:

[0295] The terminal presents the user with specific shift plans based on analysis results from the server. The user can then use this as a reference to adjust staff schedules.

[0296] Step 7:

[0297] The server uses promotional support tools to analyze past campaign data and develop effective promotional strategies. Based on the collected campaign data, data analysis is performed using visualization tools, and new campaign proposals are generated as output.

[0298] Step 8:

[0299] Users can improve operational efficiency and increase customer satisfaction by reviewing proposed inventory adjustments and campaign plans through their devices and making necessary changes.

[0300] (Application Example 1)

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

[0302] In modern sales operations, inventory management, analysis of customer visit patterns, and staff allocation are very important, but their efficient implementation requires a lot of time and effort. Also, with conventional methods, sales histories and visit patterns cannot be fully utilized, making it difficult to respond quickly. Furthermore, it is difficult for the store side to grasp the current situation in real time, which is a major obstacle when determining appropriate inventory levels and staff allocation.

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

[0304] In this invention, the server includes: a data acquisition means for acquiring sales histories and related information; a demand prediction means for predicting the demand for each product group based on the acquired information; an inventory adjustment means for generating an inventory adjustment plan using the predicted demand information; an information presentation means for presenting and guiding the generated inventory adjustment plan; and an image analysis means for analyzing photo data and evaluating the current situation. Thereby, the efficiency of inventory management, visitor analysis, and staff allocation is improved, enabling rapid decision-making in actual store operations.

[0305] The "sales history" refers to information regarding all past sales activities conducted at the store, and is data including the type of product, quantity, sales date, and the like.

[0306] The "related information" refers to all data that affects inventory management and store operations other than the sales history, and includes, for example, weather information and regional event information.

[0307] The "data acquisition means" is a mechanism for collecting necessary information and data, and is a system including methods for acquiring information from sensors and databases.

[0308] The "demand prediction means" is an algorithm and process for analyzing past data and inferring / predicting future demand.

[0309] "Inventory adjustment measures" refer to the function of determining the appropriate inventory level based on predicted demand and formulating plans to prevent excess inventory and stockouts.

[0310] "Information presentation means" refers to user interfaces and devices that display important information to store staff in an easy-to-understand manner and support decision-making.

[0311] "Photo data" refers to visual information acquired as an image, and is a digital image file used to check the condition of products, their display, etc.

[0312] "Image analysis means" refers to the process of extracting meaningful information from a photograph, and is a technology for recognizing features within an image and deriving analysis results.

[0313] The system that realizes this invention consists of a server, a terminal, and a user.

[0314] The server is built using the Flask framework in Python and uses PostgreSQL as its database. The server automatically collects sales history and visitor information and analyzes it to forecast demand. A demand forecasting model trained with Scikit-learn is used for demand forecasting. This model is based on a random forest and uses sales history and related information as input to predict future demand with high accuracy.

[0315] The device is used as a smartphone or tablet and provides an interface for user access. The device receives inventory adjustment proposals and campaign suggestions sent from the server and presents them to the user. Since the user interface is represented through a web browser, the device can utilize all the functions of the present invention simply by opening a specific web page.

[0316] Users can receive information from the server via their terminals, allowing them to, for example, check inventory levels and determine optimal order quantities. Users can also manage store shifts and optimize staff allocation based on customer traffic forecast data from the server.

[0317] As a concrete example, a user can take a picture of the current inventory status with their device and send the photo to the server. The server analyzes this photo data and makes demand forecasts based on the image. An example of a prompt message might be: "The inventory of product A is decreasing. Send a photo to check inventory and receive order suggestions."

[0318] As a result, inventory management, shift management, and campaign planning in physical stores can be carried out efficiently, leading to optimized operations and improved customer service.

[0319] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0320] Step 1:

[0321] The server acquires sales history and related information. Using data acquisition methods, it automatically collects necessary information from databases and sensors and stores it. The acquired data is used as input for a predictive model.

[0322] Step 2:

[0323] The server uses the acquired data to perform demand forecasting using a generative AI model. Using Scikit-learn's Random Forest, it analyzes sales history and related information to predict future demand for each product group. These forecast results serve as the basis for generating inventory adjustment proposals.

[0324] Step 3:

[0325] The server develops an inventory adjustment plan based on predicted demand data. Using inventory adjustment tools, it calculates the order quantities needed to prevent excess inventory and stockouts, and sends the results to the terminal. This plan serves as a guideline to streamline the user's ordering process.

[0326] Step 4:

[0327] The terminal presents the user with inventory adjustment proposals sent from the server. Using an information presentation system, it clearly displays the necessary information through a user-friendly interface. Based on this information, the user can make quick decisions.

[0328] Step 5:

[0329] The user sends current inventory information to the server via a photograph through their device. The device's built-in camera captures the information, and the photograph is sent to the server as digital data. This data is then analyzed using image analysis tools.

[0330] Step 6:

[0331] The server performs image analysis based on the transmitted photo data. Using an image analysis model, it analyzes the number of products, their display status, etc., and evaluates the current inventory status based on this. The results are used as a reference for more detailed inventory adjustments.

[0332] Step 7:

[0333] Users can check visitor information via their devices and optimize shifts. The system analyzes visitor data and forecast data provided by the server to plan optimal staffing. This enables efficient staffing while maintaining the store's service level.

[0334] 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.

[0335] This invention combines a system that utilizes sales history and customer data to improve the efficiency of inventory management and staff allocation with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user.

[0336] First, the server uses various sensors and input systems to acquire sales history data and customer data, and simultaneously acquires user emotion data through terminals. Next, the server integrates this data to create a dataset for analysis. For emotion recognition, a specific algorithm is used to analyze the user's facial expressions and tone of voice and classify their emotional state.

[0337] Based on the acquired data, the server performs demand forecasting and optimizes inventory management. By incorporating user sentiment data into the analysis, more precise demand forecasting is achieved. In this process, it is estimated that demand may increase if a large number of positive emotions are recognized.

[0338] The server also analyzes customer visit data and generates optimized staffing plans based on customer patterns. It uses emotional data to evaluate customer satisfaction during specific time periods and suggests adjustments to staffing accordingly.

[0339] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server to the user. Based on this, the user can efficiently perform tasks such as ordering, shift management, and customer service. Furthermore, by providing communication and services tailored to the user's emotions, the system aims to improve customer satisfaction.

[0340] As a concrete example, if the server detects a customer's negative emotions during peak hours, it will alert the user via their terminal and suggest improvements such as assigning additional staff. In this way, the system of the present invention enables increased efficiency and improved service in all aspects of store operations by integrating data-driven approaches with emotional data.

[0341] The following describes the processing flow.

[0342] Step 1:

[0343] The server collects sales history data and customer visitor data. Furthermore, it collects customer sentiment data through audio and video data acquired from users' devices.

[0344] Step 2:

[0345] The server builds a demand forecasting model based on collected sales history and customer data. This model includes analytical parameters that use positive customer sentiment as an indicator of increased demand.

[0346] Step 3:

[0347] The server generates inventory adjustment plans based on demand forecasts. In this process, if customer satisfaction is high based on sentiment data, it predicts increased demand and creates an adjustment plan to secure more inventory.

[0348] Step 4:

[0349] The terminal presents the generated inventory adjustment proposal to the user. The user reviews the proposal and places orders for products as needed.

[0350] Step 5:

[0351] The server analyzes visitor data and emotional data, optimizing staff allocation based on visit patterns and customer emotional states. If the emotional state is negative, it suggests additional staff allocation.

[0352] Step 6:

[0353] The terminal receives the calculated staffing plan and presents it to the user. The user adjusts staff shifts based on the presented plan to ensure optimal staffing.

[0354] Step 7:

[0355] The server analyzes customer sentiment data and, if there are many negative emotions, generates suggestions that include specific measures for service improvement.

[0356] Step 8:

[0357] The terminal provides users with service improvement suggestions, which users then use to modify their customer service and store management strategies.

[0358] In this way, the server integrates and analyzes diverse data, and presents appropriate operational strategies to users through terminals, thereby improving the efficiency of store operations and enhancing customer service.

[0359] (Example 2)

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

[0361] In store operations, relying solely on sales history and customer data is insufficient to accurately capture fluctuating consumer needs and customer emotional states, making it difficult to optimize inventory management and staffing. Furthermore, there is a lack of specific information needed to streamline customer service and improve customer satisfaction.

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

[0363] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing user emotions, and inventory adjustment means for generating inventory adjustment proposals using predicted demand data and sentiment data. This enables optimization of inventory management and staff allocation that takes into account fluctuations in consumer needs and customer emotional states, thereby improving the efficiency of store operations and enhancing service.

[0364] "Data acquisition means" refers to methods for collecting store-related information such as sales history and customer data.

[0365] A "demand forecasting tool" is a means of predicting the future demand for each product based on acquired data.

[0366] An "emotion analysis tool" is a method for analyzing a user's facial expressions and tone of voice to classify their emotional state.

[0367] "Inventory adjustment tools" are means of generating suggestions for adjusting inventory to optimal levels using predicted demand data and sentiment data.

[0368] "Information presentation means" refers to means for displaying generated inventory adjustment proposals and other data to the user.

