system

Abstract

Provide a system. 【Solution means】 Means for collecting past sales information and related data to perform demand forecasting, Means for executing an algorithm to predict next-period demand based on the collected data, Means for automatically transmitting an order instruction to a supplier based on the prediction, Means for optimizing the work schedule of workers in business operations, Means for generating and distributing a work schedule considering customer arrival prediction data and labor conditions, Means for analyzing past sales promotion activity data and proposing a plan, Means for automatically setting and executing the proposed plan, Means for displaying inventory information using an electronic device, Means for notifying a smart device of a work schedule and planning information, A system including the above.

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, including 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] In store operations, appropriate inventory management, efficient staff allocation, and effective implementation of promotional measures are necessary. However, these tasks are often performed manually, which requires a great deal of time and labor. In addition, there may be a lack of accuracy in prediction and promptness in response, which may affect customer satisfaction and operating costs as a result. Therefore, there is a need for an effective system to efficiently solve these problems with limited resources and achieve differentiation in a highly competitive market environment.

Means for Solving the Problems

[0005] This invention solves the above problems by providing an automated system for store operations. Specifically, it collects past sales history and related data to forecast demand, and then executes an algorithm to predict the next period's demand based on this data. Furthermore, it uses the forecast results to calculate the optimal order quantity and automatically sends order instructions to suppliers. It also has a mechanism to generate shift schedules considering customer visit forecast data and working conditions to optimize staff shifts and distribute them to each staff member. In addition, it analyzes past campaign data to propose effective promotions and provides a function to automatically set and execute them, thereby improving the efficiency of store operations and customer service.

[0006] "Demand forecasting" is the process of estimating future consumer demand based on past sales data and related information.

[0007] "Sales history" refers to data that records the sales status of a product within a specific period.

[0008] An "algorithm" is a set of steps that outline the procedures or methods of calculation needed to solve a particular problem.

[0009] "Order quantity" refers to the number of goods that are ordered from a supplier to replenish inventory.

[0010] A "supplier" is a company or factory that supplies products or services.

[0011] A "shift" is a schedule that outlines working hours and assignments.

[0012] "Visitor prediction data" refers to information used to predict future visitor numbers based on past visitor data and related factors.

[0013] "Working conditions" refer to conditions related to work, such as employees' working hours, break times, salary, and benefits.

[0014] "Campaign data" refers to data related to promotional activities, including the implementation results and customer reactions in promotional activities.

[0015] "Promotion" refers to promotional activities and sales promotion campaigns carried out to promote the sales of products and services.

Brief Explanation of Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Example 2 when the emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when the emotion engine is combined.

Mode for Carrying Out the Invention

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

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

[0019] 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.

[0020] 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.

[0021] 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.

[0022] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0023] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0024] [First Embodiment]

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

[0026] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0027] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0028] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0029] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0031] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0033] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0034] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0035] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0036] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0037] The system of the present invention aims to improve the efficiency of store operations by using an AI agent to automate demand forecasting, inventory management, shift management, and campaign management. The following components and operations are required to implement the present invention.

[0038] The server functions as the core, continuously collecting historical sales data, customer information, and relevant data such as weather and events. This data is stored in a cloud database and analyzed by a demand forecasting algorithm. This algorithm uses machine learning techniques to predict future demand with high accuracy. Based on these forecasts, the server calculates the optimal order quantity and automatically sends order instructions to suppliers.

[0039] Similarly, the server uses customer visitor forecast data to generate optimal staff shifts. This allows for staffing levels that match customer numbers, ensuring a balanced workforce allocation. The shift schedule is distributed to staff terminals, allowing users to review its contents. It's also possible to suggest shift adjustments as needed.

[0040] Furthermore, the server analyzes campaign data and automatically generates effective promotional strategies. Based on past campaign successes and response rates, it plans coupons and discounts tailored to specific days of the week and time slots. This campaign information is integrated with POS systems and online advertising platforms, and automatically configured and executed. Users can monitor the results on a dashboard and receive real-time feedback.

[0041] For example, in the summer, the server predicts that rising temperatures will increase demand for ice cream and automatically instructs the system to increase the order quantity. It can also predict an increase in Saturday foot traffic and suggest additional staffing shifts. For campaigns, optimizations are made, such as re-offering a previously successful 20% discount coupon to specific customer segments.

[0042] Thus, this invention aims to improve customer satisfaction by utilizing AI technology to streamline and optimize store operations.

[0043] The following describes the processing flow.

[0044] Step 1:

[0045] The server collects historical sales data, customer information, and event information from client databases and external APIs. This includes sales data from the past several years and sales trends for specific periods.

[0046] Step 2:

[0047] The server preprocesses the collected data and formats it as an input dataset for machine learning algorithms. This process includes imputing missing values ​​and removing outliers.

[0048] Step 3:

[0049] The server uses machine learning models to forecast demand. The algorithm employs gradient boosting and time series analysis to predict future demand.

[0050] Step 4:

[0051] The server calculates the optimal inventory order quantity based on the prediction results. Furthermore, it generates automated order instructions for suppliers and sends them via the internet.

[0052] Step 5:

[0053] The server collects and analyzes weather information and past customer data to predict the number of customers visiting the store each day.

[0054] Step 6:

[0055] The server creates an optimal staff shift schedule based on customer traffic prediction data. It assigns appropriate hours and staff numbers to each member in accordance with labor regulations.

[0056] Step 7:

[0057] The server distributes the generated shift schedule to each staff member's terminal. Users can check their schedule through their terminal and inquire if they have any questions.

[0058] Step 8:

[0059] The server analyzes the effectiveness of past campaigns and automatically generates new promotional strategies. Based on the day of the week and customer segments, it determines the most effective coupons and discounts.

[0060] Step 9:

[0061] The server automatically configures the determined campaign information on the relevant digital platforms. This automates the start and management of advertising.

[0062] Step 10:

[0063] Users can monitor results in real time on a dashboard. They can check campaign effectiveness and inventory status, and fine-tune settings as needed.

[0064] (Example 1)

[0065] 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."

[0066] Responding quickly and accurately to fluctuations in demand is difficult in store operations. Furthermore, personnel management and campaign management have traditionally relied heavily on manual processes, leading to inefficiencies. In particular, there is a challenge in efficiently utilizing historical data and external information, which prevents optimal decision-making.

[0067] 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.

[0068] In this invention, the server includes means for collecting information to forecast demand, means for executing an algorithm to forecast demand based on the collected information, and means for calculating quantities based on the forecast and automatically sending instructions to suppliers. This enables automated and efficient store operations based on data.

[0069] "Demand forecasting" is the process of predicting future fluctuations in demand based on past data and influencing factors.

[0070] "Means of collecting information" refers to devices and processes for systematically collecting various data related to store operations.

[0071] An "algorithm" is a set of procedures or calculation methods defined to solve a specific problem. In this invention, it specifically refers to a calculation method for forecasting demand.

[0072] A "supplier" is a company or organization that provides goods or services to a store.

[0073] "Means of automatic transmission" refers to methods or devices that allow a system to send instructions based on predictions or calculations to relevant organizations without manual intervention.

[0074] "Means of optimizing working hours" refer to systems and methods for efficiently allocating employees' working hours and securing the necessary personnel for operations.

[0075] "Visitor forecast information" refers to data used to predict the number of customers visiting a store during a specific time period.

[0076] A "work schedule" is a table that shows the work shifts of employees and is used to plan staffing arrangements.

[0077] "Past project information" refers to data related to campaigns and promotions that were previously conducted.

[0078] "Means of proposing advertising" refers to devices and methods for planning and proposing effective advertising activities based on data analysis.

[0079] "Means for automatic setup and execution" refers to methods or devices that allow the system to set up and start the proposed advertisement without manual operation.

[0080] A "dashboard" is an interface that visually displays the system's operating status and analysis results.

[0081] A "generative AI model" is a program that uses artificial intelligence to generate patterns and predictions.

[0082] "Weather information" refers to data on temperature, precipitation, weather, etc., and is used to predict store visits.

[0083] The system of this invention aims to improve the efficiency of store operations, with a server playing a central role. This server collects various information related to the store and has multiple functions for efficient demand forecasting and management.

[0084] The server collects data from various sources, including sales history, customer information, weather information, and event information. This data is stored in a cloud database and continuously updated. On this database, the server executes demand forecasting algorithms. The algorithms used here include generative AI models, achieving high forecasting accuracy. Furthermore, weather information is used as an important factor in predicting the number of visitors.

[0085] The server calculates the optimal order quantity based on demand forecasts and automatically sends this instruction to suppliers. This uses an API that can communicate with the order management system. It also optimizes employee work shifts using visitor forecast information and delivers the results to terminals. Staff can review the delivered shift information and suggest adjustments as needed.

[0086] Furthermore, the server analyzes past campaign data and proposes effective advertising strategies. The proposed advertising is integrated with POS systems and online platforms and executed automatically. Throughout this process, users can view real-time results on a dashboard and obtain necessary feedback.

[0087] For example, in the summer, the server predicts increased demand for ice cream due to high temperatures and automatically places additional orders. Also, if an increase in Saturday visitor numbers is predicted, it creates a shift schedule suggesting the deployment of additional staff. For campaigns, a strategy is automatically set up to redistribute 20% discount coupons to specific customer segments. All of these functions are based on generative AI models and advanced analytical techniques, with the following prompt being used as an example: "Perform demand forecasts for each product category based on the weather patterns for the next holiday and historical sales data." This allows the server to support efficient and effective store operations.

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server collects store-related data such as sales history, customer information, weather information, and event information from external data sources. This input data is obtained through various APIs and database connections. The acquired data is stored in a cloud database to prepare for subsequent processing.

[0091] Step 2:

[0092] The server cleanses the collected data and performs demand forecasting using a generated AI model. Specifically, it inputs time-series data and other information into the model, analyzes and learns data patterns, and then outputs demand forecast values ​​for a specified period.

[0093] Step 3:

[0094] The server calculates the optimal order quantity for each product based on demand forecasts. This calculation uses an algorithm that takes into account past sales performance, inventory levels, lead times, and other factors. As output, it determines the order quantity for each product and generates instructions to input into a dedicated order management system and automatically send them to suppliers.

[0095] Step 4:

[0096] The server optimizes work shifts by considering visitor forecasts and working conditions. This process uses the predicted number of visitors, each employee's schedule, and skill set as input to calculate the optimal staffing. The generated work schedule is then distributed to the terminals.

[0097] Step 5:

[0098] The server analyzes past campaign data and automatically generates effective advertising strategies. Using campaign response rates and sales performance as input, it optimizes promotions based on this information and outputs coupon and discount suggestions. The generated advertising information is then linked to POS systems and online advertising platforms, and execution is instructed.

[0099] Step 6:

[0100] Users can use the dashboard to monitor server-generated results and promotional effectiveness in real time. This monitoring allows them to evaluate the success of promotions and improvements in operational efficiency, and provide necessary feedback.

[0101] (Application Example 1)

[0102] 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."

[0103] Traditional store operations faced problems such as the significant effort and time required for demand forecasting, inventory management, and staff shift management. This hindered efficient store operations and often led to decreased customer satisfaction. Furthermore, the difficulty in managing and verifying inventory and staff work information in real time exacerbated these problems, especially in situations requiring quick responses.

[0104] 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.

[0105] In this invention, the server includes means for collecting past sales information and related data to forecast demand; means for executing an algorithm to forecast the next period's demand based on the collected data; means for automatically sending order instructions to suppliers based on the forecast; means for optimizing the work schedule of workers in business operations; means for generating and distributing work schedules considering customer forecast data and working conditions; means for analyzing past sales promotion activity data and proposing plans; means for automatically setting and executing the proposed plans; means for displaying inventory information using electronic devices; and means for notifying smart devices of work schedules and plan information. This improves the efficiency of store operations and enables real-time information management and rapid response.

[0106] "Demand forecasting" is the process of predicting future consumption trends for products and services based on past sales information and related data.

[0107] "Sales information" refers to data relating to transactions of a product or service during a specific period.

[0108] "Related data" refers to various types of data that are used to complement sales information, such as customer purchasing trends and market conditions.

[0109] An "algorithm" is a set of procedures or methods for performing a specific calculation or process.

[0110] A "supplier" is an organization or company that supplies products or services to a store or business entity.

[0111] An "order instruction" is a command to a supplier requesting the supply of products or services.

[0112] "Workers" are personnel hired to carry out store operations and business activities.

[0113] A "work plan" is a plan that outlines the time allocation and work assignments necessary for workers to work effectively.

[0114] "Customer visitor prediction data" refers to information used to predict the number of customers who visit a store and their behavior.

[0115] "Working conditions" refer to various factors such as the environment, hours, and treatment of workers when they are employed.

[0116] "Sales promotion activity data" refers to information about the content and effectiveness of past promotional activities.

[0117] A "plan" is a strategy or plan devised to achieve a specific objective.

[0118] "Electronic devices" are devices that use electronic engineering technology to process and display information.

[0119] "Inventory information" refers to information about the quantity and condition of products in warehouses and stores.

[0120] A "smart device" is a portable electronic device that uses information and communication technology to achieve multiple functions.

[0121] "Notification" refers to the act or function of sending information and informing others.

[0122] The system implementing this invention provides functions to streamline store operations through the organic cooperation of a server, terminals, and users. The server continuously collects and stores past sales information and related data in a cloud database to perform demand forecasting. Using this data, it executes a highly accurate demand forecasting algorithm utilizing machine learning technology, places appropriate orders based on the forecast results, and sends instructions to suppliers. For example, it is possible to predict the demand for juices by considering next week's weather forecast and adjust the order quantity appropriately.

