System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring sales data; means for acquiring weather information; means for acquiring regional event information; means for integrating and preprocessing the acquired data; means for predicting demand from the integrated data; means for determining an order quantity based on a demand prediction result; means for generating and notifying an order instruction to a user terminal; means for displaying the order instruction received by the user terminal; means for confirming and correcting order information by a user; and means for determining final order information and transmitting the final order information to a warehouse or a supplier.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] ---

[0005] Convenience stores and other retailers still rely on analog methods for inventory management of products with short expiration dates, resulting in food waste issues due to inefficient management. Accurate demand forecasts are also difficult when part-time employees place orders while stocking shelves, resulting in over-ordering and shortages. This leads to an increase in unsold products, higher disposal costs, and a negative impact on store operations. Furthermore, the workload on employees is heavy, necessitating greater efficiency in operations. [Means for solving the problem]

[0006] The present invention provides a system that performs demand forecasting based on sales data, weather information, and local event information, and automatically determines optimal ordering timing and order quantities. Specifically, the system includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for predicting demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order orders and notifying a user terminal, means for displaying order orders received on the user terminal, means for the user to confirm and modify order information, and means for finalizing order information and sending it to a warehouse or supplier. This aims to improve the efficiency of product inventory management, reduce food waste, and streamline store operations.

[0007] ---

[0008] ---

[0009] "Sales data" refers to information recorded when a product is sold in a store.

[0010] "Weather information" refers to data that indicates weather conditions in a particular area or time.

[0011] "Local event information" refers to schedule information for events, gatherings, etc. held in a specific local area.

[0012] "Integrated data" refers to information that combines and associates multiple different data sets, such as sales data, weather information, and local event information.

[0013] "Preprocessing" refers to the processing performed to prepare data in an analyzable format.

[0014] "Demand forecasting" is the process of predicting future sales volumes for a product based on past data and external information.

[0015] "Order quantity" refers to the quantity of additional products to be ordered based on sales forecasts.

[0016] An "order command" is instruction information for actually replenishing products based on a specified order quantity.

[0017] A "user terminal" is a device such as a computer or tablet used by a store employee.

[0018] "Verification and correction means" refers to a function that allows the user to verify the purchase order and change the purchase order information as necessary.

[0019] "Warehouse or Supplier" means a storage facility or supplier that supplies goods to a store.

[0020] --- [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] ---

[0043] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0044] Server Processing

[0045] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to predict product demand. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[0046] Terminal handling

[0047] The terminal displays the order instructions received from the server on its screen. The user (store employee) checks the order details displayed on the terminal and can make corrections if necessary. For example, if it is determined that demand for tea is higher than expected, the amount to be ordered can be manually increased.

[0048] User operations

[0049] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[0050] Specific examples

[0051] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0052] 1. Server

[0053] Retrieve sales data from the POS system up to August 14th.

[0054] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[0055] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[0056] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[0057] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0058] 2. Terminal

[0059] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[0060] 3. Users

[0061] The user checks the order details displayed on the terminal.

[0062] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[0063] After making corrections, confirm the order information and press the Confirm button.

[0064] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0065] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits.

[0066] ---

[0067] The processing flow will be explained below.

[0068] ---

[0069] Step 1:

[0070] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[0071] Step 2:

[0072] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[0073] Step 3:

[0074] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[0075] Step 4:

[0076] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[0077] Step 5:

[0078] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[0079] Step 6:

[0080] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[0081] Step 7:

[0082] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[0083] Step 8:

[0084] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[0085] Step 9:

[0086] The user checks the order information displayed on the terminal, checks whether the displayed order quantity is appropriate, and takes into account the stock situation to prevent unnecessary ordering mistakes.

[0087] Step 10:

[0088] The user can adjust the order quantity as needed. For example, if it is determined that 500 bottles of 500ml tea is not enough, the user can manually adjust the order quantity to 600 bottles.

[0089] Step 11:

[0090] After the user confirms and modifies the order information, they press the button on the terminal to confirm the order, which finalizes the order information.

[0091] Step 12:

[0092] The terminal sends the finalized order information to the server, which receives the final order information and sends an order instruction to the warehouse or supplier.

[0093] Step 13:

[0094] The server receives confirmation from the warehouse or supplier and notifies the user terminal that the order has been accepted, thereby completing the ordering process.

[0095] ---

[0096] Example 1

[0097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0098] Traditionally, product demand forecasting and ordering in stores relied primarily on experience and intuition, often lacking in accuracy. Furthermore, manually collecting and integrating data from multiple sources required time and effort, making it inefficient. This often led to problems such as inventory shortages and excess inventory, making optimal inventory management and efficient ordering difficult.

[0099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0100] In this invention, the server includes a means for acquiring sales data, a means for acquiring weather information, and a means for acquiring local event information. This enables accurate demand forecasting by automatically collecting and integrating data from multiple data sources and using a generative AI model. Furthermore, the server includes a means for determining optimal order quantities based on the demand forecast results, generating order orders, and notifying the terminal. This allows store employees to efficiently perform ordering tasks, preventing inventory shortages and excess inventory, reducing food waste, and improving store profits. Furthermore, a system is constructed in which users can use their terminals to confirm and modify order information, finalize the order information, and send it to the server, ensuring that the final order details are accurately reflected.

[0101] ---

[0102] ---

[0103] "Sales data" is a record of merchandise sales in a store, and includes information such as sales quantity, sales date and time, and merchandise category.

[0104] "Weather information" is data relating to weather conditions, and is weather forecast data including information such as temperature, precipitation, humidity, and wind speed.

[0105] "Regional event information" is data relating to events held in a specific region, including information such as the date and time of the event, the venue, the content of the event, and the expected number of participants.

[0106] "Integrated data" is data that combines sales data, weather information, and local event information into a single dataset, and these data are linked together and organized into a processable format.

[0107] A "generative AI model" is a model that uses machine learning algorithms to learn patterns from data and predict future demand.

[0108] An "order command" is a command that specifies the order quantity and timing of a specific product based on predicted demand.

[0109] A "user terminal" is a device used by a store employee to receive, display, and modify order instructions.

[0110] "Supply source" refers to the warehouse or supplier responsible for supplying the goods, and is the party to which the goods are delivered upon receipt of an order.

[0111] "Confirmation and modification" refers to the operation in which the user checks the order information displayed on the terminal and changes the contents as necessary.

[0112] "Final order information" refers to the final order details confirmed after confirmation and correction by the user.

[0113] ---

[0114] The above are definitions of important words included in the scope of the patent claims.

[0115] ---

[0116] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0117] Server Processing

[0118] The server first obtains sales data from the POS system. To do this, the server automatically accesses the POS system at a specific time (for example, 1:00 AM every day) and downloads all sales data from the previous day. Next, it obtains weather information using a weather forecast API. In this process, the server sends a request to the weather forecast API at 2:00 AM to obtain real-time weather information. The server also references a local event calendar to obtain information about events in the vicinity of the store. Specifically, the server accesses a website that provides event information at 3:00 AM and scrapes information about nearby events.

[0119] After collecting this data, the server integrates and preprocesses sales data, weather information, and local event information. The integrated data is processed by standardizing different data formats, filtering unnecessary data, and imputing missing values. The preprocessed data is then input into a generative AI model to forecast product demand. The generative AI model uses machine learning algorithms to learn patterns from the data and predict future demand with high accuracy.

[0120] Based on the results of the demand forecast, the server determines the optimal order quantity and generates an order command. The generated order command includes a specific product name and order quantity, such as "500 bottles of 500ml tea" or "300 ice creams." This order command is notified to the terminal.

[0121] Terminal handling

[0122] The terminal displays the ordering instructions received from the server on its screen. Terminals are devices used by store employees, and include tablets and desktop PCs. The terminal receives an ordering instruction from the server at 6:00 AM and displays an order such as "500 bottles of 500ml tea" or "300 ice creams" on its screen.

[0123] User operations

[0124] The user checks the order information displayed on the terminal. Specifically, the user can check each item and its order quantity displayed on the screen and make any necessary corrections. For example, if the user wants to add 50 more ice creams to the predicted order quantity, they can correct it to 350 on the terminal.

[0125] After making the corrections, the user confirms the order information and sends it to the server. When the user presses the "Confirm" button, the corrected order information is sent from the terminal to the server. The server receives the final order information and sends it to the supply source (warehouse or supplier) to complete the order processing.

[0126] Examples and prompts

[0127] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0128] The server retrieves sales data up to August 14th from the POS system, and determines from weather information retrieved from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. By integrating this data and using a generative AI model to perform a demand forecast, it predicts that demand for 500ml tea and ice cream will increase. As a result, an order to order 500 additional 500ml bottles of tea and 300 ice creams is generated and notified to the terminal.

[0129] If the user checks the order on the terminal and corrects the order quantity to 350 ice creams, the final order information is sent to the server by pressing the confirm button. The server sends this information to the supplier and completes the order process.

[0130] Examples of prompts:

[0131] Integrate store sales data, weather information, and local event information to forecast demand at convenience stores in Tokyo on August 15th. Based on the forecast, determine the timing and quantity of orders.

[0132] ---

[0133] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0134] ---

[0135] Step 1: Obtaining sales data

[0136] The server obtains sales data from the POS system.

[0137] Input: The server sends a request to the POS system's API.

[0138] Data processing: The previous day's sales data is sent in response to the request.

[0139] Output: The previous day's sales data is saved in JSON format on the server.

[0140] Specific operation: The server accesses the POS system at 1:00 AM every day and downloads all sales data from the previous day.

[0141] Step 2: Get weather information

[0142] The server retrieves weather information from an online weather forecast API.

[0143] Input: The server sends a request to the weather API.

[0144] Data processing: Analyze the data returned from the weather forecast API and extract the necessary parts.

[0145] Output: The weather information for the day is saved in JSON format on the server.

[0146] Specific operation: The server sends a request to the weather forecast API at 2 AM to obtain real-time weather information.

[0147] Step 3: Get local event information

[0148] The server obtains event information from a local event calendar.

[0149] Input: Server accesses a website for local event information.

[0150] Data processing: Using scraping technology to extract event information from web pages.

[0151] Output: Event information is saved to the server in text format.

[0152] What it does: The server scrapes a website that provides event information at 3 AM.

[0153] Step 4: Data integration and preprocessing

[0154] The server integrates the acquired sales data, weather information, and local event information and performs preprocessing.

[0155] Inputs: Sales data, weather information, and event information datasets.

[0156] Data processing: Standardize data formats, filter unnecessary data, and fill in missing values.

[0157] Output: Preprocessed integrated data is generated.

[0158] Specific operation: The server performs the process of unifying different data formats into a single dataset.

[0159] Step 5: Demand forecast

[0160] The server inputs the preprocessed data into a generative AI model to predict product demand.

[0161] Input: Preprocessed integrated data.

[0162] Data Computing: Use generative AI models to forecast demand.

[0163] Output: Demand forecast results, demand quantity for each product.

[0164] Specific operation: The server inputs data into the generated AI model, and the AI ​​outputs the demand forecast results.

[0165] Step 6: Determine order quantity and generate order instructions

[0166] The server determines the optimal order quantity based on the demand forecast results and generates an order instruction.

[0167] Input: Demand forecast results.

[0168] Data calculation: Calculate the order quantity based on the forecast results.

[0169] Output: A purchase order is generated, containing the specific product name and quantity to order.

[0170] Specific operation: The server analyzes the AI's demand forecast results and automatically generates ordering instructions such as "500ml tea: 500 bottles" and "Ice cream: 300 pieces."

[0171] Step 7: View Purchase Orders

[0172] The terminal displays the order instruction received from the server on the screen.

[0173] Input: The purchase order sent by the server.

[0174] Data processing: Converting order orders into a format that is easy to view on the screen.

[0175] Output: The order details are displayed on the display screen.

[0176] Specific operation: The terminal receives an order command from the server at 6:00 a.m. and displays "500ml tea: 500 bottles" and "300 ice creams" on the screen.

[0177] Step 8: Review and correct your order

[0178] The user checks the order information displayed on the terminal and makes corrections as necessary.

[0179] Input: Purchase order displayed on the terminal.

[0180] Data manipulation: The order quantity is modified based on the user's input.

[0181] Output: The modified purchase order.

[0182] Specific operation: The user checks the order details displayed on the screen and corrects the order quantity to, for example, 350 ice creams.

[0183] Step 9: Confirm and submit your order

[0184] The user confirms the corrected order information and transmits it from the terminal to the server.

[0185] Input: Revised purchase order information.

[0186] Data calculation: The order information is finalized.

[0187] Output: The final order information is sent to the server.

[0188] Specific operation: The user presses the "Confirm" button, and the revised order details are sent from the terminal to the server.

[0189] Step 10: Complete the final order process

[0190] The server receives the final order information and transmits it to the source to complete the order process.

[0191] Input: Final order information.

[0192] Data Calculation: Sends final order information to the source system.

[0193] Output: An order is sent to the source of supply.

[0194] Specific operation: The server automatically sends the revised order information to the warehouse management system and arranges for inventory.

[0195] ---

[0196] The above is a description of the specific flow of processing of the system program and the specific operation at each processing step.

[0197] (Application example 1)

[0198] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0199] Determining the appropriate product order quantity for a store requires consideration of multiple factors, including sales data, weather information, and information about local events, making it difficult to predict. In particular, employees often rely on their own experience and intuition, resulting in ordering errors and excessive or insufficient inventory. Furthermore, it is difficult to respond appropriately when sudden fluctuations in demand or unexpected events occur. This can lead to inefficient inventory management, increased food waste, and reduced profits.

[0200] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0201] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for using a generative AI model to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order orders and notifying a user terminal, means for displaying the order orders received on the user terminal, means for the user to confirm and modify order information using prompt text, and means for finalizing order information and sending it to a warehouse or supplier. This improves the accuracy of demand forecasts and enables the determination of appropriate order quantities. Furthermore, users can easily confirm and modify order information using prompt text, enabling quick and accurate ordering.

[0202] "Sales data" refers to data including the quantity of merchandise sold at a store, sales figures by category, and sales trends by date and time.

[0203] "Weather information" refers to meteorological data such as the weather forecast, temperature, precipitation, wind speed, and humidity for a specified area.

[0204] "Regional event information" is information about events such as festivals, sporting events, and exhibitions held in a specified region.

[0205] "Integrated data" is data that combines multiple datasets, such as sales data, weather information, and local event information, into a format that can be processed as a single dataset.

[0206] A "generative AI model" is an artificial intelligence algorithm that is trained to perform a specific task, such as demand forecasting, from a large dataset.

[0207] "Demand forecast result" is a forecast value of future demand calculated by the generative AI model.

[0208] "Order quantity" refers to the amount of each product to be purchased that is determined based on the demand forecast results.