[0369] A "customer visitor analysis method" is a means of acquiring customer data and analyzing that data to reveal customer visit patterns.

[0370] "Staff allocation optimization methods" are means of optimizing staff allocation based on customer visit data and emotional data, in order to achieve efficient personnel management.

[0371] "Information provision means" are means to support users in using the provided data to improve the efficiency of their work.

[0372] The embodiments for carrying out the present invention will now be described. This system is built to improve the efficiency of store operations by utilizing sales history and customer data, and consists of three elements: a server, a terminal, and a user.

[0373] The server collects sales history data and customer information through various sensors and input devices. Hardware includes, for example, cameras and microphones, while software algorithms such as "OpenFace" and "Prosody" are used. The data is first aggregated on the server, where it analyzes the user's facial expressions and voice tone to generate emotion data.

[0374] The server performs demand forecasting based on the acquired data. The demand forecasting algorithm utilizes machine learning models on "PyTorch" and "TensorFlow," which calculate the demand for products according to the time of year and generate inventory optimization plans. For example, if many positive emotions are recognized, demand is predicted to increase. This information is presented to the user via the terminal.

[0375] Furthermore, the server analyzes customer visit patterns and creates optimal staffing plans. Based on emotional data, it evaluates customer satisfaction during specific time periods and suggests staffing changes as needed. This information is also provided to users through their terminals, supporting them in making decisions regarding store operations.

[0376] As a concrete example, if the server detects negative customer emotions during peak hours, the terminal will issue a warning and recommend that the user allocate additional staff. This enables data-driven and emotion-based decision-making, contributing to more efficient store operations and improved service.

[0377] Examples of prompts for a generative AI model include, "Please provide details on demand forecasting using sales history and visit data," and "How can sentiment data be used to optimize staffing?" These prompts demonstrate the AI's ability to suggest specific information that the user needs.

[0378] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0379] Step 1:

[0380] The server collects sales history data and customer data through various sensors and input devices. Specifically, it obtains sales history from the POS system and records customer behavior using cameras installed in the store. Inputs include product sales information and the number of customers, and outputs that store this information in an integrated database.

[0381] Step 2:

[0382] The server receives and analyzes user emotion data transmitted from the terminal. Specifically, it uses data captured by cameras and audio sensors to analyze facial expressions and voice using algorithms such as "OpenFace" and "Prosody" to classify the emotional state. The input is the user's video and audio data, and the output is a score indicating the emotional state.

[0383] Step 3:

[0384] The server combines sales history data and sentiment data to forecast demand. This process utilizes machine learning algorithms, such as a model on TensorFlow, to analyze the data. The input is integrated sales history and sentiment data, and the output is the predicted demand for each product. Based on this forecast, the server generates inventory adjustment plans for the next period.

[0385] Step 4:

[0386] The server analyzes customer behavior patterns and generates optimal staffing plans. It combines customer visit data and sentiment data to provide staffing recommendations. Using customer visit time and frequency data as input, it provides suggestions on how staff should be allocated during specific time periods as output.

[0387] Step 5:

[0388] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results received from the server to the user. Based on this, the user can optimize orders and shifts, and revise customer service strategies. It receives information from the server as input and displays visual information on the terminal screen as output.

[0389] Step 6:

[0390] Users perform their actual tasks based on feedback from their devices. For example, if data indicates that customer sentiment deteriorates during peak hours, additional staff will be assigned to strengthen customer service. In this way, practical countermeasures can be taken by utilizing information from the server.

[0391] (Application Example 2)

[0392] 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."

[0393] In the modern real world, many brick-and-mortar stores are striving to improve the efficiency of inventory management and staffing, but systems that take customer emotions into account are not yet widespread. As a result, they face problems such as inaccurate demand forecasts and decreased customer satisfaction. To improve the customer experience while maximizing operational efficiency, it is necessary to optimize store operations by considering the emotional state of customers.

[0394] 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.

[0395] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing and classifying the emotional state of users, and business optimization means for dynamically adjusting staff allocation and service content using the sentiment analysis results. This makes it possible to optimize operations in accordance with customer emotions, thereby simultaneously achieving improved customer satisfaction and operational efficiency.

[0396] "Data acquisition means" refers to a device or process for collecting sales history, customer information, etc.

[0397] A "demand forecasting tool" is a device or process that has the function of calculating and forecasting future demand based on acquired data.

[0398] An "inventory adjustment device" is a device or process that has the function of appropriately adjusting inventory levels based on predicted demand.

[0399] An "emotional analysis tool" is a device or process that has the function of recognizing a user's emotional state, analyzing that information, and classifying it.

[0400] A "business optimization tool" is a device or process that has the function of dynamically adjusting staff allocation and service content using the results of sentiment analysis to optimize business efficiency.

[0401] "Information presentation means" refers to a device or process for displaying generated inventory adjustment proposals and business optimization details to the user.

[0402] "Visitor analysis means" refers to a device or process for analyzing visitor patterns based on visitor data.

[0403] A "means for reflecting emotional data" refers to a device or process that has the function of reflecting emotional data analyzed in real time into store operations.

[0404] A "staff allocation optimization method" is a device or process that has the function of achieving efficient staff allocation based on customer visit data and sentiment data.

[0405] To implement this invention, the server first utilizes data acquisition means to collect sales history and customer information. The data is acquired via hardware such as cameras, sensors, and register recording systems installed within the commercial store. This allows for the collection of information such as which products were sold and in what quantities, and which times of day see the most customers.

[0406] Next, the server uses emotion analysis software such as EmotionRecognizer to analyze the customer's facial expressions and tone of voice to determine their emotional state. Specifically, it captures the user's emotions in real time through smartphones and cameras and microphones on robots installed in the store, and processes this data using an analysis algorithm. This process analyzes that if there are many positive emotions, demand tends to increase.

[0407] Based on these analysis results, the server generates suggestions for dynamically adjusting staffing and service content using operational optimization tools. For example, if customer frustration is detected during peak hours, the server sends a notification to the terminal, prompting the deployment of additional staff or the provision of alternative services. The store terminal uses the inventory adjustment suggestions, staffing suggestions, and sentiment analysis results sent from the server to present users with instructions and options.

[0408] For example, if many customers are showing signs of frustration on a Friday afternoon, the server will analyze the emotional data, send notifications to staff, and suggest adding additional staff to improve customer satisfaction. In this way, the server can integrate data and emotional information and utilize it in all aspects of store operations.

[0409] An example of a prompt given to a generative AI model is, "If the majority of customers who visited on Friday afternoon showed signs of frustration, what measures would be effective?" It is expected that the AI ​​will then suggest appropriate actions based on this prompt.

[0410] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0411] Step 1:

[0412] The server collects sales history data and customer data from cameras, sensors, and cash registers installed within the store. Inputs include the number of items sold and time information of customers who visited the store, and the output is a dataset in which this data is organized.

[0413] Step 2:

[0414] The server uses EmotionRecognizer to perform emotion analysis using customer video and audio data acquired from smartphones and in-store robots. The input includes customer facial expressions and voice data, which are processed by an analysis algorithm to output evaluation results classifying the customer's emotional state.

[0415] Step 3:

[0416] The server integrates sales history data, customer data, and sentiment analysis results to forecast demand. All data is included as input, and statistical models and machine learning algorithms are used to predict demand, outputting forecast data useful for inventory management.

[0417] Step 4:

[0418] Subsequently, the server optimizes operations based on the results of the sentiment analysis. In particular, it generates adjustments to staff allocation and suggestions for additional services. The inputs include customer sentiment data and visit patterns, and these are used to output the optimal staff allocation plan.

[0419] Step 5:

[0420] The terminal presents the user with inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server. Based on the input, it provides visual information to the user on the user interface, and the output is information designed to facilitate the user's decision-making.

[0421] Step 6:

[0422] Users efficiently perform tasks such as taking orders, managing shifts, and handling customer service based on suggestions provided through the terminal. Input consists of suggested ideas and instructions, and by performing practical operations based on these, the system outputs results that improve the overall operational efficiency of the store.

[0423] 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.

[0424] 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.

[0425] 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.

[0426] [Third Embodiment]

[0427] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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).

[0433] 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.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] 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.

[0438] 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".

[0439] This invention is a system designed to streamline inventory management, shift management, and campaign planning in retail stores. This system primarily consists of a server, terminals, and users, and its specific embodiments are described below.

[0440] First, the server automatically collects and stores diverse information, such as sales history and customer data. This allows it to always have access to the latest business environment information. Next, the server uses advanced algorithms to forecast demand based on the collected data. Through this process, the server can accurately estimate the future demand for each product.

[0441] Furthermore, the server utilizes the predicted demand data to create efficient inventory adjustment plans. These plans are presented to the user via a terminal, allowing the user to manage ordering appropriately based on them. As a result, users can prevent problems such as excess inventory and stockouts, and reduce operating costs.

[0442] The analysis of customer data is also performed automatically by the server. By understanding customer patterns, the server can plan optimal staffing during expected busy times and propose shift plans to users via terminals. This function improves the efficiency of staffing in store operations, making it possible to reduce the burden on staff while maintaining service quality.