[0123] The server further optimizes worker schedules by referencing customer forecast data and working conditions, generating and distributing optimal work schedules to terminals. Through these terminals, users can review their schedules and adjust their shifts as needed. This system allows, for example, predicting an increase in customer traffic on Saturdays and creating appropriate work schedules that include additional staffing.

[0124] Furthermore, the server analyzes past sales promotion activity data and proposes effective plans. These plans are automatically set and notified to customers via electronic devices. In addition, smart devices notify users of inventory and plan information in real time, allowing for immediate adjustments to sales strategies. For example, by re-offering previously successful discount coupons to specific customer segments, a higher promotional effect can be achieved.

[0125] By utilizing a generative AI model and using prompts like the following, the system can perform even more detailed demand forecasts. An example of a prompt is, "Please propose a demand forecast for juices and inventory adjustment plans based on next week's weather forecast."

[0126] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0127] Step 1:

[0128] The server collects historical sales information and related data. In this step, it retrieves historical transaction data, customer information, and weather information from a cloud database as input. The server organizes this data and processes it into a dataset for demand forecasting. The output is a formatted dataset.

[0129] Step 2:

[0130] The server executes a demand forecasting algorithm using the formatted dataset. The dataset obtained in step 1 is used as input. Based on this, the server utilizes a machine learning model to forecast the next period's demand. This algorithmic processing yields future demand forecast results as output.

[0131] Step 3:

[0132] The server generates order instructions to suppliers based on demand forecast results. Here, the output from step 2 is used as input, and the order quantity is calculated considering the required number of goods and the supply chain situation. The calculation results are automatically sent as instructions to the suppliers. The output is a specific order instruction.

[0133] Step 4:

[0134] The server optimizes the worker's work schedule based on customer forecast data and working conditions. Using the customer forecast data obtained in Step 2 as input, it generates an optimal work schedule. This schedule takes working conditions into consideration and efficiently allocates workers' working hours and shifts. The optimized work schedule is output and delivered to the terminal.

[0135] Step 5:

[0136] The terminal displays the received work schedule to the user. Based on the entered work schedule, the user can check and adjust their shifts. In this step, the user directly operates and checks through the terminal's interface. The output is shift information that the user can check.

[0137] Step 6:

[0138] The server analyzes past sales promotion activity data and proposes new plans. Using the promotion activity data obtained in Step 1 as input, the server performs data analysis and generates an effective sales plan. The output is the proposed sales plan, which is automatically set and executed.

[0139] Step 7:

[0140] The terminal notifies the user of inventory and promotional information via a smart device. This step provides a mechanism to notify the smart device of the latest inventory and campaign information obtained from the server as input. The output is the notification information received by the user. This notification allows the user to immediately check inventory and adjust sales strategies.

[0141] 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.

[0142] The system of this invention aims to improve not only the efficiency of store operations but also the quality of customer service by combining it with an emotion engine that recognizes user emotions. In addition to functions such as demand forecasting, inventory management, shift management, and campaign management, the system can analyze customer emotions and reflect them in store operations.

[0143] The server inputs customer feedback, either in-store or through online platforms, into an emotion recognition algorithm. This algorithm utilizes natural language processing techniques to analyze customer emotions in real time from text and voice. The resulting emotion information is then quantified to determine customer satisfaction and dissatisfaction factors, and stored in a database.

[0144] Based on this sentiment information, users can develop even more customized customer response strategies. For example, if the sentiment engine's analysis indicates customer dissatisfaction, the system automatically proposes compensation offers or special discounts and notifies the customer immediately. Conversely, if positive feedback is received, the system can build promotional strategies to maximize its impact.

[0145] Furthermore, the server can perform emotion-based shift adjustments. For example, it can enable flexible shift scheduling by assigning more staff to times when complaints are frequently received.

[0146] As a concrete example, when dealing with a large number of customers during a holiday sale, the emotion engine analyzes feedback in real time and points out that the staff may be overworked. Based on this result, the server immediately reorganizes the shifts to allocate more resources and takes measures to reduce the burden on the staff.

[0147] This invention, by incorporating an emotion engine in this way, is a system that not only improves efficiency but also comprehensively enhances the customer experience.

[0148] The following describes the processing flow.

[0149] Step 1:

[0150] The server retrieves customer text and voice feedback collected in-store and online. This includes customer surveys, reviews, and conversation history.

[0151] Step 2:

[0152] The server runs an emotion recognition algorithm to analyze customer emotions in real time from collected feedback. This algorithm uses natural language processing techniques to classify emotions as positive, negative, neutral, etc.

[0153] Step 3:

[0154] The server stores the analysis results in a database and generates satisfaction reports for each customer segment based on this sentiment data. The reports are updated regularly and serve as reference material for customer service strategies.

[0155] Step 4:

[0156] Users access emotional data to formulate specific strategies for store operations and customer service. Based on the analysis results of the emotional engine, they determine special offers and discounts to improve customer satisfaction.

[0157] Step 5:

[0158] The server automates the determined customer response and delivers promotional content to each customer's device as needed. This process is fully automated, enabling a rapid response to customers.

[0159] Step 6:

[0160] The server takes emotional data into consideration and provides information to the shift management system. This information is used to adjust shifts, such as requiring additional staff during times when there is a lot of unsatisfactory feedback.

[0161] Step 7:

[0162] Users will check the shift information provided on their terminals and ensure that it is communicated to the staff. They will also monitor whether suggestions based on feedback are being implemented appropriately and make adjustments as needed.

[0163] Step 8:

[0164] For example, if the emotion engine reports an increase in customer dissatisfaction during peak hours on Saturday, the server will immediately use this information to increase staffing and implement measures to improve the quality of service.

[0165] In this way, this system can optimize customer service and store operations using emotional data.

[0166] (Example 2)

[0167] 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".

[0168] Improving customer satisfaction and streamlining store operations simultaneously is a critical challenge for many organizations. While traditional systems could forecast demand and optimize shifts, they struggled to adjust operations in real time, taking customer sentiment into account. Furthermore, there is a need to quickly customize customer service and efficiently allocate staff.

[0169] 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.

[0170] In this invention, the server includes means for collecting past sales history and related data in order to forecast demand; means for performing calculations to forecast the next period's demand based on the collected data; means for calculating the order quantity based on the forecast and automatically sending order instructions to suppliers; means for analyzing customer reactions and extracting emotional information; means for storing the extracted emotional information in a database; means for automating customer response strategies based on the emotional information; and means for adjusting personnel shifts based on customer emotional information. This enables real-time adjustment of store operations based on customer emotions and prompt and appropriate customer response.

[0171] "Demand forecasting" refers to estimating future demand based on past sales history and related information.

[0172] "Sales history" refers to records of past sales of goods or services.

[0173] "Related data" refers to supplementary information that is thought to influence sales history, and this includes market trends and seasonality.

[0174] "Order quantity" refers to the number of goods ordered from a supplier.

[0175] A "supplier" refers to an organization or individual that provides goods or services.

[0176] "Personnel shifts" refer to the arrangement of working hours and schedules for employees.

[0177] "Store visit prediction data" refers to information about predicted customer visits to stores in the future.

[0178] "Working conditions" refer to the various conditions that apply to employees when they are working, and include working hours, salary, and benefits.

[0179] "Sales promotion data" refers to information about sales promotion activities that have been conducted in the past.

[0180] "Sales promotion" refers to various activities aimed at encouraging the sale of goods and services.

[0181] "Customer response" refers to the feelings and opinions that customers express about a service or product.

[0182] "Emotional information" refers to data about emotions extracted from customer responses.

[0183] A "database" is a system for managing a collection of information, enabling efficient information retrieval and manipulation.

[0184] "Customer service strategies" refer to specific means and plans for providing services and support to customers.

[0185] Embodiments of the present invention will now be described. This system aims to improve the efficiency of store operations and enhance customer service by taking customer emotions into consideration. The main components of the system are a server, terminals, and users. The server plays a central role in processing and analyzing data using advanced algorithms.

[0186] The server can be implemented with a variety of hardware and software configurations. For example, the server might use natural language processing libraries such as TextBlob, written in Python, or the Google® Cloud Natural Language API to extract sentiment information from customer feedback. This information is used to analyze customer satisfaction and dissatisfaction factors. The obtained data is stored in a storage solution such as a SQL database.

[0187] The device provides an interface for customers to provide feedback. Specifically, it functions as an application on a mobile device or PC, sending entered text and audio data to the server in real time. This allows the server to quickly process the data and extract sentiment information.

[0188] Users develop store operations and customer service strategies based on sentiment data provided by the server. If customer sentiment is negative, users can implement compensation offers or special discounts based on automated suggestions. Conversely, if positive feedback is received, they can develop strategies for further sales promotion.

[0189] For example, if analysis of customer feedback from customers who visited during a holiday sale reveals that staff are overloaded at specific times, the server will suggest shift adjustments based on these findings. This allows for the allocation of additional personnel, thereby reducing staff workload and maintaining the quality of customer service.

[0190] An example of a prompt might be, "Please suggest an effective shift management method using real-time sentiment feedback during holiday sales." Based on such prompts, the system is expected to generate the optimal solution.

[0191] In this way, the system of the present invention goes beyond demand forecasting and inventory management, enabling a comprehensive store management strategy that leverages customer emotions.

[0192] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0193] Step 1:

[0194] The server collects customer feedback data from both in-store and online platforms. This input data includes text and voice feedback. Terminals transmit customer input to the server in real time, enabling rapid data collection.

[0195] Step 2:

[0196] The server feeds the collected data into an emotion recognition algorithm. Based on natural language processing techniques, it analyzes the input text and audio data to determine positive, negative, or neutral emotions. This process uses TextBlob and the Google Cloud Natural Language API for data analysis. The output is a customer emotion score.

[0197] Step 3:

[0198] The server stores the analyzed sentiment information in a database. It receives sentiment scores as input and stores them in association with each customer. This step makes it possible to refer to the sentiment analysis results individually or collectively at a later date.

[0199] Step 4:

[0200] Users formulate strategies based on sentiment information stored on the server. Specifically, they determine customer response measures based on sentiment scores. For example, they devise special promotions or responses for customers exhibiting negative sentiment and automatically notify them through the server.

[0201] Step 5:

[0202] The server optimizes shift management based on real-time sentiment data. It takes sentiment information and customer traffic prediction data as input and generates adjusted staff shifts as output. For example, if many complaints are reported during a particular time period, it takes measures such as assigning additional staff.

[0203] This allows the system to comprehensively support improvements in the customer experience.

[0204] (Application Example 2)

[0205] 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".

[0206] In today's world, where efficient store operations and improved customer service are paramount, simultaneously achieving optimal staffing and increased customer satisfaction is crucial. However, conventional systems lacked the means to effectively address these challenges in real time. Specifically, shift adjustments based on customer traffic forecasts and immediate customer service were difficult, and operations that took customer emotions into account were not adequately implemented.

[0207] 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.

[0208] In this invention, the server includes means for collecting past sales history and related data to perform demand forecasting, means for executing an algorithm to forecast future demand based on the collected data, and means for calculating order quantities based on the forecast and automatically sending order instructions to suppliers. This enables optimal work allocation for employees and immediate response measures based on customer sentiment.

[0209] "Demand forecasting" is the process of predicting future demand by analyzing past sales history and related data.

[0210] "Optimizing worker shifts" refers to a method of efficiently creating and distributing worker shifts by considering customer traffic forecast data and working conditions.

[0211] "Emotion recognition" is a technology that analyzes emotions from a customer's text or voice and grasps their emotional state in real time.

[0212] "Sales promotion proposals" refer to analyzing past campaign data and proposing effective promotional strategies.

[0213] "Smartphone-based emotion analysis" is a function that uses the camera and microphone of a smart device to recognize emotions from a customer's facial expressions and voice.

[0214] "Automatically sending order instructions to suppliers" refers to a system that calculates the required quantity based on demand forecasts and automatically sends that order information to suppliers.

[0215] To implement this invention, the server provides a system that collects and analyzes customer emotions in real time via the internet. Specifically, when a customer uses a smart device and performs voice or text input, the data is sent to the cloud and analyzed using natural language processing technology. Based on the analysis results, the server recognizes the customer's emotions and, if necessary, immediately presents the customer with appropriate countermeasures.

[0216] The hardware used includes smartphones and tablets, which are equipped with devices such as cameras and microphones. The software utilizes natural language processing libraries such as the Google Cloud Natural Language API to analyze customer emotions from text and voice. Furthermore, a database management system is used for data management, and the accumulated emotional data is used to improve the service.

[0217] For example, if a customer complains about being kept waiting for a long time in a shopping center, a smart device can pick up on their voice, and an emotion recognition engine can detect their dissatisfaction. A server immediately receives this information and automatically notifies the customer that they can use a coupon on their next visit.

[0218] An example of a prompt to the generating AI model is, "Suggest promotions and response methods to use when a customer expresses dissatisfaction." This system enables real-time and effective customer support.

[0219] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0220] Step 1:

[0221] The device uses the smartphone's camera and microphone to capture the customer's facial expressions and voice in real time. This input data serves as foundational data for analyzing emotions.

[0222] Step 2:

[0223] The device sends the captured audio and text data to the cloud. There, natural language processing libraries such as the Google Cloud Natural Language API are used to analyze the data and extract emotional information. This analysis classifies the data into emotional categories such as "positive" or "negative."

[0224] Step 3:

[0225] The server stores the customer's emotional state in a database based on the emotional information received from the cloud. This step involves data processing, where the emotional data is associated with the customer ID and stored accordingly.