[0209] An "order instruction" is an instruction document that specifies a specific product name and quantity, and is generated based on the determined order amount.

[0210] "User terminal" means an electronic device used by a store employee to receive, display, and modify order instructions.

[0211] "Prompt text" refers to guidelines or instructions that users use when checking or correcting order information.

[0212] "Final order information" refers to the final product order information that has been confirmed after the user has confirmed and corrected it.

[0213] "Warehouse or supplier" refers to the logistics facility or product supplier to which order information is sent.

[0214] This invention is a demand forecasting and optimal ordering system for stores, specifically a system that uses sales data, weather information, and local event information to forecast demand and determine order quantities, thereby improving the efficiency of store inventory management and reducing food waste.

[0215] Server Processing

[0216] The server first obtains sales data from the store's POS system. Next, it obtains weather information online using a weather forecast API, and also collects event information from a local event calendar. Statistical methods and data cleaning techniques are used to integrate and preprocess this data. The server uses a generative AI model based on this integrated data to predict product demand. The optimal order quantity is determined based on the demand forecast results, and an order order is generated.

[0217] Terminal handling

[0218] The terminal displays the order instruction received from the server on the screen. The user, who is a store employee, confirms the order details displayed on the terminal. Prompt statements are used to allow the user to confirm the order information in an easy-to-understand manner. For example, specific items and quantities such as "500ml of tea: 500 bottles" are displayed. If necessary, the user can modify the order quantity. The modified details are quickly recalculated, and the final order information is generated when the user presses the confirm button.

[0219] User operations

[0220] The user checks and modifies the order information displayed on the terminal and finally confirms the order. The confirmed order information is sent back to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0221] Hardware and software used

[0222] Hardware: Servers, user devices (tablets and smartphones)

[0223] Software: Weather forecast API, data cleaning software, generative AI models (e.g., Keras)

[0224] Specific examples

[0225] For example, consider a case study at a convenience store in Tokyo on August 15th. The server retrieves sales data up to August 14th from the POS system, and determines from weather information obtained from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. This integrated data is input into an AI model, which predicts an increase in demand for 500ml tea and ice cream. As a result, it generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0226] Prompt Sentence Examples

[0227] Below is an example of an actual prompt sentence.

[0228] 1. Weather information prompts:

[0229] Please enter the weather information for this weekend. Example: Sunny, temperature 30°C

[0230] 2. Event information related prompts:

[0231] Enter local event information. Example: Summer festival, 1000 people

[0232] 3. Sales data related prompts:

[0233] Please enter the sales data for the most recent week in CSV format.

[0234] This reduces the workload of employees while enabling accurate demand forecasting and efficient inventory management, reducing food waste and improving store profits.

[0235] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0236] Step 1:

[0237] The server retrieves sales data from the store's POS system. Specifically, it connects to the database and uses a query to extract sales data from the past few days. This allows data to be obtained that can be used to understand the sales trends of products in the store.

[0238] Input: Sales data from POS system

[0239] Output: Extracted sales dataset

[0240] Step 2:

[0241] The server retrieves weather information from a weather forecast API, which includes meteorological data such as weather, temperature, and precipitation for a specific region. It sends a request to the API endpoint and analyzes the data received in response. This allows it to obtain weather information that affects product demand.

[0242] Input: Weather forecast API request information (location, date and time, etc.)

[0243] Output: Obtained weather information data

[0244] Step 3:

[0245] The server collects event information from the local event calendar and stores it in a database, allowing it to consider the impact of local events on product demand.

[0246] Input: Events calendar URL or API endpoint

[0247] Output: Captured event information data

[0248] Step 4:

[0249] The server integrates sales data, weather information, and event information, performs preprocessing, cleans the data, and converts it into a format suitable for AI models by properly handling missing values ​​and outliers.

[0250] Input: Sales dataset, weather information data, event information data

[0251] Output: Unified dataset

[0252] Step 5:

[0253] The server then inputs the integrated data into a generative AI model that is pre-trained and uses statistical methods and machine learning algorithms to forecast product demand.

[0254] Input: Unified dataset

[0255] Output: Demand forecast result data

[0256] Step 6:

[0257] The server determines the optimal order quantity based on the demand forecast results, and uses a decision algorithm to calculate the order quantity of the product according to the forecasted demand.

[0258] Input: Demand forecast result data

[0259] Output: Order quantity determination data

[0260] Step 7:

[0261] The server generates an order instruction and notifies the user terminal of the order instruction, which includes the specific product name and quantity.

[0262] Input: Order quantity determination data

[0263] Output: Purchase order data

[0264] Step 8:

[0265] The terminal displays the order command received from the server on its screen, and the order information is displayed in a format that is easy for the user to understand.

[0266] Input: Purchase order data

[0267] Output: Order information displayed on the user's terminal

[0268] Step 9:

[0269] The user checks the order information displayed on the terminal and makes any necessary corrections. Prompts are displayed to assist the user in making corrections. For example, it is possible to change a 500ml order of tea from 400 bottles to 500 bottles.

[0270] Input: User modifications

[0271] Output: Corrected order information

[0272] Step 10:

[0273] The user finally confirms the revised order information by pressing the Confirm button, which sends the final order information to the server.

[0274] Enter: Confirmed order information

[0275] Output: Sends the final order information to the server

[0276] Step 11:

[0277] The server sends the final confirmed order information to the warehouse or supplier to complete the order processing.

[0278] Input: Final Order Information

[0279] Output: Send purchase order information to warehouse or supplier

[0280] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0281] ---

[0282] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information at stores such as convenience stores, and automatically determines the optimal ordering timing and order quantity, thereby improving ordering accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[0283] Server Processing

[0284] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to perform product demand forecasting. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[0285] Terminal handling

[0286] The terminal displays the order instructions received from the server on its screen. The user (store employee) can check the order details displayed on the terminal and make any necessary corrections. In addition, the emotion engine collects the user's emotional data and evaluates the user's stress level and emotional state. This information is also sent to the server as part of the demand forecast.

[0287] User operations

[0288] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. For example, if it is determined that the demand for tea is higher than expected, the order quantity can be increased manually. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[0289] Emotion engine processing

[0290] The emotion engine collects emotional data in real time when users confirm or modify order information. This emotional data is extracted from the user's facial expressions, voice, operation speed, etc. The emotion engine uses the collected data to evaluate the user's stress level and emotional state, and sends the evaluation results to the server. The server incorporates this emotional data into the demand forecasting model to improve the accuracy of the forecast.

[0291] Specific examples

[0292] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0293] 1. Server

[0294] Retrieve sales data from the POS system up to August 14th.

[0295] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[0296] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[0297] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[0298] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0299] 2. Terminal

[0300] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[0301] The emotion engine analyzes the user's facial expressions, voice, etc. in real time to assess their stress level and emotional state.

[0302] 3. Users

[0303] The user checks the order details displayed on the terminal.

[0304] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[0305] After correction, the emotion engine records the user's reaction and sends it to the server.

[0306] Confirm the order information and press the Confirm button.

[0307] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0308] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits. In addition, by utilizing user emotion data, further improvements in ordering accuracy can be expected.

[0309] ---

[0310] The processing flow will be explained below.

[0311] ---

[0312] Step 1:

[0313] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[0314] Step 2:

[0315] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[0316] Step 3:

[0317] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[0318] Step 4:

[0319] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[0320] Step 5:

[0321] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[0322] Step 6:

[0323] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[0324] Step 7:

[0325] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[0326] Step 8:

[0327] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[0328] Step 9:

[0329] The user checks the order information displayed on the terminal, and the emotion engine analyzes the user's facial expressions, voice, and operation speed in real time to collect emotional data.

[0330] Step 10:

[0331] Check whether the order quantity confirmed by the user is appropriate and make corrections if necessary. For example, if it is determined that an order of 500 bottles of 500ml tea is insufficient, manually correct it to 600 bottles.

[0332] Step 11:

[0333] The user confirms the order information, and the emotion engine evaluates the user's stress level and emotional state and sends the data to the server.

[0334] Step 12:

[0335] The server sends an order instruction to the warehouse or supplier based on the final order information including the emotion data.

[0336] Step 13:

[0337] Once confirmation is sent from the warehouse or supplier, the server receives it and notifies the user terminal, thereby completing the order process.

[0338] ---

[0339] Example 2

[0340] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] Conventional demand forecasting systems make predictions based on sales data, weather information, and local event information, but because they do not take into account non-numerical factors such as users' emotions and stress levels, they have problems with low demand forecast accuracy and inefficient inventory management and ordering.In addition, because they ignore users' stress and emotions when adjusting order quantities, they place a heavy burden on the work and a high risk of incorrect ordering.

[0342] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for predicting demand from the integrated data, means for determining the order quantity based on the demand forecast result, means for generating an order instruction and notifying the terminal, means for displaying the order instruction received by the terminal, means for the user to confirm and correct the order information, means for collecting and evaluating user emotion data, means for reflecting the evaluation result in the demand forecast, and means for finalizing the order information and sending it to the warehouse or supplier. This enables highly accurate demand forecasting that takes user emotion data into account and efficient order management.

[0343] "Sales data" is data obtained from a sales system that indicates the sales performance of a product during a specific period.

[0344] "Weather information" is information about a specific region and time period, including weather conditions such as temperature, chance of precipitation, and wind speed.

[0345] "Regional event information" is information about the date, time, location, and content of an event held in a specific region.

[0346] "Integrated data" is centralized data that combines sales data, weather information, and local event information.

[0347] "Preprocessing" refers to processing performed on acquired data, such as filling in missing values, removing outliers, and normalizing the data.

[0348] "Demand forecasting" refers to the use of integrated data to predict future demand for a product.

[0349] The "order quantity" is the quantity of the product to be purchased, determined based on the demand forecast.

[0350] An "order command" is a command indicating the determined order quantity, and is notified to the terminal.

[0351] A "terminal" is an electronic device that receives order orders and displays information to a user.

[0352] "User" refers to a person, such as a store employee, who operates the system and checks and modifies order information.

[0353] "Emotion data" is data that indicates the user's emotional state, extracted from the user's facial expression, tone of voice, operation speed, and the like.

[0354] The "evaluation result" is an evaluation index of the user's stress level and emotional state derived from the emotion data.

[0355] A "warehouse" is a facility where product inventory is stored.

[0356] "Supplier" refers to the supplier or manufacturer that provides the goods.

[0357] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines optimal order quantities and timing, improving prediction accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[0358] The server obtains sales data from the POS system. To do this, for example, the sales data collection device requests sales data for a specific period using API communication and receives it in JSON format. As a specific example, a request to the POS system is made as follows: GET / sales?start_date=2023-08-01&end_date=2023-08-14.

[0359] Next, the server retrieves weather information using a weather forecast API. For example, the API request uses the format GET / weather?location=tokyo&date=2023-08-15. The retrieved weather information includes data such as temperature, probability of precipitation, and wind speed.

[0360] The server then uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The response includes the event name, location, start time, and end time.

[0361] The acquired sales data, weather information, and local event information are centralized and treated as integrated data. This integrated data is then preprocessed. Preprocessing includes filling in missing values, removing outliers, and normalizing the data. This improves the quality of the data.

[0362] The server inputs the preprocessed integrated data into a generative AI model, such as Google Cloud's "AI Platform Prediction." The generative AI model performs demand forecasting based on a prompt, such as, "Please predict tomorrow's product demand based on today's sales data, weather information, and local event information. Please provide detailed information on demand for 500ml of tea and ice cream."

[0363] Based on the demand forecast results, the server determines the optimal order quantity. For example, it generates an order to order 500 bottles of 500ml tea and 300 ice creams. The order is notified to the terminal.

[0364] The terminal displays the ordering instructions received from the server on its screen. Specifically, for example, information such as "500 bottles of 500ml tea" and "300 ice creams" is displayed to the user on a tablet. The user can check this information and modify it as necessary.

[0365] The device is equipped with an emotion engine that uses Microsoft's Azure Emotion API to collect user emotion data, which is extracted from the user's facial expressions, tone of voice, and operation speed, and analyzed in real time.

[0366] The user checks the order information displayed on the terminal and modifies the order quantity if necessary. For example, the user can change the predicted order quantity of ice cream to 350. The emotion engine records the modifications made by the user and their emotional state at the time, and sends them to the server.

[0367] Finally, once the user has finalized the order information, it is sent to the server, which then sends it to the warehouse or supplier to complete the order process.

[0368] This will enable highly accurate demand forecasting and efficient order management that takes into account user emotional data. Utilizing emotional data will also reduce user stress and significantly reduce the risk of incorrect orders.

[0369] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0370] Step 1:

[0371] The server obtains sales data from the POS system. Specifically, it requests sales data for a specific period via API communication and receives it in JSON format. For example, a request is made in the format GET / sales?start_date=2023-08-01&end_date=2023-08-14. The input is an API request with a specified period, and the output is sales data for the specified period. Data processing includes normalization and missing value completion.

[0372] Step 2:

[0373] The server obtains weather information using the weather forecast API. Using the API key, it makes a request in the format GET / weather?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is weather information such as temperature, precipitation probability, and wind speed. The server converts this data into the required format and performs preprocessing.

[0374] Step 3:

[0375] The server uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is event information such as the event name, location, start time, and end time. The server organizes and preprocesses the acquired event information.

[0376] Step 4:

[0377] The server integrates sales data, weather information, and local event information to generate a unified dataset. The input is the various data that has been acquired and preprocessed up to that point, and the output is the integrated data. Data processing includes filling in missing values, removing outliers, and normalizing the data. For example, data frames are manipulated using the Python Pandas library.

[0378] Step 5:

[0379] The server inputs the integrated data into a generative AI model (for example, Google Cloud's "AI Platform Prediction") and performs demand forecasting. The input is the integrated dataset, and the output is a supply and demand forecast for each product. The prompt used is, "Based on today's sales data, weather information, and local event information, please predict tomorrow's product demand. Please tell me in detail the demand for 500ml of tea and ice cream in particular."

[0380] Step 6:

[0381] The server determines the optimal order quantity based on the results of the demand forecast. The input is the demand forecast result, and the output is an order command. For example, it generates a command to order 500 bottles of 500ml tea and 300 ice creams. The server converts this command data into JSON format and notifies the terminal.

[0382] Step 7:

[0383] The terminal displays the ordering command received from the server on its screen. The input is the ordering command sent from the server, and the output is the ordering information displayed on the terminal screen. For example, "500ml tea: 500 bottles" and "300 ice creams" are displayed on the tablet.

[0384] Step 8:

[0385] The user checks the order information displayed on the terminal and modifies it as necessary. The input is the order information displayed on the screen, and the output is the order information modified by the user. For example, the user can modify the order quantity to 350 ice creams.