[0443] Furthermore, the server analyzes past campaign data to develop the most effective promotional methods. This system automatically suggests appropriate campaigns via the terminal and presents an implementation schedule to the user. Based on the suggested strategies, users can then develop more effective marketing activities.

[0444] For example, if the server predicts a surge in demand for a particular product, the terminal will notify the user early and urge them to secure the necessary stock. Also, if the number of visitors is expected to peak on weekends, the server will suggest a shift plan to the user, such as allocating additional staff. Furthermore, if a particular campaign proves highly successful, the server will leverage that knowledge to automatically optimize the next promotional strategy.

[0445] These functions enable the present invention to comprehensively support the operation of retail stores, thereby improving operational efficiency and customer satisfaction.

[0446] The following describes the processing flow.

[0447] Step 1:

[0448] The server automatically acquires sales history data, customer count data, and other related data from various sensors and input systems. This step involves collecting and storing the latest information in the database.

[0449] Step 2:

[0450] The server analyzes the acquired data and uses machine learning models to predict future demand for each product. This involves techniques such as time series analysis and regression analysis. Based on the results of this analysis, demand forecast data is generated.

[0451] Step 3:

[0452] The server generates inventory adjustment plans based on demand forecast data. Specifically, it calculates order quantities according to the predicted demand and optimizes inventory levels. These adjustment plans are used in subsequent steps.

[0453] Step 4:

[0454] The terminal receives inventory adjustment proposals sent from the server and presents them visually to the user. The user reviews the presented information and places orders as needed, thereby supporting inventory management.

[0455] Step 5:

[0456] The server uses customer data to analyze customer patterns and predict congestion levels. Based on the algorithms used, it predicts future congestion and plans optimal staffing arrangements.

[0457] Step 6:

[0458] The terminal receives shift proposals calculated by the server and presents them to the user, suggesting a shift management plan. The user reviews the proposed shifts and makes adjustments as needed to determine staff allocation.

[0459] Step 7:

[0460] The server analyzes campaign data and automatically generates a new campaign strategy based on the effectiveness of past promotions. This strategy includes details such as the products to be applied to, the discount rate, and the duration of the campaign.

[0461] Step 8:

[0462] The terminal presents the generated campaign plan to the user and suggests an implementation schedule. Based on the presented campaign strategy, the user develops efficient promotional activities.

[0463] This series of processing steps allows servers, terminals, and users to work together to streamline the operation of retail stores.

[0464] (Example 1)

[0465] 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."

[0466] Retail stores are required to effectively utilize sales history and customer data to streamline demand forecasting, inventory management, staffing, and campaign strategies. However, the lack of sufficient integration of this data is leading to problems such as lost sales opportunities, wasted staffing, and ineffective campaigns. It is necessary to address these issues to improve store operations efficiency and enhance customer satisfaction.

[0467] 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.

[0468] In this invention, the server includes information gathering means for acquiring sales history and related data, forecasting calculation means for predicting the demand for each product based on the acquired information, and personnel allocation means for analyzing customer trends and planning the optimal staffing arrangement. This improves the accuracy of demand forecasting and enables the optimization of inventory management and efficient personnel allocation planning.

[0469] "Information gathering means" refers to a function that efficiently acquires sales history and related data and stores that information on a server.

[0470] A "predictive calculation means" is a function that predicts future demand for each product based on acquired data and formulates optimal sales and inventory strategies based on the analysis results.

[0471] "Resource management tools" refer to functions that use predicted demand data to generate inventory adjustment plans and maintain appropriate inventory levels.

[0472] A "data presentation method" is a function that displays generated inventory adjustment proposals and personnel allocation plans, presenting them in a way that is easy for users to understand.

[0473] "Personnel allocation methods" refer to functions that improve the efficiency of store operations by analyzing customer trends and planning the optimal allocation of staff.

[0474] "Promotional activity support tools" refer to functions that analyze past sales promotion activity information and support the development and implementation of effective promotion strategies.

[0475] The "analysis and presentation means" is a function that creates a staffing plan based on the results of customer trends and provides information related to it.

[0476] The "activity suggestion tool" is a function that optimizes promotional activities based on analyzed sales and customer visitor information, and provides efficient suggestions to users.

[0477] This invention is a system aimed at improving the operational efficiency of retail stores. This system consists of a server, terminals, and users as its main components, and optimizes demand forecasting, inventory management, staffing, and campaign strategies by linking various data.

[0478] First, the server uses information gathering tools to collect store sales history, customer information, and other data. This data is retrieved via a RESTful API and stored in a data management system, which is a multi-purpose database software.

[0479] Next, the server uses predictive computation to forecast the future demand for each product based on the collected data. This process utilizes the data analysis library pandas and the machine learning library scikit-learn. By employing sophisticated algorithms, precise predictions become possible.

[0480] The server further analyzes customer trends using staffing methods and plans the optimal staffing arrangement. This analysis utilizes big data processing tools on a cloud service, and the analysis results are sent to terminals for the user to receive.

[0481] The terminal displays generated inventory adjustment proposals and shift plans to the user through a data presentation system. Based on the presented information, the user can place orders and adjust staff schedules.

[0482] Furthermore, the server's promotional support tools analyze past campaign results and formulate future promotional strategies. This function uses data visualization tools to analyze results and automatically derive effective strategies.

[0483] For example, if the server predicts an increase in sales of a particular product, the terminal will display a notification prompting the user to place an early order to secure inventory. Also, if an increase in the number of visitors is predicted during a specific time period, the server will plan the deployment of additional staff and propose this to the user via the terminal. Furthermore, if past campaigns have been highly successful, that data can be used to automatically adjust future promotional strategies.

[0484] An example of a prompt message is, "Please provide the results of a demand forecast based on historical sales data to determine if a particular product is suitable for the next campaign."

[0485] This system provides comprehensive support for retail store operations, resulting in a significant improvement in operational efficiency and maximizing customer satisfaction.

[0486] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0487] Step 1:

[0488] The server uses data collection tools to retrieve sales history and customer information from the POS systems of retail stores. This input data is aggregated via a RESTful API and stored in a data management system. This ensures that the necessary information is always up-to-date.

[0489] Step 2:

[0490] The server uses predictive computation methods to forecast demand based on collected sales history data and customer information. The input data is formatted using the pandas library and fed into a machine learning model using scikit-learn. The output is the predicted demand value for each product. The predicted data is updated periodically to improve accuracy.

[0491] Step 3:

[0492] The server uses resource management tools to generate inventory adjustment proposals from predicted demand data. Based on the demand data as input, a linear programming algorithm calculates the optimal order quantity. The output of this process is the recommended inventory level for each product.

[0493] Step 4:

[0494] The terminal displays inventory adjustment proposals sent from the server to the user via a data presentation mechanism. Specifically, a pop-up notification appears on the terminal's display, allowing the user to place an order based on it.

[0495] Step 5:

[0496] The server uses staffing methods to analyze customer data and plan the optimal staffing arrangement. The input data is processed by a big data processing tool, and congestion predictions are output as analysis results. This ensures that the appropriate number of staff are allocated during the necessary time periods.

[0497] Step 6:

[0498] The terminal presents the user with specific shift plans based on analysis results from the server. The user can then use this as a reference to adjust staff schedules.

[0499] Step 7:

[0500] The server uses promotional support tools to analyze past campaign data and develop effective promotional strategies. Based on the collected campaign data, data analysis is performed using visualization tools, and new campaign proposals are generated as output.

[0501] Step 8:

[0502] Users can improve operational efficiency and increase customer satisfaction by reviewing proposed inventory adjustments and campaign plans through their devices and making necessary changes.

[0503] (Application Example 1)

[0504] 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."

[0505] In modern sales operations, inventory management, customer visit pattern analysis, and staffing are crucial, but their efficient implementation requires significant time and effort. Furthermore, traditional methods fail to fully utilize sales history and visit patterns, making rapid response difficult. Additionally, stores struggle to grasp the current situation in real time, posing a major obstacle to determining appropriate inventory levels and staffing.

[0506] 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.

[0507] In this invention, the server includes data acquisition means for acquiring sales history and related information, demand forecasting means for predicting demand for each product group based on the acquired information, inventory adjustment means for generating an inventory adjustment plan using the predicted demand information, information presentation means for presenting and guiding customers through the generated inventory adjustment plan, and image analysis means for analyzing photographic data and evaluating the current situation. This improves the efficiency of inventory management, visitor analysis, and staff allocation, enabling rapid decision-making in physical store operations.

[0508] "Sales history" refers to information about all sales activities that have taken place at a store in the past, and includes data such as the type of product, quantity, and date of sale.

[0509] "Relevant information" refers to all data that affects inventory management and store operations, in addition to sales history, and includes, for example, weather information and local event information.

[0510] "Data acquisition means" refers to a mechanism for collecting necessary information and data, and includes a system that incorporates methods for obtaining information from sensors and databases.

[0511] "Demand forecasting tools" refer to algorithms and processes for analyzing past data to estimate and predict future demand.

[0512] "Inventory adjustment measures" refer to the function of determining the appropriate inventory level based on predicted demand and formulating plans to prevent excess inventory and stockouts.

[0513] "Information presentation means" refers to user interfaces and devices that display important information to store staff in an easy-to-understand manner and support decision-making.