[0226] Step 4:

[0227] The server analyzes stored emotional information to determine the appropriate customer response. For example, if the emotional recognition result indicates "dissatisfaction," the server runs a program (generative AI model) to propose compensation offers or special discounts to that customer.

[0228] Step 5:

[0229] The server notifies the customer's device of the generated countermeasures. This notification is delivered instantly via push notification or email, immediately communicating the information to the customer.

[0230] Step 6:

[0231] Users (i.e., store staff) can receive customer response strategies sent from the server, contact customers based on those strategies, and provide appropriate support and services.

[0232] 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.

[0233] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0234] 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.

[0235] [Second Embodiment]

[0236] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0237] 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.

[0238] 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).

[0239] 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.

[0240] 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.

[0241] 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).

[0242] 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.

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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".

[0248] The system of the present invention aims to improve the efficiency of store operations by using an AI agent to automate demand forecasting, inventory management, shift management, and campaign management. The following components and operations are required to implement the present invention.

[0249] The server functions as the core, continuously collecting historical sales data, customer information, and relevant data such as weather and events. This data is stored in a cloud database and analyzed by a demand forecasting algorithm. This algorithm uses machine learning techniques to predict future demand with high accuracy. Based on these forecasts, the server calculates the optimal order quantity and automatically sends order instructions to suppliers.

[0250] Similarly, the server uses customer visitor forecast data to generate optimal staff shifts. This allows for staffing levels that match customer numbers, ensuring a balanced workforce allocation. The shift schedule is distributed to staff terminals, allowing users to review its contents. It's also possible to suggest shift adjustments as needed.

[0251] Furthermore, the server analyzes campaign data and automatically generates effective promotional strategies. Based on past campaign successes and response rates, it plans coupons and discounts tailored to specific days of the week and time slots. This campaign information is integrated with POS systems and online advertising platforms, and automatically configured and executed. Users can monitor the results on a dashboard and receive real-time feedback.

[0252] For example, in the summer, the server predicts that rising temperatures will increase demand for ice cream and automatically instructs the system to increase the order quantity. It can also predict an increase in Saturday foot traffic and suggest additional staffing shifts. For campaigns, optimizations are made, such as re-offering a previously successful 20% discount coupon to specific customer segments.

[0253] Thus, this invention aims to improve customer satisfaction by utilizing AI technology to streamline and optimize store operations.

[0254] The following describes the processing flow.

[0255] Step 1:

[0256] The server collects historical sales data, customer information, and event information from client databases and external APIs. This includes sales data from the past several years and sales trends for specific periods.

[0257] Step 2:

[0258] The server preprocesses the collected data and formats it as an input dataset for machine learning algorithms. This process includes imputing missing values ​​and removing outliers.

[0259] Step 3:

[0260] The server uses machine learning models to forecast demand. The algorithm employs gradient boosting and time series analysis to predict future demand.

[0261] Step 4:

[0262] The server calculates the optimal inventory order quantity based on the prediction results. Furthermore, it generates automated order instructions for suppliers and sends them via the internet.

[0263] Step 5:

[0264] The server collects and analyzes weather information and past customer data to predict the number of customers visiting the store each day.

[0265] Step 6:

[0266] The server creates an optimal staff shift schedule based on customer traffic prediction data. It assigns appropriate hours and staff numbers to each member in accordance with labor regulations.

[0267] Step 7:

[0268] The server distributes the generated shift schedule to each staff member's terminal. Users can check their schedule through their terminal and inquire if they have any questions.

[0269] Step 8:

[0270] The server analyzes the effectiveness of past campaigns and automatically generates new promotional strategies. Based on the day of the week and customer segments, it determines the most effective coupons and discounts.

[0271] Step 9:

[0272] The server automatically configures the determined campaign information on the relevant digital platforms. This automates the start and management of advertising.

[0273] Step 10:

[0274] Users can monitor results in real time on a dashboard. They can check campaign effectiveness and inventory status, and fine-tune settings as needed.

[0275] (Example 1)

[0276] 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."

[0277] Responding quickly and accurately to fluctuations in demand is difficult in store operations. Furthermore, personnel management and campaign management have traditionally relied heavily on manual processes, leading to inefficiencies. In particular, there is a challenge in efficiently utilizing historical data and external information, which prevents optimal decision-making.

[0278] 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.

[0279] In this invention, the server includes means for collecting information to perform demand forecasting, means for executing an algorithm for predicting demand based on the collected information, and means for calculating the quantity based on the prediction and automatically transmitting an instruction to the supplier. Thereby, automatic and efficient store operation based on data becomes possible.

[0280] "Demand forecasting" is a process of inferring future demand fluctuations based on past data and influencing factors.

[0281] "Means for collecting information" is a device or process for systematically collecting various data related to store operation.

[0282] "Algorithm" is a defined procedure or calculation method for solving a specific problem. In this invention, it particularly refers to a calculation method for predicting demand.

[0283] "Supplier" is an enterprise or organization that provides goods or services to the store.

[0284] "Means for automatically transmitting" is a method or device by which the system sends an instruction based on prediction or calculation to the relevant institution without manual operation.

[0285] "Means for optimizing working hours" is a system or method for efficiently arranging the working hours of employees and ensuring the necessary personnel for the business.

[0286] "Visitor prediction information" is data for predicting the number of visitors to the store in a specific time period.

[0287] "Work schedule" is a table showing the work shifts of employees and is used for planning personnel allocation.

[0288] "Past planning information" is data related to previously implemented campaigns or promotions.

[0289] "Means of proposing advertising" refers to devices and methods for planning and proposing effective advertising activities based on data analysis.

[0290] "Means for automatic setup and execution" refers to methods or devices that allow the system to set up and start the proposed advertisement without manual operation.

[0291] A "dashboard" is an interface that visually displays the system's operating status and analysis results.

[0292] A "generative AI model" is a program that uses artificial intelligence to generate patterns and predictions.

[0293] "Weather information" refers to data on temperature, precipitation, weather, etc., and is used to predict store visits.

[0294] The system of this invention aims to improve the efficiency of store operations, with a server playing a central role. This server collects various information related to the store and has multiple functions for efficient demand forecasting and management.

[0295] The server collects data from various sources, including sales history, customer information, weather information, and event information. This data is stored in a cloud database and continuously updated. On this database, the server executes demand forecasting algorithms. The algorithms used here include generative AI models, achieving high forecasting accuracy. Furthermore, weather information is used as an important factor in predicting the number of visitors.

[0296] The server calculates the optimal order quantity based on demand forecasts and automatically sends this instruction to suppliers. This uses an API that can communicate with the order management system. It also optimizes employee work shifts using visitor forecast information and delivers the results to terminals. Staff can review the delivered shift information and suggest adjustments as needed.

[0297] Furthermore, the server analyzes past campaign data and proposes effective advertising strategies. The proposed advertising is integrated with POS systems and online platforms and executed automatically. Throughout this process, users can view real-time results on a dashboard and obtain necessary feedback.

[0298] For example, in the summer, the server predicts increased demand for ice cream due to high temperatures and automatically places additional orders. Also, if an increase in Saturday visitor numbers is predicted, it creates a shift schedule suggesting the deployment of additional staff. For campaigns, a strategy is automatically set up to redistribute 20% discount coupons to specific customer segments. All of these functions are based on generative AI models and advanced analytical techniques, with the following prompt being used as an example: "Perform demand forecasts for each product category based on the weather patterns for the next holiday and historical sales data." This allows the server to support efficient and effective store operations.

[0299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0300] Step 1:

[0301] The server collects store-related data such as sales history, customer information, weather information, and event information from external data sources. This input data is obtained through various APIs and database connections. The acquired data is stored in a cloud database to prepare for subsequent processing.

[0302] Step 2:

[0303] The server cleanses the collected data and performs demand forecasting using a generated AI model. Specifically, it inputs time-series data and other information into the model, analyzes and learns data patterns, and then outputs demand forecast values ​​for a specified period.

[0304] Step 3:

[0305] The server calculates the optimal order quantity of products based on the demand forecast value. This calculation uses an algorithm that takes into account past sales performance, inventory status, lead time, etc. As output, it determines the order quantity for each product, generates an instruction to input it into a dedicated order management system and automatically send it to the supplier.

[0306] Step 4:

[0307] The server optimizes the work schedule considering the predicted visit information and working conditions. In this process, the predicted number of visitors and the schedule and skill set of each employee are used as inputs to calculate the optimal staffing arrangement. It distributes the generated work schedule to the terminals.

[0308] Step 5:

[0309] The server analyzes past campaign data and automatically generates an effective promotion strategy. Using the campaign response rate and sales effect as inputs, it optimizes the promotion based on this information and outputs proposals for coupons and discounts. It links the generated promotion information to the POS system and online advertising platforms and instructs their execution.

[0310] Step 6:

[0311] The user uses the dashboard to monitor in real time the results generated by the server and the effects of the promotion. Through this monitoring, the degree of success of the promotion and the improvement of business efficiency can be evaluated, and necessary feedback can be provided.

[0312] (Application Example 1)

[0313] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0314] Traditional store operations faced problems such as the significant effort and time required for demand forecasting, inventory management, and staff shift management. This hindered efficient store operations and often led to decreased customer satisfaction. Furthermore, the difficulty in managing and verifying inventory and staff work information in real time exacerbated these problems, especially in situations requiring quick responses.

[0315] 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.

[0316] In this invention, the server includes means for collecting past sales information and related data to forecast demand; means for executing an algorithm to forecast the next period's demand based on the collected data; means for automatically sending order instructions to suppliers based on the forecast; means for optimizing the work schedule of workers in business operations; means for generating and distributing work schedules considering customer forecast data and working conditions; means for analyzing past sales promotion activity data and proposing plans; means for automatically setting and executing the proposed plans; means for displaying inventory information using electronic devices; and means for notifying smart devices of work schedules and plan information. This improves the efficiency of store operations and enables real-time information management and rapid response.

[0317] "Demand forecasting" is the process of predicting future consumption trends for products and services based on past sales information and related data.

[0318] "Sales information" refers to data relating to transactions of a product or service during a specific period.

[0319] "Related data" refers to various types of data that are used to complement sales information, such as customer purchasing trends and market conditions.

[0320] An "algorithm" is a set of procedures or methods for performing a specific calculation or process.

[0321] A "supplier" is an organization or company that supplies products or services to a store or business entity.

[0322] An "order instruction" is a command to a supplier requesting the supply of products or services.

[0323] "Workers" are personnel hired to carry out store operations and business activities.

[0324] A "work plan" is a plan that outlines the time allocation and work assignments necessary for workers to work effectively.

[0325] "Customer visitor prediction data" refers to information used to predict the number of customers who visit a store and their behavior.

[0326] "Working conditions" refer to various factors such as the environment, hours, and treatment of workers when they are employed.

[0327] "Sales promotion activity data" refers to information about the content and effectiveness of past promotional activities.

[0328] A "plan" is a strategy or plan devised to achieve a specific objective.

[0329] "Electronic devices" are devices that use electronic engineering technology to process and display information.

[0330] "Inventory information" refers to information about the quantity and condition of products in warehouses and stores.

[0331] A "smart device" is a portable electronic device that uses information and communication technology to achieve multiple functions.

[0332] "Notification" refers to the act or function of sending information and informing others.

[0333] The system implementing this invention provides functions to streamline store operations through the organic cooperation of a server, terminals, and users. The server continuously collects and stores past sales information and related data in a cloud database to perform demand forecasting. Using this data, it executes a highly accurate demand forecasting algorithm utilizing machine learning technology, places appropriate orders based on the forecast results, and sends instructions to suppliers. For example, it is possible to predict the demand for juices by considering next week's weather forecast and adjust the order quantity appropriately.

[0334] The server further optimizes worker schedules by referencing customer forecast data and working conditions, generating and distributing optimal work schedules to terminals. Through these terminals, users can review their schedules and adjust their shifts as needed. This system allows, for example, predicting an increase in customer traffic on Saturdays and creating appropriate work schedules that include additional staffing.

[0335] Furthermore, the server analyzes past sales promotion activity data and proposes effective plans. These plans are automatically set and notified to customers via electronic devices. In addition, smart devices notify users of inventory and plan information in real time, allowing for immediate adjustments to sales strategies. For example, by re-offering previously successful discount coupons to specific customer segments, a higher promotional effect can be achieved.

[0336] By utilizing a generative AI model and using prompts like the following, the system can perform even more detailed demand forecasts. An example of a prompt is, "Please propose a demand forecast for juices and inventory adjustment plans based on next week's weather forecast."

[0337] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0338] Step 1:

[0339] The server collects historical sales information and related data. In this step, it retrieves historical transaction data, customer information, and weather information from a cloud database as input. The server organizes this data and processes it into a dataset for demand forecasting. The output is a formatted dataset.

[0340] Step 2:

[0341] The server executes a demand forecasting algorithm using the formatted dataset. The dataset obtained in step 1 is used as input. Based on this, the server utilizes a machine learning model to forecast the next period's demand. This algorithmic processing yields future demand forecast results as output.

[0342] Step 3:

[0343] The server generates order instructions to suppliers based on demand forecast results. Here, the output from step 2 is used as input, and the order quantity is calculated considering the required number of goods and the supply chain situation. The calculation results are automatically sent as instructions to the suppliers. The output is a specific order instruction.

[0344] Step 4:

[0345] The server optimizes the worker's work schedule based on customer forecast data and working conditions. Using the customer forecast data obtained in Step 2 as input, it generates an optimal work schedule. This schedule takes working conditions into consideration and efficiently allocates workers' working hours and shifts. The optimized work schedule is output and delivered to the terminal.