[0386] Step 9:

[0387] The device uses an emotion engine (for example, Microsoft's "Azure Emotion API") to collect and evaluate the user's emotional data. The input is the user's facial expression, tone of voice, operation speed, etc., and the output is an evaluation of the user's stress level and emotional state. The evaluation results are sent from the device to a server.

[0388] Step 10:

[0389] The server reflects the user's emotional data and the revised order information in the demand forecasting model and performs a new forecast. The input is the user's emotional data and the revised order information, and the output is the revised demand forecast result. This allows the final order quantity to be reevaluated.

[0390] Step 11:

[0391] The user finally confirms the order information and presses the "Confirm" button on the terminal. The input is the confirmation instruction by the user's operation, and the output is the confirmed order information.

[0392] Step 12:

[0393] The server then sends the confirmed order information to the warehouse or supplier to complete the order processing. The input is the confirmed order information, and the output is the status of delivery preparation or supply instruction. This ensures the smooth running of the product supply chain.

[0394] (Application example 2)

[0395] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0396] Conventional product demand forecasting and order management systems for convenience stores and other retailers use sales data, weather information, local event information, and other data to perform automated demand forecasting. However, these systems still sometimes result in incorrect orders, which impacts the work environment and mental stress of users (store employees). Furthermore, the process of checking and correcting demand forecast results is cumbersome, requiring more efficient work. Furthermore, there is a lack of means to visually check order information in real time using wearable devices. The problem that this invention aims to solve is to provide a system that solves these problems and allows users to intuitively and efficiently perform demand forecasting and order management.

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

[0398] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, and means for acquiring local event information. This allows the server to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order instructions and notifying a user terminal, means for displaying the order instructions received on the user terminal, means for the user to confirm and modify order information, means for finalizing order information and sending it to a warehouse or supplier, means for collecting emotional data and evaluating the emotional state, means for incorporating the emotional data into demand forecasting to improve order accuracy, and means for using a wearable device for the user to visually check order information displayed in real time. This allows the user to intuitively and efficiently perform demand forecasting and order management, improve order accuracy, reduce the user's workload, and improve the work environment.

[0399] "Sales data" is data that records the sales performance of each product in a store.

[0400] "Weather information" is data related to weather conditions and is information used to predict demand for stores.

[0401] "Regional event information" is data related to events held in the target region.

[0402] "Integrated data" refers to data that integrates sales data, weather information, and local event information.

[0403] "Demand forecasting" refers to predicting future demand for a product based on integrated data.

[0404] An "order command" is a command that specifies the order quantity determined based on the demand forecast results.

[0405] A "user terminal" is a device operated by a user, which displays order instructions and allows modification and confirmation of orders.

[0406] "Emotion data" refers to data relating to the emotional state of a user extracted from facial expressions, voice, and the like.

[0407] "Emotional state" is an evaluation that indicates the user's emotional state, and includes stress level, satisfaction level, and the like.

[0408] A "wearable device" is a device worn by a user, such as smart glasses.

[0409] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines the optimal order timing and order quantity. This system allows users to intuitively and efficiently perform demand forecasting and order management. It also uses a wearable device that allows users to visually check order information displayed in real time.

[0410] Program Generation

[0411] The server is configured as follows:

[0412] 1. The means of obtaining sales data is connected to a POS system, which has the function of automatically collecting daily sales data.

[0413] 2. To obtain weather information, use an online weather forecast API (e.g., OpenWeatherMap API) to obtain the necessary weather information.

[0414] 3. To obtain local event information, use a local event calendar API (e.g., Google Calendar API) to collect information on events occurring in the area.

[0415] The means for integrating and preprocessing this data is integrated with a database system to clean the data and standardize the format. The means for predicting demand from the integrated data is to use a generative AI model using TensorFlow or PyTorch to perform demand forecasting. The means for determining order quantities based on the demand forecast results is an algorithm that calculates the optimal order quantity from the prediction results of the AI ​​model.

[0416] The means of collecting emotional data and evaluating emotional states are to use sensors built into smart glasses and wearable devices, as well as the Affectiva SDK and Microsoft Azure's Emotion API, to collect and evaluate emotional data from the user's facial expressions and voice in real time. By incorporating the results of this evaluation into demand forecasts, the accuracy of ordering can be improved.

[0417] The system notifies the user terminal of the order order and allows the user to confirm and modify it by displaying the order information in real time on the display of smart glasses (e.g., HoloLens or Google Glass). The user can confirm the displayed order details and modify them as necessary. The final order information is automatically sent to the server and transmitted to the warehouse or supplier.

[0418] Specific examples

[0419] For example, a demand forecast is made for a store in an urban area on August 15th based on sales data, weather information, and local event information. Based on sales data obtained from the POS system, high temperature forecasts obtained from a weather forecast API, and information about local summer festivals, it is predicted that demand for 500ml of tea and ice cream will increase. The generative AI model generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0420] Users wear smart glasses and check order information in real time. The emotion engine detects the user's stress level from their facial expressions and can automatically adjust the order quantity if the stress level is high. If the user wants to manually increase the order quantity, they can make the adjustment through the smart glasses and the information is sent back to the server.

[0421] Prompt Sentence Examples

[0422] "Use the smart glasses to check the order quantity for 500ml of tea and manually adjust it based on demand forecast and emotion data. The emotion engine will detect stress levels from facial expressions and optimize the ordering process as needed."

[0423] This improves ordering accuracy, reduces the user's workload, and enables efficient inventory management. Utilizing user emotion data also enables more detailed demand forecasts, contributing to increased store profits.

[0424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0425] Step 1:

[0426] The server retrieves sales data from the POS system. This sales data includes sales records for each product and is used as information necessary for the next demand forecast. Specifically, the most recent sales data is extracted from the database using a query.

[0427] Step 2:

[0428] The server retrieves weather information from an online weather forecast API (e.g., OpenWeatherMap API). The retrieved information includes temperature, probability of precipitation, humidity, etc., and combines this information with sales data to input into the next forecast model. The weather data retrieved from the API is parsed in JSON format, and the necessary information is extracted.

[0429] Step 3:

[0430] The server retrieves local event information from a local event calendar API (e.g., Google Calendar API). It collects information such as the event type, date, time, and location, and combines this with sales data and weather information. The event information is also retrieved in JSON format, and the necessary data is extracted by parsing it.

[0431] Step 4:

[0432] The server combines sales data, weather information, and local event information, and performs preprocessing. It normalizes the data, removes outliers, and standardizes formats to create a combined dataset that is ready to be input into the AI ​​model.

[0433] Step 5:

[0434] The server inputs the integrated data into a generative AI model (using, for example, TensorFlow or PyTorch) to perform demand forecasting. The AI ​​model predicts product demand from the integrated data and outputs the results. Specifically, a regression analysis is performed using a neural network, and the predicted sales volume for each product is output.

[0435] Step 6:

[0436] The server determines the optimal order quantity based on the demand forecast results. This order quantity is calculated taking into account forecast sales volume and inventory information, and is generated as an order instruction. The algorithm adjusts the order quantity so that the optimal inventory level is maintained.

[0437] Step 7:

[0438] The server notifies the user terminal of the generated order command. The order command includes the product type, order quantity, delivery date, etc., and is sent to the user terminal. The notification is sent in real time via a cloud service.

[0439] Step 8:

[0440] The user terminal displays the order instruction received from the server. The order information is displayed on the display of the smart glasses or wearable device, and the user confirms it. The UI is designed to display the order details in a format that is easy to visually confirm.

[0441] Step 9:

[0442] The user can check the order information displayed on the device and make any necessary changes. If necessary, the user can change the order quantity through the smart glasses interface. During this process, the emotion engine analyzes the user's facial expressions and voice to collect emotional data such as stress level.

[0443] Step 10:

[0444] The user terminal sends the final confirmed order information to the server, which then forwards the received confirmed order information to the warehouse or supplier and completes the actual order processing. This ensures that the appropriate quantity of products is ordered at the appropriate time.

[0445] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0446] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0447] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0448] [Second embodiment]

[0449] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0450] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0451] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0452] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0453] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0454] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0455] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0456] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0457] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0458] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0459] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0460] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0461] ---

[0462] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0463] Server Processing

[0464] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to predict product demand. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[0465] Terminal handling

[0466] The terminal displays the order instructions received from the server on its screen. The user (store employee) checks the order details displayed on the terminal and can make corrections if necessary. For example, if it is determined that demand for tea is higher than expected, the amount to be ordered can be manually increased.

[0467] User operations

[0468] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[0469] Specific examples

[0470] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0471] 1. Server

[0472] Retrieve sales data from the POS system up to August 14th.

[0473] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[0474] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[0475] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[0476] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0477] 2. Terminal

[0478] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[0479] 3. Users

[0480] The user checks the order details displayed on the terminal.

[0481] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[0482] After making corrections, confirm the order information and press the Confirm button.

[0483] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0484] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits.

[0485] ---

[0486] The processing flow will be explained below.

[0487] ---

[0488] Step 1:

[0489] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[0490] Step 2:

[0491] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[0492] Step 3:

[0493] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[0494] Step 4:

[0495] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[0496] Step 5:

[0497] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[0498] Step 6:

[0499] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[0500] Step 7:

[0501] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[0502] Step 8:

[0503] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[0504] Step 9:

[0505] The user checks the order information displayed on the terminal, checks whether the displayed order quantity is appropriate, and takes into account the stock situation to prevent unnecessary ordering mistakes.

[0506] Step 10:

[0507] The user can adjust the order quantity as needed. For example, if it is determined that 500 bottles of 500ml tea is not enough, the user can manually adjust the order quantity to 600 bottles.

[0508] Step 11:

[0509] After the user confirms and modifies the order information, they press the button on the terminal to confirm the order, which finalizes the order information.

[0510] Step 12:

[0511] The terminal sends the finalized order information to the server, which receives the final order information and sends an order instruction to the warehouse or supplier.

[0512] Step 13:

[0513] The server receives confirmation from the warehouse or supplier and notifies the user terminal that the order has been accepted, thereby completing the ordering process.

[0514] ---

[0515] Example 1

[0516] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0517] Traditionally, product demand forecasting and ordering in stores relied primarily on experience and intuition, often lacking in accuracy. Furthermore, manually collecting and integrating data from multiple sources required time and effort, making it inefficient. This often led to problems such as inventory shortages and excess inventory, making optimal inventory management and efficient ordering difficult.

[0518] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0519] In this invention, the server includes a means for acquiring sales data, a means for acquiring weather information, and a means for acquiring local event information. This enables accurate demand forecasting by automatically collecting and integrating data from multiple data sources and using a generative AI model. Furthermore, the server includes a means for determining optimal order quantities based on the demand forecast results, generating order orders, and notifying the terminal. This allows store employees to efficiently perform ordering tasks, preventing inventory shortages and excess inventory, reducing food waste, and improving store profits. Furthermore, a system is constructed in which users can use their terminals to confirm and modify order information, finalize the order information, and send it to the server, ensuring that the final order details are accurately reflected.

[0520] ---

[0521] ---

[0522] "Sales data" is a record of merchandise sales in a store, and includes information such as sales quantity, sales date and time, and merchandise category.

[0523] "Weather information" is data relating to weather conditions, and is weather forecast data including information such as temperature, precipitation, humidity, and wind speed.

[0524] "Regional event information" is data relating to events held in a specific region, including information such as the date and time of the event, the venue, the content of the event, and the expected number of participants.

[0525] "Integrated data" is data that combines sales data, weather information, and local event information into a single dataset, and these data are linked together and organized into a processable format.

[0526] A "generative AI model" is a model that uses machine learning algorithms to learn patterns from data and predict future demand.

[0527] An "order command" is a command that specifies the order quantity and timing of a specific product based on predicted demand.

[0528] A "user terminal" is a device used by a store employee to receive, display, and modify order instructions.

[0529] "Supply source" refers to the warehouse or supplier responsible for supplying the goods, and is the party to which the goods are delivered upon receipt of an order.

[0530] "Confirmation and modification" refers to the operation in which the user checks the order information displayed on the terminal and changes the contents as necessary.

[0531] "Final order information" refers to the final order details confirmed after confirmation and correction by the user.

[0532] ---

[0533] The above are definitions of important words included in the scope of the patent claims.

[0534] ---

[0535] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0536] Server Processing

[0537] The server first obtains sales data from the POS system. To do this, the server automatically accesses the POS system at a specific time (for example, 1:00 AM every day) and downloads all sales data from the previous day. Next, it obtains weather information using a weather forecast API. In this process, the server sends a request to the weather forecast API at 2:00 AM to obtain real-time weather information. The server also references a local event calendar to obtain information about events in the vicinity of the store. Specifically, the server accesses a website that provides event information at 3:00 AM and scrapes information about nearby events.

[0538] After collecting this data, the server integrates and preprocesses sales data, weather information, and local event information. The integrated data is processed by standardizing different data formats, filtering unnecessary data, and imputing missing values. The preprocessed data is then input into a generative AI model to forecast product demand. The generative AI model uses machine learning algorithms to learn patterns from the data and predict future demand with high accuracy.

[0539] Based on the results of the demand forecast, the server determines the optimal order quantity and generates an order command. The generated order command includes a specific product name and order quantity, such as "500 bottles of 500ml tea" or "300 ice creams." This order command is notified to the terminal.

[0540] Terminal handling

[0541] The terminal displays the ordering instructions received from the server on its screen. Terminals are devices used by store employees, and include tablets and desktop PCs. The terminal receives an ordering instruction from the server at 6:00 AM and displays an order such as "500 bottles of 500ml tea" or "300 ice creams" on its screen.

[0542] User operations

[0543] The user checks the order information displayed on the terminal. Specifically, the user can check each item and its order quantity displayed on the screen and make any necessary corrections. For example, if the user wants to add 50 more ice creams to the predicted order quantity, they can correct it to 350 on the terminal.

[0544] After making the corrections, the user confirms the order information and sends it to the server. When the user presses the "Confirm" button, the corrected order information is sent from the terminal to the server. The server receives the final order information and sends it to the supply source (warehouse or supplier) to complete the order processing.

[0545] Examples and prompts

[0546] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0547] The server retrieves sales data up to August 14th from the POS system, and determines from weather information retrieved from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. By integrating this data and using a generative AI model to perform a demand forecast, it predicts that demand for 500ml tea and ice cream will increase. As a result, an order to order 500 additional 500ml bottles of tea and 300 ice creams is generated and notified to the terminal.

[0548] If the user checks the order on the terminal and corrects the order quantity to 350 ice creams, the final order information is sent to the server by pressing the confirm button. The server sends this information to the supplier and completes the order process.

[0549] Examples of prompts:

[0550] Integrate store sales data, weather information, and local event information to forecast demand at convenience stores in Tokyo on August 15th. Based on the forecast, determine the timing and quantity of orders.