[0514] "Photo data" refers to visual information acquired as an image, and is a digital image file used to check the condition of products, their display, etc.

[0515] "Image analysis means" refers to the process of extracting meaningful information from a photograph, and is a technology for recognizing features within an image and deriving analysis results.

[0516] The system that realizes this invention consists of a server, a terminal, and a user.

[0517] The server is built using the Flask framework in Python and uses PostgreSQL as its database. The server automatically collects sales history and visitor information and analyzes it to forecast demand. A demand forecasting model trained with Scikit-learn is used for demand forecasting. This model is based on a random forest and uses sales history and related information as input to predict future demand with high accuracy.

[0518] The device is used as a smartphone or tablet and provides an interface for user access. The device receives inventory adjustment proposals and campaign suggestions sent from the server and presents them to the user. Since the user interface is represented through a web browser, the device can utilize all the functions of the present invention simply by opening a specific web page.

[0519] Users can receive information from the server via their terminals, allowing them to, for example, check inventory levels and determine optimal order quantities. Users can also manage store shifts and optimize staff allocation based on customer traffic forecast data from the server.

[0520] As a concrete example, a user can take a picture of the current inventory status with their device and send the photo to the server. The server analyzes this photo data and makes demand forecasts based on the image. An example of a prompt message might be: "The inventory of product A is decreasing. Send a photo to check inventory and receive order suggestions."

[0521] As a result, inventory management, shift management, and campaign planning in physical stores can be carried out efficiently, leading to optimized operations and improved customer service.

[0522] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0523] Step 1:

[0524] The server acquires sales history and related information. Using data acquisition methods, it automatically collects necessary information from databases and sensors and stores it. The acquired data is used as input for a predictive model.

[0525] Step 2:

[0526] The server uses the acquired data to perform demand forecasting using a generative AI model. Using Scikit-learn's Random Forest, it analyzes sales history and related information to predict future demand for each product group. These forecast results serve as the basis for generating inventory adjustment proposals.

[0527] Step 3:

[0528] The server develops an inventory adjustment plan based on predicted demand data. Using inventory adjustment tools, it calculates the order quantities needed to prevent excess inventory and stockouts, and sends the results to the terminal. This plan serves as a guideline to streamline the user's ordering process.

[0529] Step 4:

[0530] The terminal presents the user with inventory adjustment proposals sent from the server. Using an information presentation system, it clearly displays the necessary information through a user-friendly interface. Based on this information, the user can make quick decisions.

[0531] Step 5:

[0532] The user sends current inventory information to the server via a photograph through their device. The device's built-in camera captures the information, and the photograph is sent to the server as digital data. This data is then analyzed using image analysis tools.

[0533] Step 6:

[0534] The server performs image analysis based on the transmitted photo data. Using an image analysis model, it analyzes the number of products, their display status, etc., and evaluates the current inventory status based on this. The results are used as a reference for more detailed inventory adjustments.

[0535] Step 7:

[0536] Users can check visitor information via their devices and optimize shifts. The system analyzes visitor data and forecast data provided by the server to plan optimal staffing. This enables efficient staffing while maintaining the store's service level.

[0537] 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.

[0538] This invention combines a system that utilizes sales history and customer data to improve the efficiency of inventory management and staff allocation with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user.

[0539] First, the server uses various sensors and input systems to acquire sales history data and customer data, and simultaneously acquires user emotion data through terminals. Next, the server integrates this data to create a dataset for analysis. For emotion recognition, a specific algorithm is used to analyze the user's facial expressions and tone of voice and classify their emotional state.

[0540] Based on the acquired data, the server performs demand forecasting and optimizes inventory management. By incorporating user sentiment data into the analysis, more precise demand forecasting is achieved. In this process, it is estimated that demand may increase if a large number of positive emotions are recognized.

[0541] The server also analyzes customer visit data and generates optimized staffing plans based on customer patterns. It uses emotional data to evaluate customer satisfaction during specific time periods and suggests adjustments to staffing accordingly.

[0542] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server to the user. Based on this, the user can efficiently perform tasks such as ordering, shift management, and customer service. Furthermore, by providing communication and services tailored to the user's emotions, the system aims to improve customer satisfaction.

[0543] As a concrete example, if the server detects a customer's negative emotions during peak hours, it will alert the user via their terminal and suggest improvements such as assigning additional staff. In this way, the system of the present invention enables increased efficiency and improved service in all aspects of store operations by integrating data-driven approaches with emotional data.

[0544] The following describes the processing flow.

[0545] Step 1:

[0546] The server collects sales history data and customer visitor data. Furthermore, it collects customer sentiment data through audio and video data acquired from users' devices.

[0547] Step 2:

[0548] The server builds a demand forecasting model based on collected sales history and customer data. This model includes analytical parameters that use positive customer sentiment as an indicator of increased demand.

[0549] Step 3:

[0550] The server generates inventory adjustment plans based on demand forecasts. In this process, if customer satisfaction is high based on sentiment data, it predicts increased demand and creates an adjustment plan to secure more inventory.

[0551] Step 4:

[0552] The terminal presents the generated inventory adjustment proposal to the user. The user reviews the proposal and places orders for products as needed.

[0553] Step 5:

[0554] The server analyzes visitor data and emotional data, optimizing staff allocation based on visit patterns and customer emotional states. If the emotional state is negative, it suggests additional staff allocation.

[0555] Step 6:

[0556] The terminal receives the calculated staffing plan and presents it to the user. The user adjusts staff shifts based on the presented plan to ensure optimal staffing.

[0557] Step 7:

[0558] The server analyzes customer sentiment data and, if there are many negative emotions, generates suggestions that include specific measures for service improvement.

[0559] Step 8:

[0560] The terminal provides users with service improvement suggestions, which users then use to modify their customer service and store management strategies.

[0561] In this way, the server integrates and analyzes diverse data, and presents appropriate operational strategies to users through terminals, thereby improving the efficiency of store operations and enhancing customer service.

[0562] (Example 2)

[0563] 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."

[0564] In store operations, relying solely on sales history and customer data is insufficient to accurately capture fluctuating consumer needs and customer emotional states, making it difficult to optimize inventory management and staffing. Furthermore, there is a lack of specific information needed to streamline customer service and improve customer satisfaction.

[0565] 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.

[0566] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing user emotions, and inventory adjustment means for generating inventory adjustment proposals using predicted demand data and sentiment data. This enables optimization of inventory management and staff allocation that takes into account fluctuations in consumer needs and customer emotional states, thereby improving the efficiency of store operations and enhancing service.

[0567] "Data acquisition means" refers to methods for collecting store-related information such as sales history and customer data.

[0568] A "demand forecasting tool" is a means of predicting the future demand for each product based on acquired data.

[0569] An "emotion analysis tool" is a method for analyzing a user's facial expressions and tone of voice to classify their emotional state.

[0570] "Inventory adjustment tools" are means of generating suggestions for adjusting inventory to optimal levels using predicted demand data and sentiment data.

[0571] "Information presentation means" refers to means for displaying generated inventory adjustment proposals and other data to the user.

[0572] A "customer visitor analysis method" is a means of acquiring customer data and analyzing that data to reveal customer visit patterns.

[0573] "Staff allocation optimization methods" are means of optimizing staff allocation based on customer visit data and emotional data, in order to achieve efficient personnel management.

[0574] "Information provision means" are means to support users in using the provided data to improve the efficiency of their work.

[0575] The embodiments for carrying out the present invention will now be described. This system is built to improve the efficiency of store operations by utilizing sales history and customer data, and consists of three elements: a server, a terminal, and a user.

[0576] The server collects sales history data and customer information through various sensors and input devices. Hardware includes, for example, cameras and microphones, while software algorithms such as "OpenFace" and "Prosody" are used. The data is first aggregated on the server, where it analyzes the user's facial expressions and voice tone to generate emotion data.

[0577] The server performs demand forecasting based on the acquired data. The demand forecasting algorithm utilizes machine learning models on "PyTorch" and "TensorFlow," which calculate the demand for products according to the time of year and generate inventory optimization plans. For example, if many positive emotions are recognized, demand is predicted to increase. This information is presented to the user via the terminal.

[0578] Furthermore, the server analyzes customer visit patterns and creates optimal staffing plans. Based on emotional data, it evaluates customer satisfaction during specific time periods and suggests staffing changes as needed. This information is also provided to users through their terminals, supporting them in making decisions regarding store operations.

[0579] As a concrete example, if the server detects negative customer emotions during peak hours, the terminal will issue a warning and recommend that the user allocate additional staff. This enables data-driven and emotion-based decision-making, contributing to more efficient store operations and improved service.

[0580] Examples of prompts for a generative AI model include, "Please provide details on demand forecasting using sales history and visit data," and "How can sentiment data be used to optimize staffing?" These prompts demonstrate the AI's ability to suggest specific information that the user needs.

[0581] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0582] Step 1:

[0583] The server collects sales history data and customer data through various sensors and input devices. Specifically, it obtains sales history from the POS system and records customer behavior using cameras installed in the store. Inputs include product sales information and the number of customers, and outputs that store this information in an integrated database.