[0346] Step 5:

[0347] The terminal displays the received work schedule to the user. Based on the entered work schedule, the user can check and adjust their shifts. In this step, the user directly operates and checks through the terminal's interface. The output is shift information that the user can check.

[0348] Step 6:

[0349] The server analyzes past sales promotion activity data and proposes new plans. Using the promotion activity data obtained in Step 1 as input, the server performs data analysis and generates an effective sales plan. The output is the proposed sales plan, which is automatically set and executed.

[0350] Step 7:

[0351] The terminal notifies the user of inventory and promotional information via a smart device. This step provides a mechanism to notify the smart device of the latest inventory and campaign information obtained from the server as input. The output is the notification information received by the user. This notification allows the user to immediately check inventory and adjust sales strategies.

[0352] 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.

[0353] The system of this invention aims to improve not only the efficiency of store operations but also the quality of customer service by combining it with an emotion engine that recognizes user emotions. In addition to functions such as demand forecasting, inventory management, shift management, and campaign management, the system can analyze customer emotions and reflect them in store operations.

[0354] The server inputs customer feedback, either in-store or through online platforms, into an emotion recognition algorithm. This algorithm utilizes natural language processing techniques to analyze customer emotions in real time from text and voice. The resulting emotion information is then quantified to determine customer satisfaction and dissatisfaction factors, and stored in a database.

[0355] Based on this sentiment information, users can develop even more customized customer response strategies. For example, if the sentiment engine's analysis indicates customer dissatisfaction, the system automatically proposes compensation offers or special discounts and notifies the customer immediately. Conversely, if positive feedback is received, the system can build promotional strategies to maximize its impact.

[0356] Furthermore, the server can perform emotion-based shift adjustments. For example, it can enable flexible shift scheduling by assigning more staff to times when complaints are frequently received.

[0357] As a concrete example, when dealing with a large number of customers during a holiday sale, the emotion engine analyzes feedback in real time and points out that the staff may be overworked. Based on this result, the server immediately reorganizes the shifts to allocate more resources and takes measures to reduce the burden on the staff.

[0358] This invention, by incorporating an emotion engine in this way, is a system that not only improves efficiency but also comprehensively enhances the customer experience.

[0359] The following describes the processing flow.

[0360] Step 1:

[0361] The server retrieves customer text and voice feedback collected in-store and online. This includes customer surveys, reviews, and conversation history.

[0362] Step 2:

[0363] The server runs an emotion recognition algorithm to analyze customer emotions in real time from collected feedback. This algorithm uses natural language processing techniques to classify emotions as positive, negative, neutral, etc.

[0364] Step 3:

[0365] The server stores the analysis results in a database and generates satisfaction reports for each customer segment based on this sentiment data. The reports are updated regularly and serve as reference material for customer service strategies.

[0366] Step 4:

[0367] Users access emotional data to formulate specific strategies for store operations and customer service. Based on the analysis results of the emotional engine, they determine special offers and discounts to improve customer satisfaction.

[0368] Step 5:

[0369] The server automates the determined customer response and delivers promotional content to each customer's device as needed. This process is fully automated, enabling a rapid response to customers.

[0370] Step 6:

[0371] The server takes emotional data into consideration and provides information to the shift management system. This information is used to adjust shifts, such as requiring additional staff during times when there is a lot of unsatisfactory feedback.

[0372] Step 7:

[0373] Users will check the shift information provided on their terminals and ensure that it is communicated to the staff. They will also monitor whether suggestions based on feedback are being implemented appropriately and make adjustments as needed.

[0374] Step 8:

[0375] For example, if the emotion engine reports an increase in customer dissatisfaction during peak hours on Saturday, the server will immediately use this information to increase staffing and implement measures to improve the quality of service.

[0376] In this way, this system can optimize customer service and store operations using emotional data.

[0377] (Example 2)

[0378] 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".

[0379] Improving customer satisfaction and streamlining store operations simultaneously is a critical challenge for many organizations. While traditional systems could forecast demand and optimize shifts, they struggled to adjust operations in real time, taking customer sentiment into account. Furthermore, there is a need to quickly customize customer service and efficiently allocate staff.

[0380] 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.

[0381] In this invention, the server includes means for collecting past sales history and related data in order to forecast demand; means for performing calculations to forecast the next period's demand based on the collected data; means for calculating the order quantity based on the forecast and automatically sending order instructions to suppliers; means for analyzing customer reactions and extracting emotional information; means for storing the extracted emotional information in a database; means for automating customer response strategies based on the emotional information; and means for adjusting personnel shifts based on customer emotional information. This enables real-time adjustment of store operations based on customer emotions and prompt and appropriate customer response.

[0382] "Demand forecasting" refers to estimating future demand based on past sales history and related information.

[0383] "Sales history" refers to records of past sales of goods or services.

[0384] "Related data" refers to supplementary information that is thought to influence sales history, and this includes market trends and seasonality.

[0385] "Order quantity" refers to the number of goods ordered from a supplier.

[0386] A "supplier" refers to an organization or individual that provides goods or services.

[0387] "Personnel shifts" refer to the arrangement of working hours and schedules for employees.

[0388] "Store visit prediction data" refers to information about predicted customer visits to stores in the future.

[0389] "Working conditions" refer to the various conditions that apply to employees when they are working, and include working hours, salary, and benefits.

[0390] "Sales promotion data" refers to information about sales promotion activities that have been conducted in the past.

[0391] "Sales promotion" refers to various activities aimed at encouraging the sale of goods and services.

[0392] "Customer response" refers to the feelings and opinions that customers express about a service or product.

[0393] "Emotional information" refers to data about emotions extracted from customer responses.

[0394] A "database" is a system for managing a collection of information, enabling efficient information retrieval and manipulation.

[0395] "Customer service strategies" refer to specific means and plans for providing services and support to customers.

[0396] Embodiments of the present invention will now be described. This system aims to improve the efficiency of store operations and enhance customer service by taking customer emotions into consideration. The main components of the system are a server, terminals, and users. The server plays a central role in processing and analyzing data using advanced algorithms.

[0397] The server can be implemented with a variety of hardware and software configurations. For example, the server might use natural language processing libraries such as TextBlob written in Python, or the Google Cloud Natural Language API, to extract sentiment information from customer feedback. This information is used to analyze customer satisfaction and dissatisfaction factors. The obtained data is stored in a storage solution such as a SQL database.

[0398] The device provides an interface for customers to provide feedback. Specifically, it functions as an application on a mobile device or PC, sending entered text and audio data to the server in real time. This allows the server to quickly process the data and extract sentiment information.

[0399] Users develop store operations and customer service strategies based on sentiment data provided by the server. If customer sentiment is negative, users can implement compensation offers or special discounts based on automated suggestions. Conversely, if positive feedback is received, they can develop strategies for further sales promotion.

[0400] For example, if analysis of customer feedback from customers who visited during a holiday sale reveals that staff are overloaded at specific times, the server will suggest shift adjustments based on these findings. This allows for the allocation of additional personnel, thereby reducing staff workload and maintaining the quality of customer service.

[0401] An example of a prompt might be, "Please suggest an effective shift management method using real-time sentiment feedback during holiday sales." Based on such prompts, the system is expected to generate the optimal solution.

[0402] In this way, the system of the present invention goes beyond demand forecasting and inventory management, enabling a comprehensive store management strategy that leverages customer emotions.

[0403] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0404] Step 1:

[0405] The server collects customer feedback data from both in-store and online platforms. This input data includes text and voice feedback. Terminals transmit customer input to the server in real time, enabling rapid data collection.

[0406] Step 2:

[0407] The server feeds the collected data into an emotion recognition algorithm. Based on natural language processing techniques, it analyzes the input text and audio data to determine positive, negative, or neutral emotions. This process uses TextBlob and the Google Cloud Natural Language API for data analysis. The output is a customer emotion score.

[0408] Step 3:

[0409] The server stores the analyzed sentiment information in a database. It receives sentiment scores as input and stores them in association with each customer. This step makes it possible to refer to the sentiment analysis results individually or collectively at a later date.

[0410] Step 4:

[0411] Users formulate strategies based on sentiment information stored on the server. Specifically, they determine customer response measures based on sentiment scores. For example, they devise special promotions or responses for customers exhibiting negative sentiment and automatically notify them through the server.

[0412] Step 5:

[0413] The server optimizes shift management based on real-time sentiment data. It takes sentiment information and customer traffic prediction data as input and generates adjusted staff shifts as output. For example, if many complaints are reported during a particular time period, it takes measures such as assigning additional staff.

[0414] This allows the system to comprehensively support improvements in the customer experience.

[0415] (Application Example 2)

[0416] 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."

[0417] In today's world, where efficient store operations and improved customer service are paramount, simultaneously achieving optimal staffing and increased customer satisfaction is crucial. However, conventional systems lacked the means to effectively address these challenges in real time. Specifically, shift adjustments based on customer traffic forecasts and immediate customer service were difficult, and operations that took customer emotions into account were not adequately implemented.

[0418] 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.

[0419] In this invention, the server includes means for collecting past sales history and related data to perform demand forecasting, means for executing an algorithm to forecast future demand based on the collected data, and means for calculating order quantities based on the forecast and automatically sending order instructions to suppliers. This enables optimal work allocation for employees and immediate response measures based on customer sentiment.

[0420] "Demand forecasting" is the process of predicting future demand by analyzing past sales history and related data.

[0421] "Optimizing worker shifts" refers to a method of efficiently creating and distributing worker shifts by considering customer traffic forecast data and working conditions.

[0422] "Emotion recognition" is a technology that analyzes emotions from a customer's text or voice and grasps their emotional state in real time.

[0423] "Sales promotion proposals" refer to analyzing past campaign data and proposing effective promotional strategies.

[0424] "Smartphone-based emotion analysis" is a function that uses the camera and microphone of a smart device to recognize emotions from a customer's facial expressions and voice.

[0425] "Automatically sending order instructions to suppliers" refers to a system that calculates the required quantity based on demand forecasts and automatically sends that order information to suppliers.

[0426] To implement this invention, the server provides a system that collects and analyzes customer emotions in real time via the internet. Specifically, when a customer uses a smart device and performs voice or text input, the data is sent to the cloud and analyzed using natural language processing technology. Based on the analysis results, the server recognizes the customer's emotions and, if necessary, immediately presents the customer with appropriate countermeasures.

[0427] The hardware used includes smartphones and tablets, which are equipped with devices such as cameras and microphones. The software utilizes natural language processing libraries such as the Google Cloud Natural Language API to analyze customer emotions from text and voice. Furthermore, a database management system is used for data management, and the accumulated emotional data is used to improve the service.

[0428] For example, if a customer complains about being kept waiting for a long time in a shopping center, a smart device can pick up on their voice, and an emotion recognition engine can detect their dissatisfaction. A server immediately receives this information and automatically notifies the customer that they can use a coupon on their next visit.

[0429] An example of a prompt to the generating AI model is, "Suggest promotions and response methods to use when a customer expresses dissatisfaction." This system enables real-time and effective customer support.

[0430] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0431] Step 1:

[0432] The device uses the smartphone's camera and microphone to capture the customer's facial expressions and voice in real time. This input data serves as foundational data for analyzing emotions.

[0433] Step 2:

[0434] The device sends the captured audio and text data to the cloud. There, natural language processing libraries such as the Google Cloud Natural Language API are used to analyze the data and extract emotional information. This analysis classifies the data into emotional categories such as "positive" or "negative."

[0435] Step 3:

[0436] The server stores the customer's emotional state in a database based on the emotional information received from the cloud. This step involves data processing, where the emotional data is associated with the customer ID and stored accordingly.

[0437] Step 4:

[0438] The server analyzes stored emotional information to determine the appropriate customer response. For example, if the emotional recognition result indicates "dissatisfaction," the server runs a program (generative AI model) to propose compensation offers or special discounts to that customer.

[0439] Step 5:

[0440] The server notifies the customer's device of the generated countermeasures. This notification is delivered instantly via push notification or email, immediately communicating the information to the customer.

[0441] Step 6:

[0442] Users (i.e., store staff) can receive customer response strategies sent from the server, contact customers based on those strategies, and provide appropriate support and services.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] [Third Embodiment]

[0447] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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).

[0453] 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.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] 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.

[0458] 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".

[0459] The system of the present invention aims to improve the efficiency of store operations by using an AI agent to automate demand forecasting, inventory management, shift management, and campaign management. The following components and operations are required to implement the present invention.

[0460] The server functions as the core, continuously collecting historical sales data, customer information, and relevant data such as weather and events. This data is stored in a cloud database and analyzed by a demand forecasting algorithm. This algorithm uses machine learning techniques to predict future demand with high accuracy. Based on these forecasts, the server calculates the optimal order quantity and automatically sends order instructions to suppliers.

[0461] Similarly, the server uses customer visitor forecast data to generate optimal staff shifts. This allows for staffing levels that match customer numbers, ensuring a balanced workforce allocation. The shift schedule is distributed to staff terminals, allowing users to review its contents. It's also possible to suggest shift adjustments as needed.

[0462] Furthermore, the server analyzes campaign data and automatically generates effective promotional strategies. Based on past campaign successes and response rates, it plans coupons and discounts tailored to specific days of the week and time slots. This campaign information is integrated with POS systems and online advertising platforms, and automatically configured and executed. Users can monitor the results on a dashboard and receive real-time feedback.

[0463] For example, in the summer, the server predicts that rising temperatures will increase demand for ice cream and automatically instructs the system to increase the order quantity. It can also predict an increase in Saturday foot traffic and suggest additional staffing shifts. For campaigns, optimizations are made, such as re-offering a previously successful 20% discount coupon to specific customer segments.