[0551] ---

[0552] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0553] ---

[0554] Step 1: Obtaining sales data

[0555] The server obtains sales data from the POS system.

[0556] Input: The server sends a request to the POS system's API.

[0557] Data processing: The previous day's sales data is sent in response to the request.

[0558] Output: The previous day's sales data is saved in JSON format on the server.

[0559] Specific operation: The server accesses the POS system at 1:00 AM every day and downloads all sales data from the previous day.

[0560] Step 2: Get weather information

[0561] The server retrieves weather information from an online weather forecast API.

[0562] Input: The server sends a request to the weather API.

[0563] Data processing: Analyze the data returned from the weather forecast API and extract the necessary parts.

[0564] Output: The weather information for the day is saved in JSON format on the server.

[0565] Specific operation: The server sends a request to the weather forecast API at 2 AM to obtain real-time weather information.

[0566] Step 3: Get local event information

[0567] The server obtains event information from a local event calendar.

[0568] Input: Server accesses a website for local event information.

[0569] Data processing: Using scraping technology to extract event information from web pages.

[0570] Output: Event information is saved to the server in text format.

[0571] What it does: The server scrapes a website that provides event information at 3 AM.

[0572] Step 4: Data integration and preprocessing

[0573] The server integrates the acquired sales data, weather information, and local event information and performs preprocessing.

[0574] Inputs: Sales data, weather information, and event information datasets.

[0575] Data processing: Standardize data formats, filter unnecessary data, and fill in missing values.

[0576] Output: Preprocessed integrated data is generated.

[0577] Specific operation: The server performs the process of unifying different data formats into a single dataset.

[0578] Step 5: Demand forecast

[0579] The server inputs the preprocessed data into a generative AI model to predict product demand.

[0580] Input: Preprocessed integrated data.

[0581] Data Computing: Use generative AI models to forecast demand.

[0582] Output: Demand forecast results, demand quantity for each product.

[0583] Specific operation: The server inputs data into the generated AI model, and the AI ​​outputs the demand forecast results.

[0584] Step 6: Determine order quantity and generate order instructions

[0585] The server determines the optimal order quantity based on the demand forecast results and generates an order instruction.

[0586] Input: Demand forecast results.

[0587] Data calculation: Calculate the order quantity based on the forecast results.

[0588] Output: A purchase order is generated, containing the specific product name and quantity to order.

[0589] Specific operation: The server analyzes the AI's demand forecast results and automatically generates ordering instructions such as "500ml tea: 500 bottles" and "Ice cream: 300 pieces."

[0590] Step 7: View Purchase Orders

[0591] The terminal displays the order instruction received from the server on the screen.

[0592] Input: The purchase order sent by the server.

[0593] Data processing: Converting order orders into a format that is easy to view on the screen.

[0594] Output: The order details are displayed on the display screen.

[0595] Specific operation: The terminal receives an order command from the server at 6:00 a.m. and displays "500ml tea: 500 bottles" and "300 ice creams" on the screen.

[0596] Step 8: Review and correct your order

[0597] The user checks the order information displayed on the terminal and makes corrections as necessary.

[0598] Input: Purchase order displayed on the terminal.

[0599] Data manipulation: The order quantity is modified based on the user's input.

[0600] Output: The modified purchase order.

[0601] Specific operation: The user checks the order details displayed on the screen and corrects the order quantity to, for example, 350 ice creams.

[0602] Step 9: Confirm and submit your order

[0603] The user confirms the corrected order information and transmits it from the terminal to the server.

[0604] Input: Revised purchase order information.

[0605] Data calculation: The order information is finalized.

[0606] Output: The final order information is sent to the server.

[0607] Specific operation: The user presses the "Confirm" button, and the revised order details are sent from the terminal to the server.

[0608] Step 10: Complete the final order process

[0609] The server receives the final order information and transmits it to the source to complete the order process.

[0610] Input: Final order information.

[0611] Data Calculation: Sends final order information to the source system.

[0612] Output: An order is sent to the source of supply.

[0613] Specific operation: The server automatically sends the revised order information to the warehouse management system and arranges for inventory.

[0614] ---

[0615] The above is a description of the specific flow of processing of the system program and the specific operation at each processing step.

[0616] (Application example 1)

[0617] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0618] Determining the appropriate product order quantity for a store requires consideration of multiple factors, including sales data, weather information, and information about local events, making it difficult to predict. In particular, employees often rely on their own experience and intuition, resulting in ordering errors and excessive or insufficient inventory. Furthermore, it is difficult to respond appropriately when sudden fluctuations in demand or unexpected events occur. This can lead to inefficient inventory management, increased food waste, and reduced profits.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0620] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for using a generative AI model to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order orders and notifying a user terminal, means for displaying the order orders received on the user terminal, means for the user to confirm and modify order information using prompt text, and means for finalizing order information and sending it to a warehouse or supplier. This improves the accuracy of demand forecasts and enables the determination of appropriate order quantities. Furthermore, users can easily confirm and modify order information using prompt text, enabling quick and accurate ordering.

[0621] "Sales data" refers to data including the quantity of merchandise sold at a store, sales figures by category, and sales trends by date and time.

[0622] "Weather information" refers to meteorological data such as the weather forecast, temperature, precipitation, wind speed, and humidity for a specified area.

[0623] "Regional event information" is information about events such as festivals, sporting events, and exhibitions held in a specified region.

[0624] "Integrated data" is data that combines multiple datasets, such as sales data, weather information, and local event information, into a format that can be processed as a single dataset.

[0625] A "generative AI model" is an artificial intelligence algorithm that is trained to perform a specific task, such as demand forecasting, from a large dataset.

[0626] "Demand forecast result" is a forecast value of future demand calculated by the generative AI model.

[0627] "Order quantity" refers to the amount of each product to be purchased that is determined based on the demand forecast results.

[0628] An "order instruction" is an instruction document that specifies a specific product name and quantity, and is generated based on the determined order amount.

[0629] "User terminal" means an electronic device used by a store employee to receive, display, and modify order instructions.

[0630] "Prompt text" refers to guidelines or instructions that users use when checking or correcting order information.

[0631] "Final order information" refers to the final product order information that has been confirmed after the user has confirmed and corrected it.

[0632] "Warehouse or supplier" refers to the logistics facility or product supplier to which order information is sent.

[0633] This invention is a demand forecasting and optimal ordering system for stores, specifically a system that uses sales data, weather information, and local event information to forecast demand and determine order quantities, thereby improving the efficiency of store inventory management and reducing food waste.

[0634] Server Processing

[0635] The server first obtains sales data from the store's POS system. Next, it obtains weather information online using a weather forecast API, and also collects event information from a local event calendar. Statistical methods and data cleaning techniques are used to integrate and preprocess this data. The server uses a generative AI model based on this integrated data to predict product demand. The optimal order quantity is determined based on the demand forecast results, and an order order is generated.

[0636] Terminal handling

[0637] The terminal displays the order instruction received from the server on the screen. The user, who is a store employee, confirms the order details displayed on the terminal. Prompt statements are used to allow the user to confirm the order information in an easy-to-understand manner. For example, specific items and quantities such as "500ml of tea: 500 bottles" are displayed. If necessary, the user can modify the order quantity. The modified details are quickly recalculated, and the final order information is generated when the user presses the confirm button.

[0638] User operations

[0639] The user checks and modifies the order information displayed on the terminal and finally confirms the order. The confirmed order information is sent back to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0640] Hardware and software used

[0641] Hardware: Servers, user devices (tablets and smartphones)

[0642] Software: Weather forecast API, data cleaning software, generative AI models (e.g., Keras)

[0643] Specific examples

[0644] For example, consider a case study at a convenience store in Tokyo on August 15th. The server retrieves sales data up to August 14th from the POS system, and determines from weather information obtained from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. This integrated data is input into an AI model, which predicts an increase in demand for 500ml tea and ice cream. As a result, it generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0645] Prompt Sentence Examples

[0646] Below is an example of an actual prompt sentence.

[0647] 1. Weather information prompts:

[0648] Please enter the weather information for this weekend. Example: Sunny, temperature 30°C

[0649] 2. Event information related prompts:

[0650] Enter local event information. Example: Summer festival, 1000 people

[0651] 3. Sales data related prompts:

[0652] Please enter the sales data for the most recent week in CSV format.

[0653] This reduces the workload of employees while enabling accurate demand forecasting and efficient inventory management, reducing food waste and improving store profits.

[0654] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0655] Step 1:

[0656] The server retrieves sales data from the store's POS system. Specifically, it connects to the database and uses a query to extract sales data from the past few days. This allows data to be obtained that can be used to understand the sales trends of products in the store.

[0657] Input: Sales data from POS system

[0658] Output: Extracted sales dataset

[0659] Step 2:

[0660] The server retrieves weather information from a weather forecast API, which includes meteorological data such as weather, temperature, and precipitation for a specific region. It sends a request to the API endpoint and analyzes the data received in response. This allows it to obtain weather information that affects product demand.

[0661] Input: Weather forecast API request information (location, date and time, etc.)

[0662] Output: Obtained weather information data

[0663] Step 3:

[0664] The server collects event information from the local event calendar and stores it in a database, allowing it to consider the impact of local events on product demand.

[0665] Input: Events calendar URL or API endpoint

[0666] Output: Captured event information data

[0667] Step 4:

[0668] The server integrates sales data, weather information, and event information, performs preprocessing, cleans the data, and converts it into a format suitable for AI models by properly handling missing values ​​and outliers.

[0669] Input: Sales dataset, weather information data, event information data

[0670] Output: Unified dataset

[0671] Step 5:

[0672] The server then inputs the integrated data into a generative AI model that is pre-trained and uses statistical methods and machine learning algorithms to forecast product demand.

[0673] Input: Unified dataset

[0674] Output: Demand forecast result data

[0675] Step 6:

[0676] The server determines the optimal order quantity based on the demand forecast results, and uses a decision algorithm to calculate the order quantity of the product according to the forecasted demand.

[0677] Input: Demand forecast result data

[0678] Output: Order quantity determination data

[0679] Step 7:

[0680] The server generates an order instruction and notifies the user terminal of the order instruction, which includes the specific product name and quantity.

[0681] Input: Order quantity determination data

[0682] Output: Purchase order data

[0683] Step 8:

[0684] The terminal displays the order command received from the server on its screen, and the order information is displayed in a format that is easy for the user to understand.

[0685] Input: Purchase order data

[0686] Output: Order information displayed on the user's terminal

[0687] Step 9:

[0688] The user checks the order information displayed on the terminal and makes any necessary corrections. Prompts are displayed to assist the user in making corrections. For example, it is possible to change a 500ml order of tea from 400 bottles to 500 bottles.

[0689] Input: User modifications

[0690] Output: Corrected order information

[0691] Step 10:

[0692] The user finally confirms the revised order information by pressing the Confirm button, which sends the final order information to the server.

[0693] Enter: Confirmed order information

[0694] Output: Sends the final order information to the server

[0695] Step 11:

[0696] The server sends the final confirmed order information to the warehouse or supplier to complete the order processing.

[0697] Input: Final Order Information

[0698] Output: Send purchase order information to warehouse or supplier

[0699] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0700] ---

[0701] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information at stores such as convenience stores, and automatically determines the optimal ordering timing and order quantity, thereby improving ordering accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[0702] Server Processing

[0703] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to perform product demand forecasting. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[0704] Terminal handling

[0705] The terminal displays the order instructions received from the server on its screen. The user (store employee) can check the order details displayed on the terminal and make any necessary corrections. In addition, the emotion engine collects the user's emotional data and evaluates the user's stress level and emotional state. This information is also sent to the server as part of the demand forecast.

[0706] User operations

[0707] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. For example, if it is determined that the demand for tea is higher than expected, the order quantity can be increased manually. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[0708] Emotion engine processing

[0709] The emotion engine collects emotional data in real time when users confirm or modify order information. This emotional data is extracted from the user's facial expressions, voice, operation speed, etc. The emotion engine uses the collected data to evaluate the user's stress level and emotional state, and sends the evaluation results to the server. The server incorporates this emotional data into the demand forecasting model to improve the accuracy of the forecast.

[0710] Specific examples

[0711] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0712] 1. Server

[0713] Retrieve sales data from the POS system up to August 14th.

[0714] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[0715] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[0716] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[0717] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0718] 2. Terminal

[0719] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[0720] The emotion engine analyzes the user's facial expressions, voice, etc. in real time to assess their stress level and emotional state.

[0721] 3. Users

[0722] The user checks the order details displayed on the terminal.

[0723] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[0724] After correction, the emotion engine records the user's reaction and sends it to the server.

[0725] Confirm the order information and press the Confirm button.

[0726] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0727] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits. In addition, by utilizing user emotion data, further improvements in ordering accuracy can be expected.

[0728] ---

[0729] The processing flow will be explained below.

[0730] ---

[0731] Step 1:

[0732] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[0733] Step 2:

[0734] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[0735] Step 3:

[0736] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[0737] Step 4:

[0738] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[0739] Step 5:

[0740] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[0741] Step 6:

[0742] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[0743] Step 7:

[0744] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[0745] Step 8:

[0746] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[0747] Step 9:

[0748] The user checks the order information displayed on the terminal, and the emotion engine analyzes the user's facial expressions, voice, and operation speed in real time to collect emotional data.

[0749] Step 10:

[0750] Check whether the order quantity confirmed by the user is appropriate and make corrections if necessary. For example, if it is determined that an order of 500 bottles of 500ml tea is insufficient, manually correct it to 600 bottles.

[0751] Step 11:

[0752] The user confirms the order information, and the emotion engine evaluates the user's stress level and emotional state and sends the data to the server.

[0753] Step 12:

[0754] The server sends an order instruction to the warehouse or supplier based on the final order information including the emotion data.

[0755] Step 13:

[0756] Once confirmation is sent from the warehouse or supplier, the server receives it and notifies the user terminal, thereby completing the order process.

[0757] ---

[0758] Example 2

[0759] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0760] Conventional demand forecasting systems make predictions based on sales data, weather information, and local event information, but because they do not take into account non-numerical factors such as users' emotions and stress levels, they have problems with low demand forecast accuracy and inefficient inventory management and ordering.In addition, because they ignore users' stress and emotions when adjusting order quantities, they place a heavy burden on the work and a high risk of incorrect ordering.

[0761] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for predicting demand from the integrated data, means for determining the order quantity based on the demand forecast result, means for generating an order instruction and notifying the terminal, means for displaying the order instruction received by the terminal, means for the user to confirm and correct the order information, means for collecting and evaluating user emotion data, means for reflecting the evaluation result in the demand forecast, and means for finalizing the order information and sending it to the warehouse or supplier. This enables highly accurate demand forecasting that takes user emotion data into account and efficient order management.