[0584] Step 2:

[0585] The server receives and analyzes user emotion data transmitted from the terminal. Specifically, it uses data captured by cameras and audio sensors to analyze facial expressions and voice using algorithms such as "OpenFace" and "Prosody" to classify the emotional state. The input is the user's video and audio data, and the output is a score indicating the emotional state.

[0586] Step 3:

[0587] The server combines sales history data and sentiment data to forecast demand. This process utilizes machine learning algorithms, such as a model on TensorFlow, to analyze the data. The input is integrated sales history and sentiment data, and the output is the predicted demand for each product. Based on this forecast, the server generates inventory adjustment plans for the next period.

[0588] Step 4:

[0589] The server analyzes customer behavior patterns and generates optimal staffing plans. It combines customer visit data and sentiment data to provide staffing recommendations. Using customer visit time and frequency data as input, it provides suggestions on how staff should be allocated during specific time periods as output.

[0590] Step 5:

[0591] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results received from the server to the user. Based on this, the user can optimize orders and shifts, and revise customer service strategies. It receives information from the server as input and displays visual information on the terminal screen as output.

[0592] Step 6:

[0593] Users perform their actual tasks based on feedback from their devices. For example, if data indicates that customer sentiment deteriorates during peak hours, additional staff will be assigned to strengthen customer service. In this way, practical countermeasures can be taken by utilizing information from the server.

[0594] (Application Example 2)

[0595] 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."

[0596] In the modern real world, many brick-and-mortar stores are striving to improve the efficiency of inventory management and staffing, but systems that take customer emotions into account are not yet widespread. As a result, they face problems such as inaccurate demand forecasts and decreased customer satisfaction. To improve the customer experience while maximizing operational efficiency, it is necessary to optimize store operations by considering the emotional state of customers.

[0597] 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.

[0598] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing and classifying the emotional state of users, and business optimization means for dynamically adjusting staff allocation and service content using the sentiment analysis results. This makes it possible to optimize operations in accordance with customer emotions, thereby simultaneously achieving improved customer satisfaction and operational efficiency.

[0599] "Data acquisition means" refers to a device or process for collecting sales history, customer information, etc.

[0600] A "demand forecasting tool" is a device or process that has the function of calculating and forecasting future demand based on acquired data.

[0601] An "inventory adjustment device" is a device or process that has the function of appropriately adjusting inventory levels based on predicted demand.

[0602] An "emotional analysis tool" is a device or process that has the function of recognizing a user's emotional state, analyzing that information, and classifying it.

[0603] A "business optimization tool" is a device or process that has the function of dynamically adjusting staff allocation and service content using the results of sentiment analysis to optimize business efficiency.

[0604] "Information presentation means" refers to a device or process for displaying generated inventory adjustment proposals and business optimization details to the user.

[0605] "Visitor analysis means" refers to a device or process for analyzing visitor patterns based on visitor data.

[0606] A "means for reflecting emotional data" refers to a device or process that has the function of reflecting emotional data analyzed in real time into store operations.

[0607] A "staff allocation optimization method" is a device or process that has the function of achieving efficient staff allocation based on customer visit data and sentiment data.

[0608] To implement this invention, the server first utilizes data acquisition means to collect sales history and customer information. The data is acquired via hardware such as cameras, sensors, and register recording systems installed within the commercial store. This allows for the collection of information such as which products were sold and in what quantities, and which times of day see the most customers.

[0609] Next, the server uses emotion analysis software such as EmotionRecognizer to analyze the customer's facial expressions and tone of voice to determine their emotional state. Specifically, it captures the user's emotions in real time through smartphones and cameras and microphones on robots installed in the store, and processes this data using an analysis algorithm. This process analyzes that if there are many positive emotions, demand tends to increase.

[0610] Based on these analysis results, the server generates suggestions for dynamically adjusting staffing and service content using operational optimization tools. For example, if customer frustration is detected during peak hours, the server sends a notification to the terminal, prompting the deployment of additional staff or the provision of alternative services. The store terminal uses the inventory adjustment suggestions, staffing suggestions, and sentiment analysis results sent from the server to present users with instructions and options.

[0611] For example, if many customers are showing signs of frustration on a Friday afternoon, the server will analyze the emotional data, send notifications to staff, and suggest adding additional staff to improve customer satisfaction. In this way, the server can integrate data and emotional information and utilize it in all aspects of store operations.

[0612] An example of a prompt given to a generative AI model is, "If the majority of customers who visited on Friday afternoon showed signs of frustration, what measures would be effective?" It is expected that the AI ​​will then suggest appropriate actions based on this prompt.

[0613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0614] Step 1:

[0615] The server collects sales history data and customer data from cameras, sensors, and cash registers installed within the store. Inputs include the number of items sold and time information of customers who visited the store, and the output is a dataset in which this data is organized.

[0616] Step 2:

[0617] The server uses EmotionRecognizer to perform emotion analysis using customer video and audio data acquired from smartphones and in-store robots. The input includes customer facial expressions and voice data, which are processed by an analysis algorithm to output evaluation results classifying the customer's emotional state.

[0618] Step 3:

[0619] The server integrates sales history data, customer data, and sentiment analysis results to forecast demand. All data is included as input, and statistical models and machine learning algorithms are used to predict demand, outputting forecast data useful for inventory management.

[0620] Step 4:

[0621] Subsequently, the server optimizes operations based on the results of the sentiment analysis. In particular, it generates adjustments to staff allocation and suggestions for additional services. The inputs include customer sentiment data and visit patterns, and these are used to output the optimal staff allocation plan.

[0622] Step 5:

[0623] The terminal presents the user with inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server. Based on the input, it provides visual information to the user on the user interface, and the output is information designed to facilitate the user's decision-making.

[0624] Step 6:

[0625] Users efficiently perform tasks such as taking orders, managing shifts, and handling customer service based on suggestions provided through the terminal. Input consists of suggested ideas and instructions, and by performing practical operations based on these, the system outputs results that improve the overall operational efficiency of the store.

[0626] 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.

[0627] 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.

[0628] 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.

[0629] [Fourth Embodiment]

[0630] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0631] 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.

[0632] 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).

[0633] 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.

[0634] 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.

[0635] 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).

[0636] 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.

[0637] 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.

[0638] 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.

[0639] 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.

[0640] 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.

[0641] 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.

[0642] 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".

[0643] This invention is a system designed to streamline inventory management, shift management, and campaign planning in retail stores. This system primarily consists of a server, terminals, and users, and its specific embodiments are described below.

[0644] First, the server automatically collects and stores diverse information, such as sales history and customer data. This allows it to always have access to the latest business environment information. Next, the server uses advanced algorithms to forecast demand based on the collected data. Through this process, the server can accurately estimate the future demand for each product.

[0645] Furthermore, the server utilizes the predicted demand data to create efficient inventory adjustment plans. These plans are presented to the user via a terminal, allowing the user to manage ordering appropriately based on them. As a result, users can prevent problems such as excess inventory and stockouts, and reduce operating costs.

[0646] The analysis of customer data is also performed automatically by the server. By understanding customer patterns, the server can plan optimal staffing during expected busy times and propose shift plans to users via terminals. This function improves the efficiency of staffing in store operations, making it possible to reduce the burden on staff while maintaining service quality.

[0647] Furthermore, the server analyzes past campaign data to develop the most effective promotional methods. This system automatically suggests appropriate campaigns via the terminal and presents an implementation schedule to the user. Based on the suggested strategies, users can then develop more effective marketing activities.

[0648] For example, if the server predicts a surge in demand for a particular product, the terminal will notify the user early and urge them to secure the necessary stock. Also, if the number of visitors is expected to peak on weekends, the server will suggest a shift plan to the user, such as allocating additional staff. Furthermore, if a particular campaign proves highly successful, the server will leverage that knowledge to automatically optimize the next promotional strategy.

[0649] These functions enable the present invention to comprehensively support the operation of retail stores, thereby improving operational efficiency and customer satisfaction.

[0650] The following describes the processing flow.

[0651] Step 1:

[0652] The server automatically acquires sales history data, customer count data, and other related data from various sensors and input systems. This step involves collecting and storing the latest information in the database.

[0653] Step 2:

[0654] The server analyzes the acquired data and uses machine learning models to predict future demand for each product. This involves techniques such as time series analysis and regression analysis. Based on the results of this analysis, demand forecast data is generated.

[0655] Step 3:

[0656] The server generates inventory adjustment plans based on demand forecast data. Specifically, it calculates order quantities according to the predicted demand and optimizes inventory levels. These adjustment plans are used in subsequent steps.

[0657] Step 4:

[0658] The terminal receives inventory adjustment proposals sent from the server and presents them visually to the user. The user reviews the presented information and places orders as needed, thereby supporting inventory management.

[0659] Step 5:

[0660] The server uses customer data to analyze customer patterns and predict congestion levels. Based on the algorithms used, it predicts future congestion and plans optimal staffing arrangements.

[0661] Step 6:

[0662] The terminal receives shift proposals calculated by the server and presents them to the user, suggesting a shift management plan. The user reviews the proposed shifts and makes adjustments as needed to determine staff allocation.

[0663] Step 7:

[0664] The server analyzes campaign data and automatically generates a new campaign strategy based on the effectiveness of past promotions. This strategy includes details such as the products to be applied to, the discount rate, and the duration of the campaign.