[0464] Thus, this invention aims to improve customer satisfaction by utilizing AI technology to streamline and optimize store operations.

[0465] The following describes the processing flow.

[0466] Step 1:

[0467] The server collects historical sales data, customer information, and event information from client databases and external APIs. This includes sales data from the past several years and sales trends for specific periods.

[0468] Step 2:

[0469] The server preprocesses the collected data and formats it as an input dataset for machine learning algorithms. This process includes imputing missing values ​​and removing outliers.

[0470] Step 3:

[0471] The server uses machine learning models to forecast demand. The algorithm employs gradient boosting and time series analysis to predict future demand.

[0472] Step 4:

[0473] The server calculates the optimal inventory order quantity based on the prediction results. Furthermore, it generates automated order instructions for suppliers and sends them via the internet.

[0474] Step 5:

[0475] The server collects and analyzes weather information and past customer data to predict the number of customers visiting the store each day.

[0476] Step 6:

[0477] The server creates an optimal staff shift schedule based on customer traffic prediction data. It assigns appropriate hours and staff numbers to each member in accordance with labor regulations.

[0478] Step 7:

[0479] The server distributes the generated shift schedule to each staff member's terminal. Users can check their schedule through their terminal and inquire if they have any questions.

[0480] Step 8:

[0481] The server analyzes the effectiveness of past campaigns and automatically generates new promotional strategies. Based on the day of the week and customer segments, it determines the most effective coupons and discounts.

[0482] Step 9:

[0483] The server automatically configures the determined campaign information on the relevant digital platforms. This automates the start and management of advertising.

[0484] Step 10:

[0485] Users can monitor results in real time on a dashboard. They can check campaign effectiveness and inventory status, and fine-tune settings as needed.

[0486] (Example 1)

[0487] 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."

[0488] Responding quickly and accurately to fluctuations in demand is difficult in store operations. Furthermore, personnel management and campaign management have traditionally relied heavily on manual processes, leading to inefficiencies. In particular, there is a challenge in efficiently utilizing historical data and external information, which prevents optimal decision-making.

[0489] 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.

[0490] In this invention, the server includes means for collecting information to forecast demand, means for executing an algorithm to forecast demand based on the collected information, and means for calculating quantities based on the forecast and automatically sending instructions to suppliers. This enables automated and efficient store operations based on data.

[0491] "Demand forecasting" is the process of predicting future fluctuations in demand based on past data and influencing factors.

[0492] "Means of collecting information" refers to devices and processes for systematically collecting various data related to store operations.

[0493] An "algorithm" is a set of procedures or calculation methods defined to solve a specific problem. In this invention, it specifically refers to a calculation method for forecasting demand.

[0494] A "supplier" is a company or organization that provides goods or services to a store.

[0495] "Means of automatic transmission" refers to methods or devices that allow a system to send instructions based on predictions or calculations to relevant organizations without manual intervention.

[0496] "Means of optimizing working hours" refer to systems and methods for efficiently allocating employees' working hours and securing the necessary personnel for operations.

[0497] "Visitor forecast information" refers to data used to predict the number of customers visiting a store during a specific time period.

[0498] A "work schedule" is a table that shows the work shifts of employees and is used to plan staffing arrangements.

[0499] "Past project information" refers to data related to campaigns and promotions that were previously conducted.

[0500] "Means of proposing advertising" refers to devices and methods for planning and proposing effective advertising activities based on data analysis.

[0501] "Means for automatic setup and execution" refers to methods or devices that allow the system to set up and start the proposed advertisement without manual operation.

[0502] A "dashboard" is an interface that visually displays the system's operating status and analysis results.

[0503] A "generative AI model" is a program that uses artificial intelligence to generate patterns and predictions.

[0504] "Weather information" refers to data on temperature, precipitation, weather, etc., and is used to predict store visits.

[0505] The system of this invention aims to improve the efficiency of store operations, with a server playing a central role. This server collects various information related to the store and has multiple functions for efficient demand forecasting and management.

[0506] The server collects data from various sources, including sales history, customer information, weather information, and event information. This data is stored in a cloud database and continuously updated. On this database, the server executes demand forecasting algorithms. The algorithms used here include generative AI models, achieving high forecasting accuracy. Furthermore, weather information is used as an important factor in predicting the number of visitors.

[0507] The server calculates the optimal order quantity based on demand forecasts and automatically sends this instruction to suppliers. This uses an API that can communicate with the order management system. It also optimizes employee work shifts using visitor forecast information and delivers the results to terminals. Staff can review the delivered shift information and suggest adjustments as needed.

[0508] Furthermore, the server analyzes past campaign data and proposes effective advertising strategies. The proposed advertising is integrated with POS systems and online platforms and executed automatically. Throughout this process, users can view real-time results on a dashboard and obtain necessary feedback.

[0509] For example, in the summer, the server predicts increased demand for ice cream due to high temperatures and automatically places additional orders. Also, if an increase in Saturday visitor numbers is predicted, it creates a shift schedule suggesting the deployment of additional staff. For campaigns, a strategy is automatically set up to redistribute 20% discount coupons to specific customer segments. All of these functions are based on generative AI models and advanced analytical techniques, with the following prompt being used as an example: "Perform demand forecasts for each product category based on the weather patterns for the next holiday and historical sales data." This allows the server to support efficient and effective store operations.

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] The server collects store-related data such as sales history, customer information, weather information, and event information from external data sources. This input data is obtained through various APIs and database connections. The acquired data is stored in a cloud database to prepare for subsequent processing.

[0513] Step 2:

[0514] The server cleanses the collected data and performs demand forecasting using a generated AI model. Specifically, it inputs time-series data and other information into the model, analyzes and learns data patterns, and then outputs demand forecast values ​​for a specified period.

[0515] Step 3:

[0516] The server calculates the optimal order quantity for each product based on demand forecasts. This calculation uses an algorithm that takes into account past sales performance, inventory levels, lead times, and other factors. As output, it determines the order quantity for each product and generates instructions to input into a dedicated order management system and automatically send them to suppliers.

[0517] Step 4:

[0518] The server optimizes work shifts by considering visitor forecasts and working conditions. This process uses the predicted number of visitors, each employee's schedule, and skill set as input to calculate the optimal staffing. The generated work schedule is then distributed to the terminals.

[0519] Step 5:

[0520] The server analyzes past campaign data and automatically generates effective advertising strategies. Using campaign response rates and sales performance as input, it optimizes promotions based on this information and outputs coupon and discount suggestions. The generated advertising information is then linked to POS systems and online advertising platforms, and execution is instructed.

[0521] Step 6:

[0522] Users can use the dashboard to monitor server-generated results and promotional effectiveness in real time. This monitoring allows them to evaluate the success of promotions and improvements in operational efficiency, and provide necessary feedback.

[0523] (Application Example 1)

[0524] 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."

[0525] Traditional store operations faced problems such as the significant effort and time required for demand forecasting, inventory management, and staff shift management. This hindered efficient store operations and often led to decreased customer satisfaction. Furthermore, the difficulty in managing and verifying inventory and staff work information in real time exacerbated these problems, especially in situations requiring quick responses.

[0526] 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.

[0527] In this invention, the server includes means for collecting past sales information and related data to forecast demand; means for executing an algorithm to forecast the next period's demand based on the collected data; means for automatically sending order instructions to suppliers based on the forecast; means for optimizing the work schedule of workers in business operations; means for generating and distributing work schedules considering customer forecast data and working conditions; means for analyzing past sales promotion activity data and proposing plans; means for automatically setting and executing the proposed plans; means for displaying inventory information using electronic devices; and means for notifying smart devices of work schedules and plan information. This improves the efficiency of store operations and enables real-time information management and rapid response.

[0528] "Demand forecasting" is the process of predicting future consumption trends for products and services based on past sales information and related data.

[0529] "Sales information" refers to data relating to transactions of a product or service during a specific period.

[0530] "Related data" refers to various types of data that are used to complement sales information, such as customer purchasing trends and market conditions.

[0531] An "algorithm" is a set of procedures or methods for performing a specific calculation or process.

[0532] A "supplier" is an organization or company that supplies products or services to a store or business entity.

[0533] An "order instruction" is a command to a supplier requesting the supply of products or services.

[0534] "Workers" are personnel hired to carry out store operations and business activities.

[0535] A "work plan" is a plan that outlines the time allocation and work assignments necessary for workers to work effectively.

[0536] "Customer visitor prediction data" refers to information used to predict the number of customers who visit a store and their behavior.

[0537] "Working conditions" refer to various factors such as the environment, hours, and treatment of workers when they are employed.

[0538] "Sales promotion activity data" refers to information about the content and effectiveness of past promotional activities.

[0539] A "plan" is a strategy or plan devised to achieve a specific objective.

[0540] "Electronic devices" are devices that use electronic engineering technology to process and display information.

[0541] "Inventory information" refers to information about the quantity and condition of products in warehouses and stores.

[0542] A "smart device" is a portable electronic device that uses information and communication technology to achieve multiple functions.

[0543] "Notification" refers to the act or function of sending information and informing others.

[0544] The system implementing this invention provides functions to streamline store operations through the organic cooperation of a server, terminals, and users. The server continuously collects and stores past sales information and related data in a cloud database to perform demand forecasting. Using this data, it executes a highly accurate demand forecasting algorithm utilizing machine learning technology, places appropriate orders based on the forecast results, and sends instructions to suppliers. For example, it is possible to predict the demand for juices by considering next week's weather forecast and adjust the order quantity appropriately.

[0545] The server further optimizes worker schedules by referencing customer forecast data and working conditions, generating and distributing optimal work schedules to terminals. Through these terminals, users can review their schedules and adjust their shifts as needed. This system allows, for example, predicting an increase in customer traffic on Saturdays and creating appropriate work schedules that include additional staffing.

[0546] Furthermore, the server analyzes past sales promotion activity data and proposes effective plans. These plans are automatically set and notified to customers via electronic devices. In addition, smart devices notify users of inventory and plan information in real time, allowing for immediate adjustments to sales strategies. For example, by re-offering previously successful discount coupons to specific customer segments, a higher promotional effect can be achieved.

[0547] By utilizing a generative AI model and using prompts like the following, the system can perform even more detailed demand forecasts. An example of a prompt is, "Please propose a demand forecast for juices and inventory adjustment plans based on next week's weather forecast."

[0548] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0549] Step 1:

[0550] The server collects historical sales information and related data. In this step, it retrieves historical transaction data, customer information, and weather information from a cloud database as input. The server organizes this data and processes it into a dataset for demand forecasting. The output is a formatted dataset.

[0551] Step 2:

[0552] The server executes a demand forecasting algorithm using the formatted dataset. The dataset obtained in step 1 is used as input. Based on this, the server utilizes a machine learning model to forecast the next period's demand. This algorithmic processing yields future demand forecast results as output.

[0553] Step 3:

[0554] The server generates order instructions to suppliers based on demand forecast results. Here, the output from step 2 is used as input, and the order quantity is calculated considering the required number of goods and the supply chain situation. The calculation results are automatically sent as instructions to the suppliers. The output is a specific order instruction.

[0555] Step 4:

[0556] The server optimizes the worker's work schedule based on customer forecast data and working conditions. Using the customer forecast data obtained in Step 2 as input, it generates an optimal work schedule. This schedule takes working conditions into consideration and efficiently allocates workers' working hours and shifts. The optimized work schedule is output and delivered to the terminal.

[0557] Step 5:

[0558] The terminal displays the received work schedule to the user. Based on the entered work schedule, the user can check and adjust their shifts. In this step, the user directly operates and checks through the terminal's interface. The output is shift information that the user can check.

[0559] Step 6:

[0560] The server analyzes past sales promotion activity data and proposes new plans. Using the promotion activity data obtained in Step 1 as input, the server performs data analysis and generates an effective sales plan. The output is the proposed sales plan, which is automatically set and executed.

[0561] Step 7:

[0562] The terminal notifies the user of inventory and promotional information via a smart device. This step provides a mechanism to notify the smart device of the latest inventory and campaign information obtained from the server as input. The output is the notification information received by the user. This notification allows the user to immediately check inventory and adjust sales strategies.

[0563] 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.

[0564] The system of this invention aims to improve not only the efficiency of store operations but also the quality of customer service by combining it with an emotion engine that recognizes user emotions. In addition to functions such as demand forecasting, inventory management, shift management, and campaign management, the system can analyze customer emotions and reflect them in store operations.

[0565] The server inputs customer feedback, either in-store or through online platforms, into an emotion recognition algorithm. This algorithm utilizes natural language processing techniques to analyze customer emotions in real time from text and voice. The resulting emotion information is then quantified to determine customer satisfaction and dissatisfaction factors, and stored in a database.

[0566] Based on this sentiment information, users can develop even more customized customer response strategies. For example, if the sentiment engine's analysis indicates customer dissatisfaction, the system automatically proposes compensation offers or special discounts and notifies the customer immediately. Conversely, if positive feedback is received, the system can build promotional strategies to maximize its impact.

[0567] Furthermore, the server can perform emotion-based shift adjustments. For example, it can enable flexible shift scheduling by assigning more staff to times when complaints are frequently received.

[0568] As a concrete example, when dealing with a large number of customers during a holiday sale, the emotion engine analyzes feedback in real time and points out that the staff may be overworked. Based on this result, the server immediately reorganizes the shifts to allocate more resources and takes measures to reduce the burden on the staff.

[0569] This invention, by incorporating an emotion engine in this way, is a system that not only improves efficiency but also comprehensively enhances the customer experience.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The server retrieves customer text and voice feedback collected in-store and online. This includes customer surveys, reviews, and conversation history.