[0762] "Sales data" is data obtained from a sales system that indicates the sales performance of a product during a specific period.

[0763] "Weather information" is information about a specific region and time period, including weather conditions such as temperature, chance of precipitation, and wind speed.

[0764] "Regional event information" is information about the date, time, location, and content of an event held in a specific region.

[0765] "Integrated data" is centralized data that combines sales data, weather information, and local event information.

[0766] "Preprocessing" refers to processing performed on acquired data, such as filling in missing values, removing outliers, and normalizing the data.

[0767] "Demand forecasting" refers to the use of integrated data to predict future demand for a product.

[0768] The "order quantity" is the quantity of the product to be purchased, determined based on the demand forecast.

[0769] An "order command" is a command indicating the determined order quantity, and is notified to the terminal.

[0770] A "terminal" is an electronic device that receives order orders and displays information to a user.

[0771] "User" refers to a person, such as a store employee, who operates the system and checks and modifies order information.

[0772] "Emotion data" is data that indicates the user's emotional state, extracted from the user's facial expression, tone of voice, operation speed, and the like.

[0773] The "evaluation result" is an evaluation index of the user's stress level and emotional state derived from the emotion data.

[0774] A "warehouse" is a facility where product inventory is stored.

[0775] "Supplier" refers to the supplier or manufacturer that provides the goods.

[0776] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines optimal order quantities and timing, improving prediction accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[0777] The server obtains sales data from the POS system. To do this, for example, the sales data collection device requests sales data for a specific period using API communication and receives it in JSON format. As a specific example, a request to the POS system is made as follows: GET / sales?start_date=2023-08-01&end_date=2023-08-14.

[0778] Next, the server retrieves weather information using a weather forecast API. For example, the API request uses the format GET / weather?location=tokyo&date=2023-08-15. The retrieved weather information includes data such as temperature, probability of precipitation, and wind speed.

[0779] The server then uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The response includes the event name, location, start time, and end time.

[0780] The acquired sales data, weather information, and local event information are centralized and treated as integrated data. This integrated data is then preprocessed. Preprocessing includes filling in missing values, removing outliers, and normalizing the data. This improves the quality of the data.

[0781] The server inputs the preprocessed integrated data into a generative AI model, such as Google Cloud's "AI Platform Prediction." The generative AI model performs demand forecasting based on a prompt, such as, "Please predict tomorrow's product demand based on today's sales data, weather information, and local event information. Please provide detailed information on demand for 500ml of tea and ice cream."

[0782] Based on the demand forecast results, the server determines the optimal order quantity. For example, it generates an order to order 500 bottles of 500ml tea and 300 ice creams. The order is notified to the terminal.

[0783] The terminal displays the ordering instructions received from the server on its screen. Specifically, for example, information such as "500 bottles of 500ml tea" and "300 ice creams" is displayed to the user on a tablet. The user can check this information and modify it as necessary.

[0784] The device is equipped with an emotion engine that uses Microsoft's Azure Emotion API to collect user emotion data, which is extracted from the user's facial expressions, tone of voice, and operation speed, and analyzed in real time.

[0785] The user checks the order information displayed on the terminal and modifies the order quantity if necessary. For example, the user can change the predicted order quantity of ice cream to 350. The emotion engine records the modifications made by the user and their emotional state at the time, and sends them to the server.

[0786] Finally, once the user has finalized the order information, it is sent to the server, which then sends it to the warehouse or supplier to complete the order process.

[0787] This will enable highly accurate demand forecasting and efficient order management that takes into account user emotional data. Utilizing emotional data will also reduce user stress and significantly reduce the risk of incorrect orders.

[0788] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0789] Step 1:

[0790] The server obtains sales data from the POS system. Specifically, it requests sales data for a specific period via API communication and receives it in JSON format. For example, a request is made in the format GET / sales?start_date=2023-08-01&end_date=2023-08-14. The input is an API request with a specified period, and the output is sales data for the specified period. Data processing includes normalization and missing value completion.

[0791] Step 2:

[0792] The server obtains weather information using the weather forecast API. Using the API key, it makes a request in the format GET / weather?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is weather information such as temperature, precipitation probability, and wind speed. The server converts this data into the required format and performs preprocessing.

[0793] Step 3:

[0794] The server uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is event information such as the event name, location, start time, and end time. The server organizes and preprocesses the acquired event information.

[0795] Step 4:

[0796] The server integrates sales data, weather information, and local event information to generate a unified dataset. The input is the various data that has been acquired and preprocessed up to that point, and the output is the integrated data. Data processing includes filling in missing values, removing outliers, and normalizing the data. For example, data frames are manipulated using the Python Pandas library.

[0797] Step 5:

[0798] The server inputs the integrated data into a generative AI model (for example, Google Cloud's "AI Platform Prediction") and performs demand forecasting. The input is the integrated dataset, and the output is a supply and demand forecast for each product. The prompt used is, "Based on today's sales data, weather information, and local event information, please predict tomorrow's product demand. Please tell me in detail the demand for 500ml of tea and ice cream in particular."

[0799] Step 6:

[0800] The server determines the optimal order quantity based on the results of the demand forecast. The input is the demand forecast result, and the output is an order command. For example, it generates a command to order 500 bottles of 500ml tea and 300 ice creams. The server converts this command data into JSON format and notifies the terminal.

[0801] Step 7:

[0802] The terminal displays the ordering command received from the server on its screen. The input is the ordering command sent from the server, and the output is the ordering information displayed on the terminal screen. For example, "500ml tea: 500 bottles" and "300 ice creams" are displayed on the tablet.

[0803] Step 8:

[0804] The user checks the order information displayed on the terminal and modifies it as necessary. The input is the order information displayed on the screen, and the output is the order information modified by the user. For example, the user can modify the order quantity to 350 ice creams.

[0805] Step 9:

[0806] The device uses an emotion engine (for example, Microsoft's "Azure Emotion API") to collect and evaluate the user's emotional data. The input is the user's facial expression, tone of voice, operation speed, etc., and the output is an evaluation of the user's stress level and emotional state. The evaluation results are sent from the device to a server.

[0807] Step 10:

[0808] The server reflects the user's emotional data and the revised order information in the demand forecasting model and performs a new forecast. The input is the user's emotional data and the revised order information, and the output is the revised demand forecast result. This allows the final order quantity to be reevaluated.

[0809] Step 11:

[0810] The user finally confirms the order information and presses the "Confirm" button on the terminal. The input is the confirmation instruction by the user's operation, and the output is the confirmed order information.

[0811] Step 12:

[0812] The server then sends the confirmed order information to the warehouse or supplier to complete the order processing. The input is the confirmed order information, and the output is the status of delivery preparation or supply instruction. This ensures the smooth running of the product supply chain.

[0813] (Application example 2)

[0814] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0815] Conventional product demand forecasting and order management systems for convenience stores and other retailers use sales data, weather information, local event information, and other data to perform automated demand forecasting. However, these systems still sometimes result in incorrect orders, which impacts the work environment and mental stress of users (store employees). Furthermore, the process of checking and correcting demand forecast results is cumbersome, requiring more efficient work. Furthermore, there is a lack of means to visually check order information in real time using wearable devices. The problem that this invention aims to solve is to provide a system that solves these problems and allows users to intuitively and efficiently perform demand forecasting and order management.

[0816] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0817] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, and means for acquiring local event information. This allows the server to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order instructions and notifying a user terminal, means for displaying the order instructions received on the user terminal, means for the user to confirm and modify order information, means for finalizing order information and sending it to a warehouse or supplier, means for collecting emotional data and evaluating the emotional state, means for incorporating the emotional data into demand forecasting to improve order accuracy, and means for using a wearable device for the user to visually check order information displayed in real time. This allows the user to intuitively and efficiently perform demand forecasting and order management, improve order accuracy, reduce the user's workload, and improve the work environment.

[0818] "Sales data" is data that records the sales performance of each product in a store.

[0819] "Weather information" is data related to weather conditions and is information used to predict demand for stores.

[0820] "Regional event information" is data related to events held in the target region.

[0821] "Integrated data" refers to data that integrates sales data, weather information, and local event information.

[0822] "Demand forecasting" refers to predicting future demand for a product based on integrated data.

[0823] An "order command" is a command that specifies the order quantity determined based on the demand forecast results.

[0824] A "user terminal" is a device operated by a user, which displays order instructions and allows modification and confirmation of orders.

[0825] "Emotion data" refers to data relating to the emotional state of a user extracted from facial expressions, voice, and the like.

[0826] "Emotional state" is an evaluation that indicates the user's emotional state, and includes stress level, satisfaction level, and the like.

[0827] A "wearable device" is a device worn by a user, such as smart glasses.

[0828] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines the optimal order timing and order quantity. This system allows users to intuitively and efficiently perform demand forecasting and order management. It also uses a wearable device that allows users to visually check order information displayed in real time.

[0829] Program Generation

[0830] The server is configured as follows:

[0831] 1. The means of obtaining sales data is connected to a POS system, which has the function of automatically collecting daily sales data.

[0832] 2. To obtain weather information, use an online weather forecast API (e.g., OpenWeatherMap API) to obtain the necessary weather information.

[0833] 3. To obtain local event information, use a local event calendar API (e.g., Google Calendar API) to collect information on events occurring in the area.

[0834] The means for integrating and preprocessing this data is integrated with a database system to clean the data and standardize the format. The means for predicting demand from the integrated data is to use a generative AI model using TensorFlow or PyTorch to perform demand forecasting. The means for determining order quantities based on the demand forecast results is an algorithm that calculates the optimal order quantity from the prediction results of the AI ​​model.

[0835] The means of collecting emotional data and evaluating emotional states are to use sensors built into smart glasses and wearable devices, as well as the Affectiva SDK and Microsoft Azure's Emotion API, to collect and evaluate emotional data from the user's facial expressions and voice in real time. By incorporating the results of this evaluation into demand forecasts, the accuracy of ordering can be improved.

[0836] The system notifies the user terminal of the order order and allows the user to confirm and modify it by displaying the order information in real time on the display of smart glasses (e.g., HoloLens or Google Glass). The user can confirm the displayed order details and modify them as necessary. The final order information is automatically sent to the server and transmitted to the warehouse or supplier.

[0837] Specific examples

[0838] For example, a demand forecast is made for a store in an urban area on August 15th based on sales data, weather information, and local event information. Based on sales data obtained from the POS system, high temperature forecasts obtained from a weather forecast API, and information about local summer festivals, it is predicted that demand for 500ml of tea and ice cream will increase. The generative AI model generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0839] Users wear smart glasses and check order information in real time. The emotion engine detects the user's stress level from their facial expressions and can automatically adjust the order quantity if the stress level is high. If the user wants to manually increase the order quantity, they can make the adjustment through the smart glasses and the information is sent back to the server.

[0840] Prompt Sentence Examples

[0841] "Use the smart glasses to check the order quantity for 500ml of tea and manually adjust it based on demand forecast and emotion data. The emotion engine will detect stress levels from facial expressions and optimize the ordering process as needed."

[0842] This improves ordering accuracy, reduces the user's workload, and enables efficient inventory management. Utilizing user emotion data also enables more detailed demand forecasts, contributing to increased store profits.

[0843] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0844] Step 1:

[0845] The server retrieves sales data from the POS system. This sales data includes sales records for each product and is used as information necessary for the next demand forecast. Specifically, the most recent sales data is extracted from the database using a query.

[0846] Step 2:

[0847] The server retrieves weather information from an online weather forecast API (e.g., OpenWeatherMap API). The retrieved information includes temperature, probability of precipitation, humidity, etc., and combines this information with sales data to input into the next forecast model. The weather data retrieved from the API is parsed in JSON format, and the necessary information is extracted.

[0848] Step 3:

[0849] The server retrieves local event information from a local event calendar API (e.g., Google Calendar API). It collects information such as the event type, date, time, and location, and combines this with sales data and weather information. The event information is also retrieved in JSON format, and the necessary data is extracted by parsing it.

[0850] Step 4:

[0851] The server combines sales data, weather information, and local event information, and performs preprocessing. It normalizes the data, removes outliers, and standardizes formats to create a combined dataset that is ready to be input into the AI ​​model.

[0852] Step 5:

[0853] The server inputs the integrated data into a generative AI model (using, for example, TensorFlow or PyTorch) to perform demand forecasting. The AI ​​model predicts product demand from the integrated data and outputs the results. Specifically, a regression analysis is performed using a neural network, and the predicted sales volume for each product is output.

[0854] Step 6:

[0855] The server determines the optimal order quantity based on the demand forecast results. This order quantity is calculated taking into account forecast sales volume and inventory information, and is generated as an order instruction. The algorithm adjusts the order quantity so that the optimal inventory level is maintained.

[0856] Step 7:

[0857] The server notifies the user terminal of the generated order command. The order command includes the product type, order quantity, delivery date, etc., and is sent to the user terminal. The notification is sent in real time via a cloud service.

[0858] Step 8:

[0859] The user terminal displays the order instruction received from the server. The order information is displayed on the display of the smart glasses or wearable device, and the user confirms it. The UI is designed to display the order details in a format that is easy to visually confirm.

[0860] Step 9:

[0861] The user can check the order information displayed on the device and make any necessary changes. If necessary, the user can change the order quantity through the smart glasses interface. During this process, the emotion engine analyzes the user's facial expressions and voice to collect emotional data such as stress level.

[0862] Step 10:

[0863] The user terminal sends the final confirmed order information to the server, which then forwards the received confirmed order information to the warehouse or supplier and completes the actual order processing. This ensures that the appropriate quantity of products is ordered at the appropriate time.

[0864] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0865] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0866] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0867] [Third embodiment]

[0868] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0869] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0870] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0871] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0872] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0873] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0874] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0875] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0876] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0877] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0878] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0879] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0880] ---

[0881] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0882] Server Processing

[0883] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to predict product demand. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[0884] Terminal handling

[0885] The terminal displays the order instructions received from the server on its screen. The user (store employee) checks the order details displayed on the terminal and can make corrections if necessary. For example, if it is determined that demand for tea is higher than expected, the amount to be ordered can be manually increased.

[0886] User operations

[0887] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[0888] Specific examples

[0889] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0890] 1. Server

[0891] Retrieve sales data from the POS system up to August 14th.

[0892] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[0893] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[0894] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[0895] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[0896] 2. Terminal

[0897] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[0898] 3. Users

[0899] The user checks the order details displayed on the terminal.

[0900] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[0901] After making corrections, confirm the order information and press the Confirm button.

[0902] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[0903] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits.

[0904] ---

[0905] The processing flow will be explained below.