[0665] Step 8:

[0666] The terminal presents the generated campaign plan to the user and suggests an implementation schedule. Based on the presented campaign strategy, the user develops efficient promotional activities.

[0667] This series of processing steps allows servers, terminals, and users to work together to streamline the operation of retail stores.

[0668] (Example 1)

[0669] 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".

[0670] Retail stores are required to effectively utilize sales history and customer data to streamline demand forecasting, inventory management, staffing, and campaign strategies. However, the lack of sufficient integration of this data is leading to problems such as lost sales opportunities, wasted staffing, and ineffective campaigns. It is necessary to address these issues to improve store operations efficiency and enhance customer satisfaction.

[0671] 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.

[0672] In this invention, the server includes information gathering means for acquiring sales history and related data, forecasting calculation means for predicting the demand for each product based on the acquired information, and personnel allocation means for analyzing customer trends and planning the optimal staffing arrangement. This improves the accuracy of demand forecasting and enables the optimization of inventory management and efficient personnel allocation planning.

[0673] "Information gathering means" refers to a function that efficiently acquires sales history and related data and stores that information on a server.

[0674] A "predictive calculation means" is a function that predicts future demand for each product based on acquired data and formulates optimal sales and inventory strategies based on the analysis results.

[0675] "Resource management tools" refer to functions that use predicted demand data to generate inventory adjustment plans and maintain appropriate inventory levels.

[0676] A "data presentation method" is a function that displays generated inventory adjustment proposals and personnel allocation plans, presenting them in a way that is easy for users to understand.

[0677] "Personnel allocation methods" refer to functions that improve the efficiency of store operations by analyzing customer trends and planning the optimal allocation of staff.

[0678] "Promotional activity support tools" refer to functions that analyze past sales promotion activity information and support the development and implementation of effective promotion strategies.

[0679] The "analysis and presentation means" is a function that creates a staffing plan based on the results of customer trends and provides information related to it.

[0680] The "activity suggestion tool" is a function that optimizes promotional activities based on analyzed sales and customer visitor information, and provides efficient suggestions to users.

[0681] This invention is a system aimed at improving the operational efficiency of retail stores. This system consists of a server, terminals, and users as its main components, and optimizes demand forecasting, inventory management, staffing, and campaign strategies by linking various data.

[0682] First, the server uses information gathering tools to collect store sales history, customer information, and other data. This data is retrieved via a RESTful API and stored in a data management system, which is a multi-purpose database software.

[0683] Next, the server uses predictive computation to forecast the future demand for each product based on the collected data. This process utilizes the data analysis library pandas and the machine learning library scikit-learn. By employing sophisticated algorithms, precise predictions become possible.

[0684] The server further analyzes customer trends using staffing methods and plans the optimal staffing arrangement. This analysis utilizes big data processing tools on a cloud service, and the analysis results are sent to terminals for the user to receive.

[0685] The terminal displays generated inventory adjustment proposals and shift plans to the user through a data presentation system. Based on the presented information, the user can place orders and adjust staff schedules.

[0686] Furthermore, the server's promotional support tools analyze past campaign results and formulate future promotional strategies. This function uses data visualization tools to analyze results and automatically derive effective strategies.

[0687] For example, if the server predicts an increase in sales of a particular product, the terminal will display a notification prompting the user to place an early order to secure inventory. Also, if an increase in the number of visitors is predicted during a specific time period, the server will plan the deployment of additional staff and propose this to the user via the terminal. Furthermore, if past campaigns have been highly successful, that data can be used to automatically adjust future promotional strategies.

[0688] An example of a prompt message is, "Please provide the results of a demand forecast based on historical sales data to determine if a particular product is suitable for the next campaign."

[0689] This system provides comprehensive support for retail store operations, resulting in a significant improvement in operational efficiency and maximizing customer satisfaction.

[0690] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0691] Step 1:

[0692] The server uses data collection tools to retrieve sales history and customer information from the POS systems of retail stores. This input data is aggregated via a RESTful API and stored in a data management system. This ensures that the necessary information is always up-to-date.

[0693] Step 2:

[0694] The server uses predictive computation methods to forecast demand based on collected sales history data and customer information. The input data is formatted using the pandas library and fed into a machine learning model using scikit-learn. The output is the predicted demand value for each product. The predicted data is updated periodically to improve accuracy.

[0695] Step 3:

[0696] The server uses resource management tools to generate inventory adjustment proposals from predicted demand data. Based on the demand data as input, a linear programming algorithm calculates the optimal order quantity. The output of this process is the recommended inventory level for each product.

[0697] Step 4:

[0698] The terminal displays inventory adjustment proposals sent from the server to the user via a data presentation mechanism. Specifically, a pop-up notification appears on the terminal's display, allowing the user to place an order based on it.

[0699] Step 5:

[0700] The server uses staffing methods to analyze customer data and plan the optimal staffing arrangement. The input data is processed by a big data processing tool, and congestion predictions are output as analysis results. This ensures that the appropriate number of staff are allocated during the necessary time periods.

[0701] Step 6:

[0702] The terminal presents the user with specific shift plans based on analysis results from the server. The user can then use this as a reference to adjust staff schedules.

[0703] Step 7:

[0704] The server uses promotional support tools to analyze past campaign data and develop effective promotional strategies. Based on the collected campaign data, data analysis is performed using visualization tools, and new campaign proposals are generated as output.

[0705] Step 8:

[0706] Users can improve operational efficiency and increase customer satisfaction by reviewing proposed inventory adjustments and campaign plans through their devices and making necessary changes.

[0707] (Application Example 1)

[0708] 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".

[0709] In modern sales operations, inventory management, customer visit pattern analysis, and staffing are crucial, but their efficient implementation requires significant time and effort. Furthermore, traditional methods fail to fully utilize sales history and visit patterns, making rapid response difficult. Additionally, stores struggle to grasp the current situation in real time, posing a major obstacle to determining appropriate inventory levels and staffing.

[0710] 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.

[0711] In this invention, the server includes data acquisition means for acquiring sales history and related information, demand forecasting means for predicting demand for each product group based on the acquired information, inventory adjustment means for generating an inventory adjustment plan using the predicted demand information, information presentation means for presenting and guiding customers through the generated inventory adjustment plan, and image analysis means for analyzing photographic data and evaluating the current situation. This improves the efficiency of inventory management, visitor analysis, and staff allocation, enabling rapid decision-making in physical store operations.

[0712] "Sales history" refers to information about all sales activities that have taken place at a store in the past, and includes data such as the type of product, quantity, and date of sale.

[0713] "Relevant information" refers to all data that affects inventory management and store operations, in addition to sales history, and includes, for example, weather information and local event information.

[0714] "Data acquisition means" refers to a mechanism for collecting necessary information and data, and includes a system that incorporates methods for obtaining information from sensors and databases.

[0715] "Demand forecasting tools" refer to algorithms and processes for analyzing past data to estimate and predict future demand.

[0716] "Inventory adjustment measures" refer to the function of determining the appropriate inventory level based on predicted demand and formulating plans to prevent excess inventory and stockouts.

[0717] "Information presentation means" refers to user interfaces and devices that display important information to store staff in an easy-to-understand manner and support decision-making.

[0718] "Photo data" refers to visual information acquired as an image, and is a digital image file used to check the condition of products, their display, etc.

[0719] "Image analysis means" refers to the process of extracting meaningful information from a photograph, and is a technology for recognizing features within an image and deriving analysis results.

[0720] The system that realizes this invention consists of a server, a terminal, and a user.

[0721] The server is built using the Flask framework in Python and uses PostgreSQL as its database. The server automatically collects sales history and visitor information and analyzes it to forecast demand. A demand forecasting model trained with Scikit-learn is used for demand forecasting. This model is based on a random forest and uses sales history and related information as input to predict future demand with high accuracy.

[0722] The device is used as a smartphone or tablet and provides an interface for user access. The device receives inventory adjustment proposals and campaign suggestions sent from the server and presents them to the user. Since the user interface is represented through a web browser, the device can utilize all the functions of the present invention simply by opening a specific web page.

[0723] Users can receive information from the server via their terminals, allowing them to, for example, check inventory levels and determine optimal order quantities. Users can also manage store shifts and optimize staff allocation based on customer traffic forecast data from the server.

[0724] As a concrete example, a user can take a picture of the current inventory status with their device and send the photo to the server. The server analyzes this photo data and makes demand forecasts based on the image. An example of a prompt message might be: "The inventory of product A is decreasing. Send a photo to check inventory and receive order suggestions."

[0725] As a result, inventory management, shift management, and campaign planning in physical stores can be carried out efficiently, leading to optimized operations and improved customer service.

[0726] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0727] Step 1:

[0728] The server acquires sales history and related information. Using data acquisition methods, it automatically collects necessary information from databases and sensors and stores it. The acquired data is used as input for a predictive model.

[0729] Step 2:

[0730] The server uses the acquired data to perform demand forecasting using a generative AI model. Using Scikit-learn's Random Forest, it analyzes sales history and related information to predict future demand for each product group. These forecast results serve as the basis for generating inventory adjustment proposals.