[0573] Step 2:

[0574] The server runs an emotion recognition algorithm to analyze customer emotions in real time from collected feedback. This algorithm uses natural language processing techniques to classify emotions as positive, negative, neutral, etc.

[0575] Step 3:

[0576] The server stores the analysis results in a database and generates satisfaction reports for each customer segment based on this sentiment data. The reports are updated regularly and serve as reference material for customer service strategies.

[0577] Step 4:

[0578] Users access emotional data to formulate specific strategies for store operations and customer service. Based on the analysis results of the emotional engine, they determine special offers and discounts to improve customer satisfaction.

[0579] Step 5:

[0580] The server automates the determined customer response and delivers promotional content to each customer's device as needed. This process is fully automated, enabling a rapid response to customers.

[0581] Step 6:

[0582] The server takes emotional data into consideration and provides information to the shift management system. This information is used to adjust shifts, such as requiring additional staff during times when there is a lot of unsatisfactory feedback.

[0583] Step 7:

[0584] Users will check the shift information provided on their terminals and ensure that it is communicated to the staff. They will also monitor whether suggestions based on feedback are being implemented appropriately and make adjustments as needed.

[0585] Step 8:

[0586] For example, if the emotion engine reports an increase in customer dissatisfaction during peak hours on Saturday, the server will immediately use this information to increase staffing and implement measures to improve the quality of service.

[0587] In this way, this system can optimize customer service and store operations using emotional data.

[0588] (Example 2)

[0589] 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."

[0590] Improving customer satisfaction and streamlining store operations simultaneously is a critical challenge for many organizations. While traditional systems could forecast demand and optimize shifts, they struggled to adjust operations in real time, taking customer sentiment into account. Furthermore, there is a need to quickly customize customer service and efficiently allocate staff.

[0591] 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.

[0592] In this invention, the server includes means for collecting past sales history and related data in order to forecast demand; means for performing calculations to forecast the next period's demand based on the collected data; means for calculating the order quantity based on the forecast and automatically sending order instructions to suppliers; means for analyzing customer reactions and extracting emotional information; means for storing the extracted emotional information in a database; means for automating customer response strategies based on the emotional information; and means for adjusting personnel shifts based on customer emotional information. This enables real-time adjustment of store operations based on customer emotions and prompt and appropriate customer response.

[0593] "Demand forecasting" refers to estimating future demand based on past sales history and related information.

[0594] "Sales history" refers to records of past sales of goods or services.

[0595] "Related data" refers to supplementary information that is thought to influence sales history, and this includes market trends and seasonality.

[0596] "Order quantity" refers to the number of goods ordered from a supplier.

[0597] A "supplier" refers to an organization or individual that provides goods or services.

[0598] "Personnel shifts" refer to the arrangement of working hours and schedules for employees.

[0599] "Store visit prediction data" refers to information about predicted customer visits to stores in the future.

[0600] "Working conditions" refer to the various conditions that apply to employees when they are working, and include working hours, salary, and benefits.

[0601] "Sales promotion data" refers to information about sales promotion activities that have been conducted in the past.

[0602] "Sales promotion" refers to various activities aimed at encouraging the sale of goods and services.

[0603] "Customer response" refers to the feelings and opinions that customers express about a service or product.

[0604] "Emotional information" refers to data about emotions extracted from customer responses.

[0605] A "database" is a system for managing a collection of information, enabling efficient information retrieval and manipulation.

[0606] "Customer service strategies" refer to specific means and plans for providing services and support to customers.

[0607] Embodiments of the present invention will now be described. This system aims to improve the efficiency of store operations and enhance customer service by taking customer emotions into consideration. The main components of the system are a server, terminals, and users. The server plays a central role in processing and analyzing data using advanced algorithms.

[0608] The server can be implemented with a variety of hardware and software configurations. For example, the server might use natural language processing libraries such as TextBlob written in Python, or the Google Cloud Natural Language API, to extract sentiment information from customer feedback. This information is used to analyze customer satisfaction and dissatisfaction factors. The obtained data is stored in a storage solution such as a SQL database.

[0609] The device provides an interface for customers to provide feedback. Specifically, it functions as an application on a mobile device or PC, sending entered text and audio data to the server in real time. This allows the server to quickly process the data and extract sentiment information.

[0610] Users develop store operations and customer service strategies based on sentiment data provided by the server. If customer sentiment is negative, users can implement compensation offers or special discounts based on automated suggestions. Conversely, if positive feedback is received, they can develop strategies for further sales promotion.

[0611] For example, if analysis of customer feedback from customers who visited during a holiday sale reveals that staff are overloaded at specific times, the server will suggest shift adjustments based on these findings. This allows for the allocation of additional personnel, thereby reducing staff workload and maintaining the quality of customer service.

[0612] An example of a prompt might be, "Please suggest an effective shift management method using real-time sentiment feedback during holiday sales." Based on such prompts, the system is expected to generate the optimal solution.

[0613] In this way, the system of the present invention goes beyond demand forecasting and inventory management, enabling a comprehensive store management strategy that leverages customer emotions.

[0614] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0615] Step 1:

[0616] The server collects customer feedback data from both in-store and online platforms. This input data includes text and voice feedback. Terminals transmit customer input to the server in real time, enabling rapid data collection.

[0617] Step 2:

[0618] The server feeds the collected data into an emotion recognition algorithm. Based on natural language processing techniques, it analyzes the input text and audio data to determine positive, negative, or neutral emotions. This process uses TextBlob and the Google Cloud Natural Language API for data analysis. The output is a customer emotion score.

[0619] Step 3:

[0620] The server stores the analyzed sentiment information in a database. It receives sentiment scores as input and stores them in association with each customer. This step makes it possible to refer to the sentiment analysis results individually or collectively at a later date.

[0621] Step 4:

[0622] Users formulate strategies based on sentiment information stored on the server. Specifically, they determine customer response measures based on sentiment scores. For example, they devise special promotions or responses for customers exhibiting negative sentiment and automatically notify them through the server.

[0623] Step 5:

[0624] The server optimizes shift management based on real-time sentiment data. It takes sentiment information and customer traffic prediction data as input and generates adjusted staff shifts as output. For example, if many complaints are reported during a particular time period, it takes measures such as assigning additional staff.

[0625] This allows the system to comprehensively support improvements in the customer experience.

[0626] (Application Example 2)

[0627] 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."

[0628] In today's world, where efficient store operations and improved customer service are paramount, simultaneously achieving optimal staffing and increased customer satisfaction is crucial. However, conventional systems lacked the means to effectively address these challenges in real time. Specifically, shift adjustments based on customer traffic forecasts and immediate customer service were difficult, and operations that took customer emotions into account were not adequately implemented.

[0629] 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.

[0630] In this invention, the server includes means for collecting past sales history and related data to perform demand forecasting, means for executing an algorithm to forecast future demand based on the collected data, and means for calculating order quantities based on the forecast and automatically sending order instructions to suppliers. This enables optimal work allocation for employees and immediate response measures based on customer sentiment.

[0631] "Demand forecasting" is the process of predicting future demand by analyzing past sales history and related data.

[0632] "Optimizing worker shifts" refers to a method of efficiently creating and distributing worker shifts by considering customer traffic forecast data and working conditions.

[0633] "Emotion recognition" is a technology that analyzes emotions from a customer's text or voice and grasps their emotional state in real time.

[0634] "Sales promotion proposals" refer to analyzing past campaign data and proposing effective promotional strategies.

[0635] "Smartphone-based emotion analysis" is a function that uses the camera and microphone of a smart device to recognize emotions from a customer's facial expressions and voice.

[0636] "Automatically sending order instructions to suppliers" refers to a system that calculates the required quantity based on demand forecasts and automatically sends that order information to suppliers.

[0637] To implement this invention, the server provides a system that collects and analyzes customer emotions in real time via the internet. Specifically, when a customer uses a smart device and performs voice or text input, the data is sent to the cloud and analyzed using natural language processing technology. Based on the analysis results, the server recognizes the customer's emotions and, if necessary, immediately presents the customer with appropriate countermeasures.

[0638] The hardware used includes smartphones and tablets, which are equipped with devices such as cameras and microphones. The software utilizes natural language processing libraries such as the Google Cloud Natural Language API to analyze customer emotions from text and voice. Furthermore, a database management system is used for data management, and the accumulated emotional data is used to improve the service.

[0639] For example, if a customer complains about being kept waiting for a long time in a shopping center, a smart device can pick up on their voice, and an emotion recognition engine can detect their dissatisfaction. A server immediately receives this information and automatically notifies the customer that they can use a coupon on their next visit.

[0640] An example of a prompt to the generating AI model is, "Suggest promotions and response methods to use when a customer expresses dissatisfaction." This system enables real-time and effective customer support.

[0641] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0642] Step 1:

[0643] The device uses the smartphone's camera and microphone to capture the customer's facial expressions and voice in real time. This input data serves as foundational data for analyzing emotions.

[0644] Step 2:

[0645] The device sends the captured audio and text data to the cloud. There, natural language processing libraries such as the Google Cloud Natural Language API are used to analyze the data and extract emotional information. This analysis classifies the data into emotional categories such as "positive" or "negative."

[0646] Step 3:

[0647] The server stores the customer's emotional state in a database based on the emotional information received from the cloud. This step involves data processing, where the emotional data is associated with the customer ID and stored accordingly.

[0648] Step 4:

[0649] The server analyzes stored emotional information to determine the appropriate customer response. For example, if the emotional recognition result indicates "dissatisfaction," the server runs a program (generative AI model) to propose compensation offers or special discounts to that customer.

[0650] Step 5:

[0651] The server notifies the customer's device of the generated countermeasures. This notification is delivered instantly via push notification or email, immediately communicating the information to the customer.

[0652] Step 6:

[0653] Users (i.e., store staff) can receive customer response strategies sent from the server, contact customers based on those strategies, and provide appropriate support and services.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] [Fourth Embodiment]

[0658] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0659] 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.

[0660] 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).

[0661] 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.

[0662] 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.

[0663] 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).

[0664] 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.

[0665] 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.

[0666] 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.

[0667] 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.

[0668] 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.

[0669] 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.

[0670] 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".

[0671] The system of the present invention aims to improve the efficiency of store operations by using an AI agent to automate demand forecasting, inventory management, shift management, and campaign management. The following components and operations are required to implement the present invention.

[0672] The server functions as the core, continuously collecting historical sales data, customer information, and relevant data such as weather and events. This data is stored in a cloud database and analyzed by a demand forecasting algorithm. This algorithm uses machine learning techniques to predict future demand with high accuracy. Based on these forecasts, the server calculates the optimal order quantity and automatically sends order instructions to suppliers.

[0673] Similarly, the server uses customer visitor forecast data to generate optimal staff shifts. This allows for staffing levels that match customer numbers, ensuring a balanced workforce allocation. The shift schedule is distributed to staff terminals, allowing users to review its contents. It's also possible to suggest shift adjustments as needed.

[0674] Furthermore, the server analyzes campaign data and automatically generates effective promotional strategies. Based on past campaign successes and response rates, it plans coupons and discounts tailored to specific days of the week and time slots. This campaign information is integrated with POS systems and online advertising platforms, and automatically configured and executed. Users can monitor the results on a dashboard and receive real-time feedback.

[0675] For example, in the summer, the server predicts that rising temperatures will increase demand for ice cream and automatically instructs the system to increase the order quantity. It can also predict an increase in Saturday foot traffic and suggest additional staffing shifts. For campaigns, optimizations are made, such as re-offering a previously successful 20% discount coupon to specific customer segments.

[0676] Thus, this invention aims to improve customer satisfaction by utilizing AI technology to streamline and optimize store operations.

[0677] The following describes the processing flow.

[0678] Step 1:

[0679] The server collects historical sales data, customer information, and event information from client databases and external APIs. This includes sales data from the past several years and sales trends for specific periods.

[0680] Step 2:

[0681] The server preprocesses the collected data and formats it as an input dataset for machine learning algorithms. This process includes imputing missing values ​​and removing outliers.

[0682] Step 3:

[0683] The server uses machine learning models to forecast demand. The algorithm employs gradient boosting and time series analysis to predict future demand.

[0684] Step 4:

[0685] The server calculates the optimal inventory order quantity based on the prediction results. Furthermore, it generates automated order instructions for suppliers and sends them via the internet.

[0686] Step 5:

[0687] The server collects and analyzes weather information and past customer data to predict the number of customers visiting the store each day.

[0688] Step 6:

[0689] The server creates an optimal staff shift schedule based on customer traffic prediction data. It assigns appropriate hours and staff numbers to each member in accordance with labor regulations.

[0690] Step 7:

[0691] The server distributes the generated shift schedule to each staff member's terminal. Users can check their schedule through their terminal and inquire if they have any questions.

[0692] Step 8:

[0693] The server analyzes the effectiveness of past campaigns and automatically generates new promotional strategies. Based on the day of the week and customer segments, it determines the most effective coupons and discounts.

[0694] Step 9:

[0695] The server automatically configures the determined campaign information on the relevant digital platforms. This automates the start and management of advertising.

[0696] Step 10:

[0697] Users can monitor results in real time on a dashboard. They can check campaign effectiveness and inventory status, and fine-tune settings as needed.

[0698] (Example 1)

[0699] 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".

[0700] Responding quickly and accurately to fluctuations in demand is difficult in store operations. Furthermore, personnel management and campaign management have traditionally relied heavily on manual processes, leading to inefficiencies. In particular, there is a challenge in efficiently utilizing historical data and external information, which prevents optimal decision-making.

[0701] 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.