[0906] ---

[0907] Step 1:

[0908] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[0909] Step 2:

[0910] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[0911] Step 3:

[0912] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[0913] Step 4:

[0914] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[0915] Step 5:

[0916] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[0917] Step 6:

[0918] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[0919] Step 7:

[0920] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[0921] Step 8:

[0922] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[0923] Step 9:

[0924] The user checks the order information displayed on the terminal, checks whether the displayed order quantity is appropriate, and takes into account the stock situation to prevent unnecessary ordering mistakes.

[0925] Step 10:

[0926] The user can adjust the order quantity as needed. For example, if it is determined that 500 bottles of 500ml tea is not enough, the user can manually adjust the order quantity to 600 bottles.

[0927] Step 11:

[0928] After the user confirms and modifies the order information, they press the button on the terminal to confirm the order, which finalizes the order information.

[0929] Step 12:

[0930] The terminal sends the finalized order information to the server, which receives the final order information and sends an order instruction to the warehouse or supplier.

[0931] Step 13:

[0932] The server receives confirmation from the warehouse or supplier and notifies the user terminal that the order has been accepted, thereby completing the ordering process.

[0933] ---

[0934] Example 1

[0935] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0936] Traditionally, product demand forecasting and ordering in stores relied primarily on experience and intuition, often lacking in accuracy. Furthermore, manually collecting and integrating data from multiple sources required time and effort, making it inefficient. This often led to problems such as inventory shortages and excess inventory, making optimal inventory management and efficient ordering difficult.

[0937] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0938] In this invention, the server includes a means for acquiring sales data, a means for acquiring weather information, and a means for acquiring local event information. This enables accurate demand forecasting by automatically collecting and integrating data from multiple data sources and using a generative AI model. Furthermore, the server includes a means for determining optimal order quantities based on the demand forecast results, generating order orders, and notifying the terminal. This allows store employees to efficiently perform ordering tasks, preventing inventory shortages and excess inventory, reducing food waste, and improving store profits. Furthermore, a system is constructed in which users can use their terminals to confirm and modify order information, finalize the order information, and send it to the server, ensuring that the final order details are accurately reflected.

[0939] ---

[0940] ---

[0941] "Sales data" is a record of merchandise sales in a store, and includes information such as sales quantity, sales date and time, and merchandise category.

[0942] "Weather information" is data relating to weather conditions, and is weather forecast data including information such as temperature, precipitation, humidity, and wind speed.

[0943] "Regional event information" is data relating to events held in a specific region, including information such as the date and time of the event, the venue, the content of the event, and the expected number of participants.

[0944] "Integrated data" is data that combines sales data, weather information, and local event information into a single dataset, and these data are linked together and organized into a processable format.

[0945] A "generative AI model" is a model that uses machine learning algorithms to learn patterns from data and predict future demand.

[0946] An "order command" is a command that specifies the order quantity and timing of a specific product based on predicted demand.

[0947] A "user terminal" is a device used by a store employee to receive, display, and modify order instructions.

[0948] "Supply source" refers to the warehouse or supplier responsible for supplying the goods, and is the party to which the goods are delivered upon receipt of an order.

[0949] "Confirmation and modification" refers to the operation in which the user checks the order information displayed on the terminal and changes the contents as necessary.

[0950] "Final order information" refers to the final order details confirmed after confirmation and correction by the user.

[0951] ---

[0952] The above are definitions of important words included in the scope of the patent claims.

[0953] ---

[0954] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[0955] Server Processing

[0956] The server first obtains sales data from the POS system. To do this, the server automatically accesses the POS system at a specific time (for example, 1:00 AM every day) and downloads all sales data from the previous day. Next, it obtains weather information using a weather forecast API. In this process, the server sends a request to the weather forecast API at 2:00 AM to obtain real-time weather information. The server also references a local event calendar to obtain information about events in the vicinity of the store. Specifically, the server accesses a website that provides event information at 3:00 AM and scrapes information about nearby events.

[0957] After collecting this data, the server integrates and preprocesses sales data, weather information, and local event information. The integrated data is processed by standardizing different data formats, filtering unnecessary data, and imputing missing values. The preprocessed data is then input into a generative AI model to forecast product demand. The generative AI model uses machine learning algorithms to learn patterns from the data and predict future demand with high accuracy.

[0958] Based on the results of the demand forecast, the server determines the optimal order quantity and generates an order command. The generated order command includes a specific product name and order quantity, such as "500 bottles of 500ml tea" or "300 ice creams." This order command is notified to the terminal.

[0959] Terminal handling

[0960] The terminal displays the ordering instructions received from the server on its screen. Terminals are devices used by store employees, and include tablets and desktop PCs. The terminal receives an ordering instruction from the server at 6:00 AM and displays an order such as "500 bottles of 500ml tea" or "300 ice creams" on its screen.

[0961] User operations

[0962] The user checks the order information displayed on the terminal. Specifically, the user can check each item and its order quantity displayed on the screen and make any necessary corrections. For example, if the user wants to add 50 more ice creams to the predicted order quantity, they can correct it to 350 on the terminal.

[0963] After making the corrections, the user confirms the order information and sends it to the server. When the user presses the "Confirm" button, the corrected order information is sent from the terminal to the server. The server receives the final order information and sends it to the supply source (warehouse or supplier) to complete the order processing.

[0964] Examples and prompts

[0965] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[0966] The server retrieves sales data up to August 14th from the POS system, and determines from weather information retrieved from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. By integrating this data and using a generative AI model to perform a demand forecast, it predicts that demand for 500ml tea and ice cream will increase. As a result, an order to order 500 additional 500ml bottles of tea and 300 ice creams is generated and notified to the terminal.

[0967] If the user checks the order on the terminal and corrects the order quantity to 350 ice creams, the final order information is sent to the server by pressing the confirm button. The server sends this information to the supplier and completes the order process.

[0968] Examples of prompts:

[0969] Integrate store sales data, weather information, and local event information to forecast demand at convenience stores in Tokyo on August 15th. Based on the forecast, determine the timing and quantity of orders.

[0970] ---

[0971] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0972] ---

[0973] Step 1: Obtaining sales data

[0974] The server obtains sales data from the POS system.

[0975] Input: The server sends a request to the POS system's API.

[0976] Data processing: The previous day's sales data is sent in response to the request.

[0977] Output: The previous day's sales data is saved in JSON format on the server.

[0978] Specific operation: The server accesses the POS system at 1:00 AM every day and downloads all sales data from the previous day.

[0979] Step 2: Get weather information

[0980] The server retrieves weather information from an online weather forecast API.

[0981] Input: The server sends a request to the weather API.

[0982] Data processing: Analyze the data returned from the weather forecast API and extract the necessary parts.

[0983] Output: The weather information for the day is saved in JSON format on the server.

[0984] Specific operation: The server sends a request to the weather forecast API at 2 AM to obtain real-time weather information.

[0985] Step 3: Get local event information

[0986] The server obtains event information from a local event calendar.

[0987] Input: Server accesses a website for local event information.

[0988] Data processing: Using scraping technology to extract event information from web pages.

[0989] Output: Event information is saved to the server in text format.

[0990] What it does: The server scrapes a website that provides event information at 3 AM.

[0991] Step 4: Data integration and preprocessing

[0992] The server integrates the acquired sales data, weather information, and local event information and performs preprocessing.

[0993] Inputs: Sales data, weather information, and event information datasets.

[0994] Data processing: Standardize data formats, filter unnecessary data, and fill in missing values.

[0995] Output: Preprocessed integrated data is generated.

[0996] Specific operation: The server performs the process of unifying different data formats into a single dataset.

[0997] Step 5: Demand forecast

[0998] The server inputs the preprocessed data into a generative AI model to predict product demand.

[0999] Input: Preprocessed integrated data.

[1000] Data Computing: Use generative AI models to forecast demand.

[1001] Output: Demand forecast results, demand quantity for each product.

[1002] Specific operation: The server inputs data into the generated AI model, and the AI ​​outputs the demand forecast results.

[1003] Step 6: Determine order quantity and generate order instructions

[1004] The server determines the optimal order quantity based on the demand forecast results and generates an order instruction.

[1005] Input: Demand forecast results.

[1006] Data calculation: Calculate the order quantity based on the forecast results.

[1007] Output: A purchase order is generated, containing the specific product name and quantity to order.

[1008] Specific operation: The server analyzes the AI's demand forecast results and automatically generates ordering instructions such as "500ml tea: 500 bottles" and "Ice cream: 300 pieces."

[1009] Step 7: View Purchase Orders

[1010] The terminal displays the order instruction received from the server on the screen.

[1011] Input: The purchase order sent by the server.

[1012] Data processing: Converting order orders into a format that is easy to view on the screen.

[1013] Output: The order details are displayed on the display screen.

[1014] Specific operation: The terminal receives an order command from the server at 6:00 a.m. and displays "500ml tea: 500 bottles" and "300 ice creams" on the screen.

[1015] Step 8: Review and correct your order

[1016] The user checks the order information displayed on the terminal and makes corrections as necessary.

[1017] Input: Purchase order displayed on the terminal.

[1018] Data manipulation: The order quantity is modified based on the user's input.

[1019] Output: The modified purchase order.

[1020] Specific operation: The user checks the order details displayed on the screen and corrects the order quantity to, for example, 350 ice creams.

[1021] Step 9: Confirm and submit your order

[1022] The user confirms the corrected order information and transmits it from the terminal to the server.

[1023] Input: Revised purchase order information.

[1024] Data calculation: The order information is finalized.

[1025] Output: The final order information is sent to the server.

[1026] Specific operation: The user presses the "Confirm" button, and the revised order details are sent from the terminal to the server.

[1027] Step 10: Complete the final order process

[1028] The server receives the final order information and transmits it to the source to complete the order process.

[1029] Input: Final order information.

[1030] Data Calculation: Sends final order information to the source system.

[1031] Output: An order is sent to the source of supply.

[1032] Specific operation: The server automatically sends the revised order information to the warehouse management system and arranges for inventory.

[1033] ---

[1034] The above is a description of the specific flow of processing of the system program and the specific operation at each processing step.

[1035] (Application example 1)

[1036] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1037] Determining the appropriate product order quantity for a store requires consideration of multiple factors, including sales data, weather information, and information about local events, making it difficult to predict. In particular, employees often rely on their own experience and intuition, resulting in ordering errors and excessive or insufficient inventory. Furthermore, it is difficult to respond appropriately when sudden fluctuations in demand or unexpected events occur. This can lead to inefficient inventory management, increased food waste, and reduced profits.

[1038] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1039] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for using a generative AI model to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order orders and notifying a user terminal, means for displaying the order orders received on the user terminal, means for the user to confirm and modify order information using prompt text, and means for finalizing order information and sending it to a warehouse or supplier. This improves the accuracy of demand forecasts and enables the determination of appropriate order quantities. Furthermore, users can easily confirm and modify order information using prompt text, enabling quick and accurate ordering.

[1040] "Sales data" refers to data including the quantity of merchandise sold at a store, sales figures by category, and sales trends by date and time.

[1041] "Weather information" refers to meteorological data such as the weather forecast, temperature, precipitation, wind speed, and humidity for a specified area.

[1042] "Regional event information" is information about events such as festivals, sporting events, and exhibitions held in a specified region.

[1043] "Integrated data" is data that combines multiple datasets, such as sales data, weather information, and local event information, into a format that can be processed as a single dataset.

[1044] A "generative AI model" is an artificial intelligence algorithm that is trained to perform a specific task, such as demand forecasting, from a large dataset.

[1045] "Demand forecast result" is a forecast value of future demand calculated by the generative AI model.

[1046] "Order quantity" refers to the amount of each product to be purchased that is determined based on the demand forecast results.

[1047] An "order instruction" is an instruction document that specifies a specific product name and quantity, and is generated based on the determined order amount.

[1048] "User terminal" means an electronic device used by a store employee to receive, display, and modify order instructions.

[1049] "Prompt text" refers to guidelines or instructions that users use when checking or correcting order information.

[1050] "Final order information" refers to the final product order information that has been confirmed after the user has confirmed and corrected it.

[1051] "Warehouse or supplier" refers to the logistics facility or product supplier to which order information is sent.

[1052] This invention is a demand forecasting and optimal ordering system for stores, specifically a system that uses sales data, weather information, and local event information to forecast demand and determine order quantities, thereby improving the efficiency of store inventory management and reducing food waste.

[1053] Server Processing

[1054] The server first obtains sales data from the store's POS system. Next, it obtains weather information online using a weather forecast API, and also collects event information from a local event calendar. Statistical methods and data cleaning techniques are used to integrate and preprocess this data. The server uses a generative AI model based on this integrated data to predict product demand. The optimal order quantity is determined based on the demand forecast results, and an order order is generated.

[1055] Terminal handling

[1056] The terminal displays the order instruction received from the server on the screen. The user, who is a store employee, confirms the order details displayed on the terminal. Prompt statements are used to allow the user to confirm the order information in an easy-to-understand manner. For example, specific items and quantities such as "500ml of tea: 500 bottles" are displayed. If necessary, the user can modify the order quantity. The modified details are quickly recalculated, and the final order information is generated when the user presses the confirm button.

[1057] User operations

[1058] The user checks and modifies the order information displayed on the terminal and finally confirms the order. The confirmed order information is sent back to the server, which then sends it to the warehouse or supplier to complete the order processing.

[1059] Hardware and software used

[1060] Hardware: Servers, user devices (tablets and smartphones)

[1061] Software: Weather forecast API, data cleaning software, generative AI models (e.g., Keras)

[1062] Specific examples

[1063] For example, consider a case study at a convenience store in Tokyo on August 15th. The server retrieves sales data up to August 14th from the POS system, and determines from weather information obtained from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. This integrated data is input into an AI model, which predicts an increase in demand for 500ml tea and ice cream. As a result, it generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1064] Prompt Sentence Examples

[1065] Below is an example of an actual prompt sentence.

[1066] 1. Weather information prompts:

[1067] Please enter the weather information for this weekend. Example: Sunny, temperature 30°C

[1068] 2. Event information related prompts:

[1069] Enter local event information. Example: Summer festival, 1000 people

[1070] 3. Sales data related prompts:

[1071] Please enter the sales data for the most recent week in CSV format.

[1072] This reduces the workload of employees while enabling accurate demand forecasting and efficient inventory management, reducing food waste and improving store profits.

[1073] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1074] Step 1:

[1075] The server retrieves sales data from the store's POS system. Specifically, it connects to the database and uses a query to extract sales data from the past few days. This allows data to be obtained that can be used to understand the sales trends of products in the store.

[1076] Input: Sales data from POS system

[1077] Output: Extracted sales dataset

[1078] Step 2:

[1079] The server retrieves weather information from a weather forecast API, which includes meteorological data such as weather, temperature, and precipitation for a specific region. It sends a request to the API endpoint and analyzes the data received in response. This allows it to obtain weather information that affects product demand.