[0731] Step 3:

[0732] The server develops an inventory adjustment plan based on predicted demand data. Using inventory adjustment tools, it calculates the order quantities needed to prevent excess inventory and stockouts, and sends the results to the terminal. This plan serves as a guideline to streamline the user's ordering process.

[0733] Step 4:

[0734] The terminal presents the user with inventory adjustment proposals sent from the server. Using an information presentation system, it clearly displays the necessary information through a user-friendly interface. Based on this information, the user can make quick decisions.

[0735] Step 5:

[0736] The user sends current inventory information to the server via a photograph through their device. The device's built-in camera captures the information, and the photograph is sent to the server as digital data. This data is then analyzed using image analysis tools.

[0737] Step 6:

[0738] The server performs image analysis based on the transmitted photo data. Using an image analysis model, it analyzes the number of products, their display status, etc., and evaluates the current inventory status based on this. The results are used as a reference for more detailed inventory adjustments.

[0739] Step 7:

[0740] Users can check visitor information via their devices and optimize shifts. The system analyzes visitor data and forecast data provided by the server to plan optimal staffing. This enables efficient staffing while maintaining the store's service level.

[0741] 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.

[0742] This invention combines a system that utilizes sales history and customer data to improve the efficiency of inventory management and staff allocation with an emotion engine that recognizes user emotions. This system consists of three elements: a server, a terminal, and a user.

[0743] First, the server uses various sensors and input systems to acquire sales history data and customer data, and simultaneously acquires user emotion data through terminals. Next, the server integrates this data to create a dataset for analysis. For emotion recognition, a specific algorithm is used to analyze the user's facial expressions and tone of voice and classify their emotional state.

[0744] Based on the acquired data, the server performs demand forecasting and optimizes inventory management. By incorporating user sentiment data into the analysis, more precise demand forecasting is achieved. In this process, it is estimated that demand may increase if a large number of positive emotions are recognized.

[0745] The server also analyzes customer visit data and generates optimized staffing plans based on customer patterns. It uses emotional data to evaluate customer satisfaction during specific time periods and suggests adjustments to staffing accordingly.

[0746] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server to the user. Based on this, the user can efficiently perform tasks such as ordering, shift management, and customer service. Furthermore, by providing communication and services tailored to the user's emotions, the system aims to improve customer satisfaction.

[0747] As a concrete example, if the server detects a customer's negative emotions during peak hours, it will alert the user via their terminal and suggest improvements such as assigning additional staff. In this way, the system of the present invention enables increased efficiency and improved service in all aspects of store operations by integrating data-driven approaches with emotional data.

[0748] The following describes the processing flow.

[0749] Step 1:

[0750] The server collects sales history data and customer visitor data. Furthermore, it collects customer sentiment data through audio and video data acquired from users' devices.

[0751] Step 2:

[0752] The server builds a demand forecasting model based on collected sales history and customer data. This model includes analytical parameters that use positive customer sentiment as an indicator of increased demand.

[0753] Step 3:

[0754] The server generates inventory adjustment plans based on demand forecasts. In this process, if customer satisfaction is high based on sentiment data, it predicts increased demand and creates an adjustment plan to secure more inventory.

[0755] Step 4:

[0756] The terminal presents the generated inventory adjustment proposal to the user. The user reviews the proposal and places orders for products as needed.

[0757] Step 5:

[0758] The server analyzes visitor data and emotional data, optimizing staff allocation based on visit patterns and customer emotional states. If the emotional state is negative, it suggests additional staff allocation.

[0759] Step 6:

[0760] The terminal receives the calculated staffing plan and presents it to the user. The user adjusts staff shifts based on the presented plan to ensure optimal staffing.

[0761] Step 7:

[0762] The server analyzes customer sentiment data and, if there are many negative emotions, generates suggestions that include specific measures for service improvement.

[0763] Step 8:

[0764] The terminal provides users with service improvement suggestions, which users then use to modify their customer service and store management strategies.

[0765] In this way, the server integrates and analyzes diverse data, and presents appropriate operational strategies to users through terminals, thereby improving the efficiency of store operations and enhancing customer service.

[0766] (Example 2)

[0767] 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".

[0768] In store operations, relying solely on sales history and customer data is insufficient to accurately capture fluctuating consumer needs and customer emotional states, making it difficult to optimize inventory management and staffing. Furthermore, there is a lack of specific information needed to streamline customer service and improve customer satisfaction.

[0769] 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.

[0770] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing user emotions, and inventory adjustment means for generating inventory adjustment proposals using predicted demand data and sentiment data. This enables optimization of inventory management and staff allocation that takes into account fluctuations in consumer needs and customer emotional states, thereby improving the efficiency of store operations and enhancing service.

[0771] "Data acquisition means" refers to methods for collecting store-related information such as sales history and customer data.

[0772] A "demand forecasting tool" is a means of predicting the future demand for each product based on acquired data.

[0773] An "emotion analysis tool" is a method for analyzing a user's facial expressions and tone of voice to classify their emotional state.

[0774] "Inventory adjustment tools" are means of generating suggestions for adjusting inventory to optimal levels using predicted demand data and sentiment data.

[0775] "Information presentation means" refers to means for displaying generated inventory adjustment proposals and other data to the user.

[0776] A "customer visitor analysis method" is a means of acquiring customer data and analyzing that data to reveal customer visit patterns.

[0777] "Staff allocation optimization methods" are means of optimizing staff allocation based on customer visit data and emotional data, in order to achieve efficient personnel management.

[0778] "Information provision means" are means to support users in using the provided data to improve the efficiency of their work.

[0779] The embodiments for carrying out the present invention will now be described. This system is built to improve the efficiency of store operations by utilizing sales history and customer data, and consists of three elements: a server, a terminal, and a user.

[0780] The server collects sales history data and customer information through various sensors and input devices. Hardware includes, for example, cameras and microphones, while software algorithms such as "OpenFace" and "Prosody" are used. The data is first aggregated on the server, where it analyzes the user's facial expressions and voice tone to generate emotion data.

[0781] The server performs demand forecasting based on the acquired data. The demand forecasting algorithm utilizes machine learning models on "PyTorch" and "TensorFlow," which calculate the demand for products according to the time of year and generate inventory optimization plans. For example, if many positive emotions are recognized, demand is predicted to increase. This information is presented to the user via the terminal.

[0782] Furthermore, the server analyzes customer visit patterns and creates optimal staffing plans. Based on emotional data, it evaluates customer satisfaction during specific time periods and suggests staffing changes as needed. This information is also provided to users through their terminals, supporting them in making decisions regarding store operations.

[0783] As a concrete example, if the server detects negative customer emotions during peak hours, the terminal will issue a warning and recommend that the user allocate additional staff. This enables data-driven and emotion-based decision-making, contributing to more efficient store operations and improved service.

[0784] Examples of prompts for a generative AI model include, "Please provide details on demand forecasting using sales history and visit data," and "How can sentiment data be used to optimize staffing?" These prompts demonstrate the AI's ability to suggest specific information that the user needs.

[0785] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0786] Step 1:

[0787] The server collects sales history data and customer data through various sensors and input devices. Specifically, it obtains sales history from the POS system and records customer behavior using cameras installed in the store. Inputs include product sales information and the number of customers, and outputs that store this information in an integrated database.

[0788] Step 2:

[0789] The server receives and analyzes user emotion data transmitted from the terminal. Specifically, it uses data captured by cameras and audio sensors to analyze facial expressions and voice using algorithms such as "OpenFace" and "Prosody" to classify the emotional state. The input is the user's video and audio data, and the output is a score indicating the emotional state.

[0790] Step 3:

[0791] The server combines sales history data and sentiment data to forecast demand. This process utilizes machine learning algorithms, such as a model on TensorFlow, to analyze the data. The input is integrated sales history and sentiment data, and the output is the predicted demand for each product. Based on this forecast, the server generates inventory adjustment plans for the next period.

[0792] Step 4:

[0793] The server analyzes customer behavior patterns and generates optimal staffing plans. It combines customer visit data and sentiment data to provide staffing recommendations. Using customer visit time and frequency data as input, it provides suggestions on how staff should be allocated during specific time periods as output.

[0794] Step 5:

[0795] The terminal displays inventory adjustment proposals, staffing plans, and sentiment analysis results received from the server to the user. Based on this, the user can optimize orders and shifts, and revise customer service strategies. It receives information from the server as input and displays visual information on the terminal screen as output.

[0796] Step 6:

[0797] Users perform their actual tasks based on feedback from their devices. For example, if data indicates that customer sentiment deteriorates during peak hours, additional staff will be assigned to strengthen customer service. In this way, practical countermeasures can be taken by utilizing information from the server.

[0798] (Application Example 2)

[0799] 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".

[0800] In the modern real world, many brick-and-mortar stores are striving to improve the efficiency of inventory management and staffing, but systems that take customer emotions into account are not yet widespread. As a result, they face problems such as inaccurate demand forecasts and decreased customer satisfaction. To improve the customer experience while maximizing operational efficiency, it is necessary to optimize store operations by considering the emotional state of customers.

[0801] 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.

[0802] In this invention, the server includes data acquisition means for acquiring sales history and related data, sentiment analysis means for analyzing and classifying the emotional state of users, and business optimization means for dynamically adjusting staff allocation and service content using the sentiment analysis results. This makes it possible to optimize operations in accordance with customer emotions, thereby simultaneously achieving improved customer satisfaction and operational efficiency.