[0702] In this invention, the server includes means for collecting information to forecast demand, means for executing an algorithm to forecast demand based on the collected information, and means for calculating quantities based on the forecast and automatically sending instructions to suppliers. This enables automated and efficient store operations based on data.

[0703] "Demand forecasting" is the process of predicting future fluctuations in demand based on past data and influencing factors.

[0704] "Means of collecting information" refers to devices and processes for systematically collecting various data related to store operations.

[0705] An "algorithm" is a set of procedures or calculation methods defined to solve a specific problem. In this invention, it specifically refers to a calculation method for forecasting demand.

[0706] A "supplier" is a company or organization that provides goods or services to a store.

[0707] "Means of automatic transmission" refers to methods or devices that allow a system to send instructions based on predictions or calculations to relevant organizations without manual intervention.

[0708] "Means of optimizing working hours" refer to systems and methods for efficiently allocating employees' working hours and securing the necessary personnel for operations.

[0709] "Visitor forecast information" refers to data used to predict the number of customers visiting a store during a specific time period.

[0710] A "work schedule" is a table that shows the work shifts of employees and is used to plan staffing arrangements.

[0711] "Past project information" refers to data related to campaigns and promotions that were previously conducted.

[0712] "Means of proposing advertising" refers to devices and methods for planning and proposing effective advertising activities based on data analysis.

[0713] "Means for automatic setup and execution" refers to methods or devices that allow the system to set up and start the proposed advertisement without manual operation.

[0714] A "dashboard" is an interface that visually displays the system's operating status and analysis results.

[0715] A "generative AI model" is a program that uses artificial intelligence to generate patterns and predictions.

[0716] "Weather information" refers to data on temperature, precipitation, weather, etc., and is used to predict store visits.

[0717] The system of this invention aims to improve the efficiency of store operations, with a server playing a central role. This server collects various information related to the store and has multiple functions for efficient demand forecasting and management.

[0718] The server collects data from various sources, including sales history, customer information, weather information, and event information. This data is stored in a cloud database and continuously updated. On this database, the server executes demand forecasting algorithms. The algorithms used here include generative AI models, achieving high forecasting accuracy. Furthermore, weather information is used as an important factor in predicting the number of visitors.

[0719] The server calculates the optimal order quantity based on demand forecasts and automatically sends this instruction to suppliers. This uses an API that can communicate with the order management system. It also optimizes employee work shifts using visitor forecast information and delivers the results to terminals. Staff can review the delivered shift information and suggest adjustments as needed.

[0720] Furthermore, the server analyzes past campaign data and proposes effective advertising strategies. The proposed advertising is integrated with POS systems and online platforms and executed automatically. Throughout this process, users can view real-time results on a dashboard and obtain necessary feedback.

[0721] For example, in the summer, the server predicts increased demand for ice cream due to high temperatures and automatically places additional orders. Also, if an increase in Saturday visitor numbers is predicted, it creates a shift schedule suggesting the deployment of additional staff. For campaigns, a strategy is automatically set up to redistribute 20% discount coupons to specific customer segments. All of these functions are based on generative AI models and advanced analytical techniques, with the following prompt being used as an example: "Perform demand forecasts for each product category based on the weather patterns for the next holiday and historical sales data." This allows the server to support efficient and effective store operations.

[0722] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0723] Step 1:

[0724] The server collects store-related data such as sales history, customer information, weather information, and event information from external data sources. This input data is obtained through various APIs and database connections. The acquired data is stored in a cloud database to prepare for subsequent processing.

[0725] Step 2:

[0726] The server cleanses the collected data and performs demand forecasting using a generated AI model. Specifically, it inputs time-series data and other information into the model, analyzes and learns data patterns, and then outputs demand forecast values ​​for a specified period.

[0727] Step 3:

[0728] The server calculates the optimal order quantity for each product based on demand forecasts. This calculation uses an algorithm that takes into account past sales performance, inventory levels, lead times, and other factors. As output, it determines the order quantity for each product and generates instructions to input into a dedicated order management system and automatically send them to suppliers.

[0729] Step 4:

[0730] The server optimizes work shifts by considering visitor forecasts and working conditions. This process uses the predicted number of visitors, each employee's schedule, and skill set as input to calculate the optimal staffing. The generated work schedule is then distributed to the terminals.

[0731] Step 5:

[0732] The server analyzes past campaign data and automatically generates effective advertising strategies. Using campaign response rates and sales performance as input, it optimizes promotions based on this information and outputs coupon and discount suggestions. The generated advertising information is then linked to POS systems and online advertising platforms, and execution is instructed.

[0733] Step 6:

[0734] Users can use the dashboard to monitor server-generated results and promotional effectiveness in real time. This monitoring allows them to evaluate the success of promotions and improvements in operational efficiency, and provide necessary feedback.

[0735] (Application Example 1)

[0736] 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".

[0737] Traditional store operations faced problems such as the significant effort and time required for demand forecasting, inventory management, and staff shift management. This hindered efficient store operations and often led to decreased customer satisfaction. Furthermore, the difficulty in managing and verifying inventory and staff work information in real time exacerbated these problems, especially in situations requiring quick responses.

[0738] 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.

[0739] In this invention, the server includes means for collecting past sales information and related data to forecast demand; means for executing an algorithm to forecast the next period's demand based on the collected data; means for automatically sending order instructions to suppliers based on the forecast; means for optimizing the work schedule of workers in business operations; means for generating and distributing work schedules considering customer forecast data and working conditions; means for analyzing past sales promotion activity data and proposing plans; means for automatically setting and executing the proposed plans; means for displaying inventory information using electronic devices; and means for notifying smart devices of work schedules and plan information. This improves the efficiency of store operations and enables real-time information management and rapid response.

[0740] "Demand forecasting" is the process of predicting future consumption trends for products and services based on past sales information and related data.

[0741] "Sales information" refers to data relating to transactions of a product or service during a specific period.

[0742] "Related data" refers to various types of data that are used to complement sales information, such as customer purchasing trends and market conditions.

[0743] An "algorithm" is a set of procedures or methods for performing a specific calculation or process.

[0744] A "supplier" is an organization or company that supplies products or services to a store or business entity.

[0745] An "order instruction" is a command to a supplier requesting the supply of products or services.

[0746] "Workers" are personnel hired to carry out store operations and business activities.

[0747] A "work plan" is a plan that outlines the time allocation and work assignments necessary for workers to work effectively.

[0748] "Customer visitor prediction data" refers to information used to predict the number of customers who visit a store and their behavior.

[0749] "Working conditions" refer to various factors such as the environment, hours, and treatment of workers when they are employed.

[0750] "Sales promotion activity data" refers to information about the content and effectiveness of past promotional activities.

[0751] A "plan" is a strategy or plan devised to achieve a specific objective.

[0752] "Electronic devices" are devices that use electronic engineering technology to process and display information.

[0753] "Inventory information" refers to information about the quantity and condition of products in warehouses and stores.

[0754] A "smart device" is a portable electronic device that uses information and communication technology to achieve multiple functions.

[0755] "Notification" refers to the act or function of sending information and informing others.

[0756] The system implementing this invention provides functions to streamline store operations through the organic cooperation of a server, terminals, and users. The server continuously collects and stores past sales information and related data in a cloud database to perform demand forecasting. Using this data, it executes a highly accurate demand forecasting algorithm utilizing machine learning technology, places appropriate orders based on the forecast results, and sends instructions to suppliers. For example, it is possible to predict the demand for juices by considering next week's weather forecast and adjust the order quantity appropriately.

[0757] The server further optimizes worker schedules by referencing customer forecast data and working conditions, generating and distributing optimal work schedules to terminals. Through these terminals, users can review their schedules and adjust their shifts as needed. This system allows, for example, predicting an increase in customer traffic on Saturdays and creating appropriate work schedules that include additional staffing.

[0758] Furthermore, the server analyzes past sales promotion activity data and proposes effective plans. These plans are automatically set and notified to customers via electronic devices. In addition, smart devices notify users of inventory and plan information in real time, allowing for immediate adjustments to sales strategies. For example, by re-offering previously successful discount coupons to specific customer segments, a higher promotional effect can be achieved.

[0759] By utilizing a generative AI model and using prompts like the following, the system can perform even more detailed demand forecasts. An example of a prompt is, "Please propose a demand forecast for juices and inventory adjustment plans based on next week's weather forecast."

[0760] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0761] Step 1:

[0762] The server collects historical sales information and related data. In this step, it retrieves historical transaction data, customer information, and weather information from a cloud database as input. The server organizes this data and processes it into a dataset for demand forecasting. The output is a formatted dataset.

[0763] Step 2:

[0764] The server executes a demand forecasting algorithm using the formatted dataset. The dataset obtained in step 1 is used as input. Based on this, the server utilizes a machine learning model to forecast the next period's demand. This algorithmic processing yields future demand forecast results as output.

[0765] Step 3:

[0766] The server generates order instructions to suppliers based on demand forecast results. Here, the output from step 2 is used as input, and the order quantity is calculated considering the required number of goods and the supply chain situation. The calculation results are automatically sent as instructions to the suppliers. The output is a specific order instruction.

[0767] Step 4:

[0768] The server optimizes the worker's work schedule based on customer forecast data and working conditions. Using the customer forecast data obtained in Step 2 as input, it generates an optimal work schedule. This schedule takes working conditions into consideration and efficiently allocates workers' working hours and shifts. The optimized work schedule is output and delivered to the terminal.

[0769] Step 5:

[0770] The terminal displays the received work schedule to the user. Based on the entered work schedule, the user can check and adjust their shifts. In this step, the user directly operates and checks through the terminal's interface. The output is shift information that the user can check.

[0771] Step 6:

[0772] The server analyzes past sales promotion activity data and proposes new plans. Using the promotion activity data obtained in Step 1 as input, the server performs data analysis and generates an effective sales plan. The output is the proposed sales plan, which is automatically set and executed.

[0773] Step 7:

[0774] The terminal notifies the user of inventory and promotional information via a smart device. This step provides a mechanism to notify the smart device of the latest inventory and campaign information obtained from the server as input. The output is the notification information received by the user. This notification allows the user to immediately check inventory and adjust sales strategies.

[0775] 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.

[0776] The system of this invention aims to improve not only the efficiency of store operations but also the quality of customer service by combining it with an emotion engine that recognizes user emotions. In addition to functions such as demand forecasting, inventory management, shift management, and campaign management, the system can analyze customer emotions and reflect them in store operations.

[0777] The server inputs customer feedback, either in-store or through online platforms, into an emotion recognition algorithm. This algorithm utilizes natural language processing techniques to analyze customer emotions in real time from text and voice. The resulting emotion information is then quantified to determine customer satisfaction and dissatisfaction factors, and stored in a database.

[0778] Based on this sentiment information, users can develop even more customized customer response strategies. For example, if the sentiment engine's analysis indicates customer dissatisfaction, the system automatically proposes compensation offers or special discounts and notifies the customer immediately. Conversely, if positive feedback is received, the system can build promotional strategies to maximize its impact.

[0779] Furthermore, the server can perform emotion-based shift adjustments. For example, it can enable flexible shift scheduling by assigning more staff to times when complaints are frequently received.

[0780] As a concrete example, when dealing with a large number of customers during a holiday sale, the emotion engine analyzes feedback in real time and points out that the staff may be overworked. Based on this result, the server immediately reorganizes the shifts to allocate more resources and takes measures to reduce the burden on the staff.

[0781] This invention, by incorporating an emotion engine in this way, is a system that not only improves efficiency but also comprehensively enhances the customer experience.

[0782] The following describes the processing flow.

[0783] Step 1:

[0784] The server retrieves customer text and voice feedback collected in-store and online. This includes customer surveys, reviews, and conversation history.

[0785] Step 2:

[0786] The server runs an emotion recognition algorithm to analyze customer emotions in real time from collected feedback. This algorithm uses natural language processing techniques to classify emotions as positive, negative, neutral, etc.

[0787] Step 3:

[0788] The server stores the analysis results in a database and generates satisfaction reports for each customer segment based on this sentiment data. The reports are updated regularly and serve as reference material for customer service strategies.

[0789] Step 4:

[0790] Users access emotional data to formulate specific strategies for store operations and customer service. Based on the analysis results of the emotional engine, they determine special offers and discounts to improve customer satisfaction.

[0791] Step 5:

[0792] The server automates the determined customer response and delivers promotional content to each customer's device as needed. This process is fully automated, enabling a rapid response to customers.

[0793] Step 6:

[0794] The server takes emotional data into consideration and provides information to the shift management system. This information is used to adjust shifts, such as requiring additional staff during times when there is a lot of unsatisfactory feedback.

[0795] Step 7:

[0796] Users will check the shift information provided on their terminals and ensure that it is communicated to the staff. They will also monitor whether suggestions based on feedback are being implemented appropriately and make adjustments as needed.

[0797] Step 8:

[0798] For example, if the emotion engine reports an increase in customer dissatisfaction during peak hours on Saturday, the server will immediately use this information to increase staffing and implement measures to improve the quality of service.

[0799] In this way, this system can optimize customer service and store operations using emotional data.

[0800] (Example 2)

[0801] 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".

[0802] Improving customer satisfaction and streamlining store operations simultaneously is a critical challenge for many organizations. While traditional systems could forecast demand and optimize shifts, they struggled to adjust operations in real time, taking customer sentiment into account. Furthermore, there is a need to quickly customize customer service and efficiently allocate staff.

[0803] 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.