[1080] Input: Weather forecast API request information (location, date and time, etc.)

[1081] Output: Obtained weather information data

[1082] Step 3:

[1083] The server collects event information from the local event calendar and stores it in a database, allowing it to consider the impact of local events on product demand.

[1084] Input: Events calendar URL or API endpoint

[1085] Output: Captured event information data

[1086] Step 4:

[1087] The server integrates sales data, weather information, and event information, performs preprocessing, cleans the data, and converts it into a format suitable for AI models by properly handling missing values ​​and outliers.

[1088] Input: Sales dataset, weather information data, event information data

[1089] Output: Unified dataset

[1090] Step 5:

[1091] The server then inputs the integrated data into a generative AI model that is pre-trained and uses statistical methods and machine learning algorithms to forecast product demand.

[1092] Input: Unified dataset

[1093] Output: Demand forecast result data

[1094] Step 6:

[1095] The server determines the optimal order quantity based on the demand forecast results, and uses a decision algorithm to calculate the order quantity of the product according to the forecasted demand.

[1096] Input: Demand forecast result data

[1097] Output: Order quantity determination data

[1098] Step 7:

[1099] The server generates an order instruction and notifies the user terminal of the order instruction, which includes the specific product name and quantity.

[1100] Input: Order quantity determination data

[1101] Output: Purchase order data

[1102] Step 8:

[1103] The terminal displays the order command received from the server on its screen, and the order information is displayed in a format that is easy for the user to understand.

[1104] Input: Purchase order data

[1105] Output: Order information displayed on the user's terminal

[1106] Step 9:

[1107] The user checks the order information displayed on the terminal and makes any necessary corrections. Prompts are displayed to assist the user in making corrections. For example, it is possible to change a 500ml order of tea from 400 bottles to 500 bottles.

[1108] Input: User modifications

[1109] Output: Corrected order information

[1110] Step 10:

[1111] The user finally confirms the revised order information by pressing the Confirm button, which sends the final order information to the server.

[1112] Enter: Confirmed order information

[1113] Output: Sends the final order information to the server

[1114] Step 11:

[1115] The server sends the final confirmed order information to the warehouse or supplier to complete the order processing.

[1116] Input: Final Order Information

[1117] Output: Send purchase order information to warehouse or supplier

[1118] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1119] ---

[1120] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information at stores such as convenience stores, and automatically determines the optimal ordering timing and order quantity, thereby improving ordering accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[1121] Server Processing

[1122] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to perform product demand forecasting. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[1123] Terminal handling

[1124] The terminal displays the order instructions received from the server on its screen. The user (store employee) can check the order details displayed on the terminal and make any necessary corrections. In addition, the emotion engine collects the user's emotional data and evaluates the user's stress level and emotional state. This information is also sent to the server as part of the demand forecast.

[1125] User operations

[1126] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. For example, if it is determined that the demand for tea is higher than expected, the order quantity can be increased manually. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[1127] Emotion engine processing

[1128] The emotion engine collects emotional data in real time when users confirm or modify order information. This emotional data is extracted from the user's facial expressions, voice, operation speed, etc. The emotion engine uses the collected data to evaluate the user's stress level and emotional state, and sends the evaluation results to the server. The server incorporates this emotional data into the demand forecasting model to improve the accuracy of the forecast.

[1129] Specific examples

[1130] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[1131] 1. Server

[1132] Retrieve sales data from the POS system up to August 14th.

[1133] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[1134] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[1135] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[1136] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1137] 2. Terminal

[1138] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[1139] The emotion engine analyzes the user's facial expressions, voice, etc. in real time to assess their stress level and emotional state.

[1140] 3. Users

[1141] The user checks the order details displayed on the terminal.

[1142] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[1143] After correction, the emotion engine records the user's reaction and sends it to the server.

[1144] Confirm the order information and press the Confirm button.

[1145] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[1146] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits. In addition, by utilizing user emotion data, further improvements in ordering accuracy can be expected.

[1147] ---

[1148] The processing flow will be explained below.

[1149] ---

[1150] Step 1:

[1151] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[1152] Step 2:

[1153] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[1154] Step 3:

[1155] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[1156] Step 4:

[1157] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[1158] Step 5:

[1159] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[1160] Step 6:

[1161] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[1162] Step 7:

[1163] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[1164] Step 8:

[1165] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[1166] Step 9:

[1167] The user checks the order information displayed on the terminal, and the emotion engine analyzes the user's facial expressions, voice, and operation speed in real time to collect emotional data.

[1168] Step 10:

[1169] Check whether the order quantity confirmed by the user is appropriate and make corrections if necessary. For example, if it is determined that an order of 500 bottles of 500ml tea is insufficient, manually correct it to 600 bottles.

[1170] Step 11:

[1171] The user confirms the order information, and the emotion engine evaluates the user's stress level and emotional state and sends the data to the server.

[1172] Step 12:

[1173] The server sends an order instruction to the warehouse or supplier based on the final order information including the emotion data.

[1174] Step 13:

[1175] Once confirmation is sent from the warehouse or supplier, the server receives it and notifies the user terminal, thereby completing the order process.

[1176] ---

[1177] Example 2

[1178] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1179] Conventional demand forecasting systems make predictions based on sales data, weather information, and local event information, but because they do not take into account non-numerical factors such as users' emotions and stress levels, they have problems with low demand forecast accuracy and inefficient inventory management and ordering.In addition, because they ignore users' stress and emotions when adjusting order quantities, they place a heavy burden on the work and a high risk of incorrect ordering.

[1180] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for predicting demand from the integrated data, means for determining the order quantity based on the demand forecast result, means for generating an order instruction and notifying the terminal, means for displaying the order instruction received by the terminal, means for the user to confirm and correct the order information, means for collecting and evaluating user emotion data, means for reflecting the evaluation result in the demand forecast, and means for finalizing the order information and sending it to the warehouse or supplier. This enables highly accurate demand forecasting that takes user emotion data into account and efficient order management.

[1181] "Sales data" is data obtained from a sales system that indicates the sales performance of a product during a specific period.

[1182] "Weather information" is information about a specific region and time period, including weather conditions such as temperature, chance of precipitation, and wind speed.

[1183] "Regional event information" is information about the date, time, location, and content of an event held in a specific region.

[1184] "Integrated data" is centralized data that combines sales data, weather information, and local event information.

[1185] "Preprocessing" refers to processing performed on acquired data, such as filling in missing values, removing outliers, and normalizing the data.

[1186] "Demand forecasting" refers to the use of integrated data to predict future demand for a product.

[1187] The "order quantity" is the quantity of the product to be purchased, determined based on the demand forecast.

[1188] An "order command" is a command indicating the determined order quantity, and is notified to the terminal.

[1189] A "terminal" is an electronic device that receives order orders and displays information to a user.

[1190] "User" refers to a person, such as a store employee, who operates the system and checks and modifies order information.

[1191] "Emotion data" is data that indicates the user's emotional state, extracted from the user's facial expression, tone of voice, operation speed, and the like.

[1192] The "evaluation result" is an evaluation index of the user's stress level and emotional state derived from the emotion data.

[1193] A "warehouse" is a facility where product inventory is stored.

[1194] "Supplier" refers to the supplier or manufacturer that provides the goods.

[1195] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines optimal order quantities and timing, improving prediction accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[1196] The server obtains sales data from the POS system. To do this, for example, the sales data collection device requests sales data for a specific period using API communication and receives it in JSON format. As a specific example, a request to the POS system is made as follows: GET / sales?start_date=2023-08-01&end_date=2023-08-14.

[1197] Next, the server retrieves weather information using a weather forecast API. For example, the API request uses the format GET / weather?location=tokyo&date=2023-08-15. The retrieved weather information includes data such as temperature, probability of precipitation, and wind speed.

[1198] The server then uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The response includes the event name, location, start time, and end time.

[1199] The acquired sales data, weather information, and local event information are centralized and treated as integrated data. This integrated data is then preprocessed. Preprocessing includes filling in missing values, removing outliers, and normalizing the data. This improves the quality of the data.

[1200] The server inputs the preprocessed integrated data into a generative AI model, such as Google Cloud's "AI Platform Prediction." The generative AI model performs demand forecasting based on a prompt, such as, "Please predict tomorrow's product demand based on today's sales data, weather information, and local event information. Please provide detailed information on demand for 500ml of tea and ice cream."

[1201] Based on the demand forecast results, the server determines the optimal order quantity. For example, it generates an order to order 500 bottles of 500ml tea and 300 ice creams. The order is notified to the terminal.

[1202] The terminal displays the ordering instructions received from the server on its screen. Specifically, for example, information such as "500 bottles of 500ml tea" and "300 ice creams" is displayed to the user on a tablet. The user can check this information and modify it as necessary.

[1203] The device is equipped with an emotion engine that uses Microsoft's Azure Emotion API to collect user emotion data, which is extracted from the user's facial expressions, tone of voice, and operation speed, and analyzed in real time.

[1204] The user checks the order information displayed on the terminal and modifies the order quantity if necessary. For example, the user can change the predicted order quantity of ice cream to 350. The emotion engine records the modifications made by the user and their emotional state at the time, and sends them to the server.

[1205] Finally, once the user has finalized the order information, it is sent to the server, which then sends it to the warehouse or supplier to complete the order process.

[1206] This will enable highly accurate demand forecasting and efficient order management that takes into account user emotional data. Utilizing emotional data will also reduce user stress and significantly reduce the risk of incorrect orders.

[1207] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1208] Step 1:

[1209] The server obtains sales data from the POS system. Specifically, it requests sales data for a specific period via API communication and receives it in JSON format. For example, a request is made in the format GET / sales?start_date=2023-08-01&end_date=2023-08-14. The input is an API request with a specified period, and the output is sales data for the specified period. Data processing includes normalization and missing value completion.

[1210] Step 2:

[1211] The server obtains weather information using the weather forecast API. Using the API key, it makes a request in the format GET / weather?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is weather information such as temperature, precipitation probability, and wind speed. The server converts this data into the required format and performs preprocessing.

[1212] Step 3:

[1213] The server uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is event information such as the event name, location, start time, and end time. The server organizes and preprocesses the acquired event information.

[1214] Step 4:

[1215] The server integrates sales data, weather information, and local event information to generate a unified dataset. The input is the various data that has been acquired and preprocessed up to that point, and the output is the integrated data. Data processing includes filling in missing values, removing outliers, and normalizing the data. For example, data frames are manipulated using the Python Pandas library.

[1216] Step 5:

[1217] The server inputs the integrated data into a generative AI model (for example, Google Cloud's "AI Platform Prediction") and performs demand forecasting. The input is the integrated dataset, and the output is a supply and demand forecast for each product. The prompt used is, "Based on today's sales data, weather information, and local event information, please predict tomorrow's product demand. Please tell me in detail the demand for 500ml of tea and ice cream in particular."

[1218] Step 6:

[1219] The server determines the optimal order quantity based on the results of the demand forecast. The input is the demand forecast result, and the output is an order command. For example, it generates a command to order 500 bottles of 500ml tea and 300 ice creams. The server converts this command data into JSON format and notifies the terminal.

[1220] Step 7:

[1221] The terminal displays the ordering command received from the server on its screen. The input is the ordering command sent from the server, and the output is the ordering information displayed on the terminal screen. For example, "500ml tea: 500 bottles" and "300 ice creams" are displayed on the tablet.

[1222] Step 8:

[1223] The user checks the order information displayed on the terminal and modifies it as necessary. The input is the order information displayed on the screen, and the output is the order information modified by the user. For example, the user can modify the order quantity to 350 ice creams.

[1224] Step 9:

[1225] The device uses an emotion engine (for example, Microsoft's "Azure Emotion API") to collect and evaluate the user's emotional data. The input is the user's facial expression, tone of voice, operation speed, etc., and the output is an evaluation of the user's stress level and emotional state. The evaluation results are sent from the device to a server.

[1226] Step 10:

[1227] The server reflects the user's emotional data and the revised order information in the demand forecasting model and performs a new forecast. The input is the user's emotional data and the revised order information, and the output is the revised demand forecast result. This allows the final order quantity to be reevaluated.

[1228] Step 11:

[1229] The user finally confirms the order information and presses the "Confirm" button on the terminal. The input is the confirmation instruction by the user's operation, and the output is the confirmed order information.

[1230] Step 12:

[1231] The server then sends the confirmed order information to the warehouse or supplier to complete the order processing. The input is the confirmed order information, and the output is the status of delivery preparation or supply instruction. This ensures the smooth running of the product supply chain.

[1232] (Application example 2)

[1233] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1234] Conventional product demand forecasting and order management systems for convenience stores and other retailers use sales data, weather information, local event information, and other data to perform automated demand forecasting. However, these systems still sometimes result in incorrect orders, which impacts the work environment and mental stress of users (store employees). Furthermore, the process of checking and correcting demand forecast results is cumbersome, requiring more efficient work. Furthermore, there is a lack of means to visually check order information in real time using wearable devices. The problem that this invention aims to solve is to provide a system that solves these problems and allows users to intuitively and efficiently perform demand forecasting and order management.

[1235] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1236] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, and means for acquiring local event information. This allows the server to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order instructions and notifying a user terminal, means for displaying the order instructions received on the user terminal, means for the user to confirm and modify order information, means for finalizing order information and sending it to a warehouse or supplier, means for collecting emotional data and evaluating the emotional state, means for incorporating the emotional data into demand forecasting to improve order accuracy, and means for using a wearable device for the user to visually check order information displayed in real time. This allows the user to intuitively and efficiently perform demand forecasting and order management, improve order accuracy, reduce the user's workload, and improve the work environment.

[1237] "Sales data" is data that records the sales performance of each product in a store.

[1238] "Weather information" is data related to weather conditions and is information used to predict demand for stores.

[1239] "Regional event information" is data related to events held in the target region.

[1240] "Integrated data" refers to data that integrates sales data, weather information, and local event information.

[1241] "Demand forecasting" refers to predicting future demand for a product based on integrated data.

[1242] An "order command" is a command that specifies the order quantity determined based on the demand forecast results.

[1243] A "user terminal" is a device operated by a user, which displays order instructions and allows modification and confirmation of orders.

[1244] "Emotion data" refers to data relating to the emotional state of a user extracted from facial expressions, voice, and the like.

[1245] "Emotional state" is an evaluation that indicates the user's emotional state, and includes stress level, satisfaction level, and the like.

[1246] A "wearable device" is a device worn by a user, such as smart glasses.

[1247] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines the optimal order timing and order quantity. This system allows users to intuitively and efficiently perform demand forecasting and order management. It also uses a wearable device that allows users to visually check order information displayed in real time.

[1248] Program Generation

[1249] The server is configured as follows:

[1250] 1. The means of obtaining sales data is connected to a POS system, which has the function of automatically collecting daily sales data.