[0803] "Data acquisition means" refers to a device or process for collecting sales history, customer information, etc.

[0804] A "demand forecasting tool" is a device or process that has the function of calculating and forecasting future demand based on acquired data.

[0805] An "inventory adjustment device" is a device or process that has the function of appropriately adjusting inventory levels based on predicted demand.

[0806] An "emotional analysis tool" is a device or process that has the function of recognizing a user's emotional state, analyzing that information, and classifying it.

[0807] A "business optimization tool" is a device or process that has the function of dynamically adjusting staff allocation and service content using the results of sentiment analysis to optimize business efficiency.

[0808] "Information presentation means" refers to a device or process for displaying generated inventory adjustment proposals and business optimization details to the user.

[0809] "Visitor analysis means" refers to a device or process for analyzing visitor patterns based on visitor data.

[0810] A "means for reflecting emotional data" refers to a device or process that has the function of reflecting emotional data analyzed in real time into store operations.

[0811] A "staff allocation optimization method" is a device or process that has the function of achieving efficient staff allocation based on customer visit data and sentiment data.

[0812] To implement this invention, the server first utilizes data acquisition means to collect sales history and customer information. The data is acquired via hardware such as cameras, sensors, and register recording systems installed within the commercial store. This allows for the collection of information such as which products were sold and in what quantities, and which times of day see the most customers.

[0813] Next, the server uses emotion analysis software such as EmotionRecognizer to analyze the customer's facial expressions and tone of voice to determine their emotional state. Specifically, it captures the user's emotions in real time through smartphones and cameras and microphones on robots installed in the store, and processes this data using an analysis algorithm. This process analyzes that if there are many positive emotions, demand tends to increase.

[0814] Based on these analysis results, the server generates suggestions for dynamically adjusting staffing and service content using operational optimization tools. For example, if customer frustration is detected during peak hours, the server sends a notification to the terminal, prompting the deployment of additional staff or the provision of alternative services. The store terminal uses the inventory adjustment suggestions, staffing suggestions, and sentiment analysis results sent from the server to present users with instructions and options.

[0815] For example, if many customers are showing signs of frustration on a Friday afternoon, the server will analyze the emotional data, send notifications to staff, and suggest adding additional staff to improve customer satisfaction. In this way, the server can integrate data and emotional information and utilize it in all aspects of store operations.

[0816] An example of a prompt given to a generative AI model is, "If the majority of customers who visited on Friday afternoon showed signs of frustration, what measures would be effective?" It is expected that the AI ​​will then suggest appropriate actions based on this prompt.

[0817] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0818] Step 1:

[0819] The server collects sales history data and customer data from cameras, sensors, and cash registers installed within the store. Inputs include the number of items sold and time information of customers who visited the store, and the output is a dataset in which this data is organized.

[0820] Step 2:

[0821] The server uses EmotionRecognizer to perform emotion analysis using customer video and audio data acquired from smartphones and in-store robots. The input includes customer facial expressions and voice data, which are processed by an analysis algorithm to output evaluation results classifying the customer's emotional state.

[0822] Step 3:

[0823] The server integrates sales history data, customer data, and sentiment analysis results to forecast demand. All data is included as input, and statistical models and machine learning algorithms are used to predict demand, outputting forecast data useful for inventory management.

[0824] Step 4:

[0825] Subsequently, the server optimizes operations based on the results of the sentiment analysis. In particular, it generates adjustments to staff allocation and suggestions for additional services. The inputs include customer sentiment data and visit patterns, and these are used to output the optimal staff allocation plan.

[0826] Step 5:

[0827] The terminal presents the user with inventory adjustment proposals, staffing plans, and sentiment analysis results sent from the server. Based on the input, it provides visual information to the user on the user interface, and the output is information designed to facilitate the user's decision-making.

[0828] Step 6:

[0829] Users efficiently perform tasks such as taking orders, managing shifts, and handling customer service based on suggestions provided through the terminal. Input consists of suggested ideas and instructions, and by performing practical operations based on these, the system outputs results that improve the overall operational efficiency of the store.

[0830] 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.

[0831] 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.

[0832] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0833] 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.

[0834] 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.

[0835] 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.

[0836] 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.

[0837] 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.

[0838] 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."

[0839] 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.

[0840] 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.

[0841] 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.

[0842] 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.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] 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.

[0849] 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.

[0850] 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 as being incorporated by reference.

[0851] The following is further disclosed regarding the embodiments described above.

[0852] (Claim 1)

[0853] A data acquisition means for acquiring sales history and related data,

[0854] A demand forecasting means that predicts the demand for each product based on acquired data,

[0855] An inventory adjustment method that generates inventory adjustment proposals using predicted demand data,

[0856] An information presentation means that presents the generated inventory adjustment plan,

[0857] A system that includes this.

[0858] (Claim 2)

[0859] The system according to claim 1, comprising a customer analysis means for acquiring customer data and analyzing customer patterns.

[0860] (Claim 3)

[0861] The system according to claim 1, comprising staff allocation optimization means for optimizing staff allocation based on analyzed customer visit data.

[0862] "Example 1"

[0863] (Claim 1)

[0864] Information gathering means for obtaining sales history and related data,

[0865] A predictive calculation means for predicting the demand for each product based on acquired information,

[0866] A resource management system that generates inventory adjustment proposals using predicted demand information,

[0867] A data presentation means that displays the generated adjustment proposal,

[0868] A staffing method that analyzes customer trends and plans the optimal staffing arrangement,

[0869] A promotional activity support tool that analyzes past sales promotion activity information to develop appropriate promotion strategies,

[0870] A system that includes this.

[0871] (Claim 2)

[0872] The system according to claim 1, comprising an analytical presentation means for analyzing customer trends and creating a staffing plan.

[0873] (Claim 3)

[0874] The system according to claim 1, comprising an activity suggestion means for automatically optimizing promotional activities based on analyzed sales and customer information.

[0875] "Application Example 1"

[0876] (Claim 1)

[0877] A data acquisition means for acquiring sales history and related information,

[0878] A demand forecasting means that predicts the demand for each product group based on the acquired information,

[0879] An inventory adjustment means that generates an inventory adjustment plan using predicted demand information,

[0880] An information presentation means that presents and guides the generated inventory adjustment plan,

[0881] Image analysis means for analyzing photographic data and evaluating the current situation,

[0882] A system that includes this.

[0883] (Claim 2)

[0884] The system according to claim 1, comprising visitor analysis means for acquiring visitor information and analyzing visitor patterns.

[0885] (Claim 3)

[0886] The system according to claim 1, comprising personnel allocation optimization means for optimizing personnel allocation based on analyzed visitor information.

[0887] "Example 2 of combining an emotion engine"

[0888] (Claim 1)

[0889] A data acquisition means for acquiring sales history and related data,

[0890] A demand forecasting means that predicts the demand for each product based on acquired data,

[0891] A means of analyzing user emotions,

[0892] An inventory adjustment means that generates inventory adjustment proposals using predicted demand data and sentiment data,

[0893] An information presentation means that presents the generated inventory adjustment plan,

[0894] A system that includes this.

[0895] (Claim 2)

[0896] A customer analysis method that acquires customer data and analyzes customer patterns,

[0897] The system according to claim 1, comprising staff allocation optimization means for optimizing staff allocation based on analyzed customer visit data and sentiment data.

[0898] (Claim 3)

[0899] The system according to claim 1, which includes an information provision means that presents inventory adjustment plans and staffing plans generated from a server to the user via a terminal, and provides the user with information to efficiently carry out their work.

[0900] "Application example 2 when combining with an emotional engine"

[0901] (Claim 1)

[0902] A data acquisition means for acquiring sales history and related data,

[0903] A demand forecasting means that predicts the demand for each product based on acquired data,

[0904] An inventory adjustment method that generates inventory adjustment proposals using predicted demand data,

[0905] A sentiment analysis tool that analyzes and classifies the emotional state of users,

[0906] A business optimization method that dynamically adjusts staff allocation and service content using the results of sentiment analysis,

[0907] An information presentation means that presents the generated inventory adjustment plan and business optimization details,

[0908] A system that includes this.

[0909] (Claim 2)

[0910] A customer analysis method that acquires customer data and analyzes customer patterns,

[0911] The system according to claim 1, including a means for performing real-time sentiment analysis and reflecting the results in store operations.

[0912] (Claim 3)

[0913] Based on the analyzed customer visit data and emotional data, staff allocation is optimized.

[0914] The system according to claim 1, comprising means for optimizing staff allocation to improve customer satisfaction. [Explanation of Symbols]

[0915] 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 data acquisition means for acquiring sales history and related data, A demand forecasting means that predicts the demand for each product based on acquired data, An inventory adjustment method that generates inventory adjustment proposals using predicted demand data, An information presentation means that presents the generated inventory adjustment plan, A system that includes this.

2. The system according to claim 1, comprising a customer analysis means for acquiring customer data and analyzing customer patterns.

3. The system according to claim 1, comprising staff allocation optimization means for optimizing staff allocation based on analyzed customer visit data.

Images