[0804] In this invention, the server includes means for collecting past sales history and related data in order to forecast demand; means for performing calculations to forecast the next period's demand based on the collected data; means for calculating the order quantity based on the forecast and automatically sending order instructions to suppliers; means for analyzing customer reactions and extracting emotional information; means for storing the extracted emotional information in a database; means for automating customer response strategies based on the emotional information; and means for adjusting personnel shifts based on customer emotional information. This enables real-time adjustment of store operations based on customer emotions and prompt and appropriate customer response.

[0805] "Demand forecasting" refers to estimating future demand based on past sales history and related information.

[0806] "Sales history" refers to records of past sales of goods or services.

[0807] "Related data" refers to supplementary information that is thought to influence sales history, and this includes market trends and seasonality.

[0808] "Order quantity" refers to the number of goods ordered from a supplier.

[0809] A "supplier" refers to an organization or individual that provides goods or services.

[0810] "Personnel shifts" refer to the arrangement of working hours and schedules for employees.

[0811] "Store visit prediction data" refers to information about predicted customer visits to stores in the future.

[0812] "Working conditions" refer to the various conditions that apply to employees when they are working, and include working hours, salary, and benefits.

[0813] "Sales promotion data" refers to information about sales promotion activities that have been conducted in the past.

[0814] "Sales promotion" refers to various activities aimed at encouraging the sale of goods and services.

[0815] "Customer response" refers to the feelings and opinions that customers express about a service or product.

[0816] "Emotional information" refers to data about emotions extracted from customer responses.

[0817] A "database" is a system for managing a collection of information, enabling efficient information retrieval and manipulation.

[0818] "Customer service strategies" refer to specific means and plans for providing services and support to customers.

[0819] Embodiments of the present invention will now be described. This system aims to improve the efficiency of store operations and enhance customer service by taking customer emotions into consideration. The main components of the system are a server, terminals, and users. The server plays a central role in processing and analyzing data using advanced algorithms.

[0820] The server can be implemented with a variety of hardware and software configurations. For example, the server might use natural language processing libraries such as TextBlob written in Python, or the Google Cloud Natural Language API, to extract sentiment information from customer feedback. This information is used to analyze customer satisfaction and dissatisfaction factors. The obtained data is stored in a storage solution such as a SQL database.

[0821] The device provides an interface for customers to provide feedback. Specifically, it functions as an application on a mobile device or PC, sending entered text and audio data to the server in real time. This allows the server to quickly process the data and extract sentiment information.

[0822] Users develop store operations and customer service strategies based on sentiment data provided by the server. If customer sentiment is negative, users can implement compensation offers or special discounts based on automated suggestions. Conversely, if positive feedback is received, they can develop strategies for further sales promotion.

[0823] For example, if analysis of customer feedback from customers who visited during a holiday sale reveals that staff are overloaded at specific times, the server will suggest shift adjustments based on these findings. This allows for the allocation of additional personnel, thereby reducing staff workload and maintaining the quality of customer service.

[0824] An example of a prompt might be, "Please suggest an effective shift management method using real-time sentiment feedback during holiday sales." Based on such prompts, the system is expected to generate the optimal solution.

[0825] In this way, the system of the present invention goes beyond demand forecasting and inventory management, enabling a comprehensive store management strategy that leverages customer emotions.

[0826] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0827] Step 1:

[0828] The server collects customer feedback data from both in-store and online platforms. This input data includes text and voice feedback. Terminals transmit customer input to the server in real time, enabling rapid data collection.

[0829] Step 2:

[0830] The server feeds the collected data into an emotion recognition algorithm. Based on natural language processing techniques, it analyzes the input text and audio data to determine positive, negative, or neutral emotions. This process uses TextBlob and the Google Cloud Natural Language API for data analysis. The output is a customer emotion score.

[0831] Step 3:

[0832] The server stores the analyzed sentiment information in a database. It receives sentiment scores as input and stores them in association with each customer. This step makes it possible to refer to the sentiment analysis results individually or collectively at a later date.

[0833] Step 4:

[0834] Users formulate strategies based on sentiment information stored on the server. Specifically, they determine customer response measures based on sentiment scores. For example, they devise special promotions or responses for customers exhibiting negative sentiment and automatically notify them through the server.

[0835] Step 5:

[0836] The server optimizes shift management based on real-time sentiment data. It takes sentiment information and customer traffic prediction data as input and generates adjusted staff shifts as output. For example, if many complaints are reported during a particular time period, it takes measures such as assigning additional staff.

[0837] This allows the system to comprehensively support improvements in the customer experience.

[0838] (Application Example 2)

[0839] 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".

[0840] In today's world, where efficient store operations and improved customer service are paramount, simultaneously achieving optimal staffing and increased customer satisfaction is crucial. However, conventional systems lacked the means to effectively address these challenges in real time. Specifically, shift adjustments based on customer traffic forecasts and immediate customer service were difficult, and operations that took customer emotions into account were not adequately implemented.

[0841] 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.

[0842] In this invention, the server includes means for collecting past sales history and related data to perform demand forecasting, means for executing an algorithm to forecast future demand based on the collected data, and means for calculating order quantities based on the forecast and automatically sending order instructions to suppliers. This enables optimal work allocation for employees and immediate response measures based on customer sentiment.

[0843] "Demand forecasting" is the process of predicting future demand by analyzing past sales history and related data.

[0844] "Optimizing worker shifts" refers to a method of efficiently creating and distributing worker shifts by considering customer traffic forecast data and working conditions.

[0845] "Emotion recognition" is a technology that analyzes emotions from a customer's text or voice and grasps their emotional state in real time.

[0846] "Sales promotion proposals" refer to analyzing past campaign data and proposing effective promotional strategies.

[0847] "Smartphone-based emotion analysis" is a function that uses the camera and microphone of a smart device to recognize emotions from a customer's facial expressions and voice.

[0848] "Automatically sending order instructions to suppliers" refers to a system that calculates the required quantity based on demand forecasts and automatically sends that order information to suppliers.

[0849] To implement this invention, the server provides a system that collects and analyzes customer emotions in real time via the internet. Specifically, when a customer uses a smart device and performs voice or text input, the data is sent to the cloud and analyzed using natural language processing technology. Based on the analysis results, the server recognizes the customer's emotions and, if necessary, immediately presents the customer with appropriate countermeasures.

[0850] The hardware used includes smartphones and tablets, which are equipped with devices such as cameras and microphones. The software utilizes natural language processing libraries such as the Google Cloud Natural Language API to analyze customer emotions from text and voice. Furthermore, a database management system is used for data management, and the accumulated emotional data is used to improve the service.

[0851] For example, if a customer complains about being kept waiting for a long time in a shopping center, a smart device can pick up on their voice, and an emotion recognition engine can detect their dissatisfaction. A server immediately receives this information and automatically notifies the customer that they can use a coupon on their next visit.

[0852] An example of a prompt to the generating AI model is, "Suggest promotions and response methods to use when a customer expresses dissatisfaction." This system enables real-time and effective customer support.

[0853] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0854] Step 1:

[0855] The device uses the smartphone's camera and microphone to capture the customer's facial expressions and voice in real time. This input data serves as foundational data for analyzing emotions.

[0856] Step 2:

[0857] The device sends the captured audio and text data to the cloud. There, natural language processing libraries such as the Google Cloud Natural Language API are used to analyze the data and extract emotional information. This analysis classifies the data into emotional categories such as "positive" or "negative."

[0858] Step 3:

[0859] The server stores the customer's emotional state in a database based on the emotional information received from the cloud. This step involves data processing, where the emotional data is associated with the customer ID and stored accordingly.

[0860] Step 4:

[0861] The server analyzes stored emotional information to determine the appropriate customer response. For example, if the emotional recognition result indicates "dissatisfaction," the server runs a program (generative AI model) to propose compensation offers or special discounts to that customer.

[0862] Step 5:

[0863] The server notifies the customer's device of the generated countermeasures. This notification is delivered instantly via push notification or email, immediately communicating the information to the customer.

[0864] Step 6:

[0865] Users (i.e., store staff) can receive customer response strategies sent from the server, contact customers based on those strategies, and provide appropriate support and services.

[0866] 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.

[0867] 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.

[0868] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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.

[0873] 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.

[0874] 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."

[0875] 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.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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.

[0885] 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.

[0886] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0887] The following is further disclosed regarding the embodiments described above.

[0888] (Claim 1)

[0889] A means of collecting past sales history and related data in order to forecast demand,

[0890] A means of executing an algorithm that predicts the next period's demand based on the collected data,

[0891] A means of calculating the order quantity based on forecasts and automatically sending order instructions to suppliers,

[0892] Methods for optimizing staff shifts in store operations,

[0893] A means of generating and distributing shift schedules considering customer visit prediction data and working conditions,

[0894] A method for analyzing past campaign data and proposing promotions,

[0895] A system that includes means for automatically setting up and executing proposed promotions.

[0896] (Claim 2)

[0897] The system according to claim 1, characterized in that the demand forecasting algorithm includes a machine learning model.

[0898] (Claim 3)

[0899] The system according to claim 1, characterized in that it includes weather information as customer visit prediction data.

[0900] "Example 1"

[0901] (Claim 1)

[0902] Means of collecting information in order to forecast demand,

[0903] A means of executing an algorithm that predicts demand based on the collected information,

[0904] A means for calculating quantities based on forecasts and automatically sending instructions to suppliers,

[0905] Means for optimizing the working hours of personnel in business operations,

[0906] A means of generating and distributing work schedules that take into account visitor forecast information and working conditions,

[0907] A method of analyzing past project information and proposing advertising strategies,

[0908] Means for automatically setting up and executing proposed advertisements,

[0909] A system that includes a means of monitoring results through a dashboard and receiving suggestions for improvement.

[0910] (Claim 2)

[0911] The system according to claim 1, characterized in that the demand forecasting algorithm includes a generative AI model.

[0912] (Claim 3)

[0913] The system according to claim 1, characterized in that it includes weather information as visitor prediction information.

[0914] "Application Example 1"

[0915] (Claim 1)

[0916] A means of collecting historical sales information and related data in order to forecast demand,

[0917] A means of executing an algorithm that predicts the next period's demand based on the collected data,

[0918] A means of automatically sending order instructions to suppliers based on predictions,

[0919] A means of optimizing the work schedule of workers in business operations,

[0920] A means for generating and distributing work schedules that take into account customer forecast data and working conditions,

[0921] A method for analyzing past sales promotion activity data and proposing plans,

[0922] A means for automatically setting up and executing the proposed plan,

[0923] A means of displaying inventory information using electronic devices,

[0924] A means of notifying smart devices of work schedules and project information,

[0925] A system that includes this.

[0926] (Claim 2)

[0927] The system according to claim 1, characterized in that the demand forecasting algorithm includes a learning technology model.

[0928] (Claim 3)

[0929] The system according to claim 1, characterized in that it includes weather information as visitor prediction data.

[0930] "Example 2 of combining an emotion engine"

[0931] (Claim 1)

[0932] A means of collecting past sales history and related data in order to forecast demand,

[0933] A means of performing calculations to predict the next period's demand based on the collected data,

[0934] A means for calculating order quantities based on forecasts and automatically sending order instructions to suppliers,

[0935] Means for optimizing staff shifts in store operations,

[0936] A means of generating and distributing shifts considering customer visit prediction data and working conditions,

[0937] A method of analyzing past sales promotion data and proposing sales promotion strategies,

[0938] A means for automatically setting up and executing proposed sales promotions,

[0939] A means of analyzing customer reactions and extracting emotional information,

[0940] A means of storing the extracted emotional information in a database,

[0941] A means to automate customer service strategies based on emotional information,

[0942] A means of adjusting staff shifts based on customer sentiment information,

[0943] A system that includes this.

[0944] (Claim 2)

[0945] The system according to claim 1, characterized in that it includes a learning model in the demand forecasting calculation.

[0946] (Claim 3)

[0947] The system according to claim 1, characterized in that it includes weather information as store visit prediction data.

[0948] "Application example 2 when combining with an emotional engine"

[0949] (Claim 1)

[0950] A means of collecting past sales history and related data in order to forecast demand,

[0951] A means of executing an algorithm that predicts the next period's demand based on the collected data,

[0952] A means of calculating the order quantity based on forecasts and automatically sending order instructions to suppliers,

[0953] Means for optimizing the working hours of employees in store operations,

[0954] A means of generating and distributing work schedules considering customer visit prediction data and working conditions,

[0955] A method of analyzing past campaign data to propose sales promotions,

[0956] A means for automatically setting up and executing proposed sales promotions,

[0957] A means of recognizing and analyzing customer emotions in real time,

[0958] A means of formulating and notifying customer response measures based on emotion recognition,

[0959] A means of making shift adjustments based on emotions,

[0960] A system that includes a means of analyzing customer emotions using smartphones.

[0961] (Claim 2)

[0962] The system according to claim 1, characterized in that the demand forecasting algorithm includes an artificial intelligence model.

[0963] (Claim 3)

[0964] The system according to claim 1, characterized in that it includes weather information as customer visit prediction data. [Explanation of Symbols]

[0965] 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 means of collecting historical sales information and related data in order to forecast demand, A means of executing an algorithm that predicts the next period's demand based on the collected data, A means of automatically sending order instructions to suppliers based on predictions, A means of optimizing the work schedule of workers in business operations, A means for generating and distributing work schedules that take into account customer forecast data and working conditions, A method for analyzing past sales promotion activity data and proposing plans, A means for automatically setting up and executing the proposed plan, A means of displaying inventory information using electronic devices, A means of notifying smart devices of work schedules and project information, A system that includes this.

2. The system according to claim 1, characterized in that the demand forecasting algorithm includes a learning technology model.

3. The system according to claim 1, characterized in that it includes weather information as visitor prediction data.

Images