[1251] 2. To obtain weather information, use an online weather forecast API (e.g., OpenWeatherMap API) to obtain the necessary weather information.

[1252] 3. To obtain local event information, use a local event calendar API (e.g., Google Calendar API) to collect information on events occurring in the area.

[1253] The means for integrating and preprocessing this data is integrated with a database system to clean the data and standardize the format. The means for predicting demand from the integrated data is to use a generative AI model using TensorFlow or PyTorch to perform demand forecasting. The means for determining order quantities based on the demand forecast results is an algorithm that calculates the optimal order quantity from the prediction results of the AI ​​model.

[1254] The means of collecting emotional data and evaluating emotional states are to use sensors built into smart glasses and wearable devices, as well as the Affectiva SDK and Microsoft Azure's Emotion API, to collect and evaluate emotional data from the user's facial expressions and voice in real time. By incorporating the results of this evaluation into demand forecasts, the accuracy of ordering can be improved.

[1255] The system notifies the user terminal of the order order and allows the user to confirm and modify it by displaying the order information in real time on the display of smart glasses (e.g., HoloLens or Google Glass). The user can confirm the displayed order details and modify them as necessary. The final order information is automatically sent to the server and transmitted to the warehouse or supplier.

[1256] Specific examples

[1257] For example, a demand forecast is made for a store in an urban area on August 15th based on sales data, weather information, and local event information. Based on sales data obtained from the POS system, high temperature forecasts obtained from a weather forecast API, and information about local summer festivals, it is predicted that demand for 500ml of tea and ice cream will increase. The generative AI model generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1258] Users wear smart glasses and check order information in real time. The emotion engine detects the user's stress level from their facial expressions and can automatically adjust the order quantity if the stress level is high. If the user wants to manually increase the order quantity, they can make the adjustment through the smart glasses and the information is sent back to the server.

[1259] Prompt Sentence Examples

[1260] "Use the smart glasses to check the order quantity for 500ml of tea and manually adjust it based on demand forecast and emotion data. The emotion engine will detect stress levels from facial expressions and optimize the ordering process as needed."

[1261] This improves ordering accuracy, reduces the user's workload, and enables efficient inventory management. Utilizing user emotion data also enables more detailed demand forecasts, contributing to increased store profits.

[1262] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1263] Step 1:

[1264] The server retrieves sales data from the POS system. This sales data includes sales records for each product and is used as information necessary for the next demand forecast. Specifically, the most recent sales data is extracted from the database using a query.

[1265] Step 2:

[1266] The server retrieves weather information from an online weather forecast API (e.g., OpenWeatherMap API). The retrieved information includes temperature, probability of precipitation, humidity, etc., and combines this information with sales data to input into the next forecast model. The weather data retrieved from the API is parsed in JSON format, and the necessary information is extracted.

[1267] Step 3:

[1268] The server retrieves local event information from a local event calendar API (e.g., Google Calendar API). It collects information such as the event type, date, time, and location, and combines this with sales data and weather information. The event information is also retrieved in JSON format, and the necessary data is extracted by parsing it.

[1269] Step 4:

[1270] The server combines sales data, weather information, and local event information, and performs preprocessing. It normalizes the data, removes outliers, and standardizes formats to create a combined dataset that is ready to be input into the AI ​​model.

[1271] Step 5:

[1272] The server inputs the integrated data into a generative AI model (using, for example, TensorFlow or PyTorch) to perform demand forecasting. The AI ​​model predicts product demand from the integrated data and outputs the results. Specifically, a regression analysis is performed using a neural network, and the predicted sales volume for each product is output.

[1273] Step 6:

[1274] The server determines the optimal order quantity based on the demand forecast results. This order quantity is calculated taking into account forecast sales volume and inventory information, and is generated as an order instruction. The algorithm adjusts the order quantity so that the optimal inventory level is maintained.

[1275] Step 7:

[1276] The server notifies the user terminal of the generated order command. The order command includes the product type, order quantity, delivery date, etc., and is sent to the user terminal. The notification is sent in real time via a cloud service.

[1277] Step 8:

[1278] The user terminal displays the order instruction received from the server. The order information is displayed on the display of the smart glasses or wearable device, and the user confirms it. The UI is designed to display the order details in a format that is easy to visually confirm.

[1279] Step 9:

[1280] The user can check the order information displayed on the device and make any necessary changes. If necessary, the user can change the order quantity through the smart glasses interface. During this process, the emotion engine analyzes the user's facial expressions and voice to collect emotional data such as stress level.

[1281] Step 10:

[1282] The user terminal sends the final confirmed order information to the server, which then forwards the received confirmed order information to the warehouse or supplier and completes the actual order processing. This ensures that the appropriate quantity of products is ordered at the appropriate time.

[1283] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1284] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1285] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1286] [Fourth embodiment]

[1287] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1288] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1289] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1290] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1291] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1292] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1293] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1294] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1295] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1296] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1297] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1298] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1299] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1300] ---

[1301] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[1302] Server Processing

[1303] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to predict product demand. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[1304] Terminal handling

[1305] The terminal displays the order instructions received from the server on its screen. The user (store employee) checks the order details displayed on the terminal and can make corrections if necessary. For example, if it is determined that demand for tea is higher than expected, the amount to be ordered can be manually increased.

[1306] User operations

[1307] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[1308] Specific examples

[1309] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[1310] 1. Server

[1311] Retrieve sales data from the POS system up to August 14th.

[1312] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[1313] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[1314] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[1315] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1316] 2. Terminal

[1317] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[1318] 3. Users

[1319] The user checks the order details displayed on the terminal.

[1320] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[1321] After making corrections, confirm the order information and press the Confirm button.

[1322] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[1323] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits.

[1324] ---

[1325] The processing flow will be explained below.

[1326] ---

[1327] Step 1:

[1328] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[1329] Step 2:

[1330] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[1331] Step 3:

[1332] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[1333] Step 4:

[1334] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[1335] Step 5:

[1336] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[1337] Step 6:

[1338] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[1339] Step 7:

[1340] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[1341] Step 8:

[1342] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[1343] Step 9:

[1344] The user checks the order information displayed on the terminal, checks whether the displayed order quantity is appropriate, and takes into account the stock situation to prevent unnecessary ordering mistakes.

[1345] Step 10:

[1346] The user can adjust the order quantity as needed. For example, if it is determined that 500 bottles of 500ml tea is not enough, the user can manually adjust the order quantity to 600 bottles.

[1347] Step 11:

[1348] After the user confirms and modifies the order information, they press the button on the terminal to confirm the order, which finalizes the order information.

[1349] Step 12:

[1350] The terminal sends the finalized order information to the server, which receives the final order information and sends an order instruction to the warehouse or supplier.

[1351] Step 13:

[1352] The server receives confirmation from the warehouse or supplier and notifies the user terminal that the order has been accepted, thereby completing the ordering process.

[1353] ---

[1354] Example 1

[1355] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1356] Traditionally, product demand forecasting and ordering in stores relied primarily on experience and intuition, often lacking in accuracy. Furthermore, manually collecting and integrating data from multiple sources required time and effort, making it inefficient. This often led to problems such as inventory shortages and excess inventory, making optimal inventory management and efficient ordering difficult.

[1357] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1358] In this invention, the server includes a means for acquiring sales data, a means for acquiring weather information, and a means for acquiring local event information. This enables accurate demand forecasting by automatically collecting and integrating data from multiple data sources and using a generative AI model. Furthermore, the server includes a means for determining optimal order quantities based on the demand forecast results, generating order orders, and notifying the terminal. This allows store employees to efficiently perform ordering tasks, preventing inventory shortages and excess inventory, reducing food waste, and improving store profits. Furthermore, a system is constructed in which users can use their terminals to confirm and modify order information, finalize the order information, and send it to the server, ensuring that the final order details are accurately reflected.

[1359] ---

[1360] ---

[1361] "Sales data" is a record of merchandise sales in a store, and includes information such as sales quantity, sales date and time, and merchandise category.

[1362] "Weather information" is data relating to weather conditions, and is weather forecast data including information such as temperature, precipitation, humidity, and wind speed.

[1363] "Regional event information" is data relating to events held in a specific region, including information such as the date and time of the event, the venue, the content of the event, and the expected number of participants.

[1364] "Integrated data" is data that combines sales data, weather information, and local event information into a single dataset, and these data are linked together and organized into a processable format.

[1365] A "generative AI model" is a model that uses machine learning algorithms to learn patterns from data and predict future demand.

[1366] An "order command" is a command that specifies the order quantity and timing of a specific product based on predicted demand.

[1367] A "user terminal" is a device used by a store employee to receive, display, and modify order instructions.

[1368] "Supply source" refers to the warehouse or supplier responsible for supplying the goods, and is the party to which the goods are delivered upon receipt of an order.

[1369] "Confirmation and modification" refers to the operation in which the user checks the order information displayed on the terminal and changes the contents as necessary.

[1370] "Final order information" refers to the final order details confirmed after confirmation and correction by the user.

[1371] ---

[1372] The above are definitions of important words included in the scope of the patent claims.

[1373] ---

[1374] This invention is a system that predicts product demand based on sales data, weather information, and local event information at convenience stores and other stores, and automatically determines the optimal order timing and order quantity. This system is composed of a server, terminals, and users.

[1375] Server Processing

[1376] The server first obtains sales data from the POS system. To do this, the server automatically accesses the POS system at a specific time (for example, 1:00 AM every day) and downloads all sales data from the previous day. Next, it obtains weather information using a weather forecast API. In this process, the server sends a request to the weather forecast API at 2:00 AM to obtain real-time weather information. The server also references a local event calendar to obtain information about events in the vicinity of the store. Specifically, the server accesses a website that provides event information at 3:00 AM and scrapes information about nearby events.

[1377] After collecting this data, the server integrates and preprocesses sales data, weather information, and local event information. The integrated data is processed by standardizing different data formats, filtering unnecessary data, and imputing missing values. The preprocessed data is then input into a generative AI model to forecast product demand. The generative AI model uses machine learning algorithms to learn patterns from the data and predict future demand with high accuracy.

[1378] Based on the results of the demand forecast, the server determines the optimal order quantity and generates an order command. The generated order command includes a specific product name and order quantity, such as "500 bottles of 500ml tea" or "300 ice creams." This order command is notified to the terminal.

[1379] Terminal handling

[1380] The terminal displays the ordering instructions received from the server on its screen. Terminals are devices used by store employees, and include tablets and desktop PCs. The terminal receives an ordering instruction from the server at 6:00 AM and displays an order such as "500 bottles of 500ml tea" or "300 ice creams" on its screen.

[1381] User operations

[1382] The user checks the order information displayed on the terminal. Specifically, the user can check each item and its order quantity displayed on the screen and make any necessary corrections. For example, if the user wants to add 50 more ice creams to the predicted order quantity, they can correct it to 350 on the terminal.

[1383] After making the corrections, the user confirms the order information and sends it to the server. When the user presses the "Confirm" button, the corrected order information is sent from the terminal to the server. The server receives the final order information and sends it to the supply source (warehouse or supplier) to complete the order processing.

[1384] Examples and prompts

[1385] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[1386] The server retrieves sales data up to August 14th from the POS system, and determines from weather information retrieved from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. By integrating this data and using a generative AI model to perform a demand forecast, it predicts that demand for 500ml tea and ice cream will increase. As a result, an order to order 500 additional 500ml bottles of tea and 300 ice creams is generated and notified to the terminal.

[1387] If the user checks the order on the terminal and corrects the order quantity to 350 ice creams, the final order information is sent to the server by pressing the confirm button. The server sends this information to the supplier and completes the order process.

[1388] Examples of prompts:

[1389] Integrate store sales data, weather information, and local event information to forecast demand at convenience stores in Tokyo on August 15th. Based on the forecast, determine the timing and quantity of orders.

[1390] ---

[1391] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1392] ---

[1393] Step 1: Obtaining sales data

[1394] The server obtains sales data from the POS system.

[1395] Input: The server sends a request to the POS system's API.

[1396] Data processing: The previous day's sales data is sent in response to the request.

[1397] Output: The previous day's sales data is saved in JSON format on the server.

[1398] Specific operation: The server accesses the POS system at 1:00 AM every day and downloads all sales data from the previous day.

[1399] Step 2: Get weather information

[1400] The server retrieves weather information from an online weather forecast API.

[1401] Input: The server sends a request to the weather API.

[1402] Data processing: Analyze the data returned from the weather forecast API and extract the necessary parts.

[1403] Output: The weather information for the day is saved in JSON format on the server.

[1404] Specific operation: The server sends a request to the weather forecast API at 2 AM to obtain real-time weather information.

[1405] Step 3: Get local event information

[1406] The server obtains event information from a local event calendar.

[1407] Input: Server accesses a website for local event information.

[1408] Data processing: Using scraping technology to extract event information from web pages.

[1409] Output: Event information is saved to the server in text format.

[1410] What it does: The server scrapes a website that provides event information at 3 AM.

[1411] Step 4: Data integration and preprocessing

[1412] The server integrates the acquired sales data, weather information, and local event information and performs preprocessing.

[1413] Inputs: Sales data, weather information, and event information datasets.

[1414] Data processing: Standardize data formats, filter unnecessary data, and fill in missing values.

[1415] Output: Preprocessed integrated data is generated.

[1416] Specific operation: The server performs the process of unifying different data formats into a single dataset.

[1417] Step 5: Demand forecast

[1418] The server inputs the preprocessed data into a generative AI model to predict product demand.

[1419] Input: Preprocessed integrated data.

[1420] Data Computing: Use generative AI models to forecast demand.

[1421] Output: Demand forecast results, demand quantity for each product.

[1422] Specific operation: The server inputs data into the generated AI model, and the AI ​​outputs the demand forecast results.

[1423] Step 6: Determine order quantity and generate order instructions

[1424] The server determines the optimal order quantity based on the demand forecast results and generates an order instruction.

[1425] Input: Demand forecast results.

[1426] Data calculation: Calculate the order quantity based on the forecast results.

[1427] Output: A purchase order is generated, containing the specific product name and quantity to order.

[1428] Specific operation: The server analyzes the AI's demand forecast results and automatically generates ordering instructions such as "500ml tea: 500 bottles" and "Ice cream: 300 pieces."

[1429] Step 7: View Purchase Orders

[1430] The terminal displays the order instruction received from the server on the screen.

[1431] Input: The purchase order sent by the server.

[1432] Data processing: Converting order orders into a format that is easy to view on the screen.

[1433] Output: The order details are displayed on the display screen.

[1434] Specific operation: The terminal receives an order command from the server at 6:00 a.m. and displays "500ml tea: 500 bottles" and "300 ice creams" on the screen.

[1435] Step 8: Review and correct your order

[1436] The user checks the order information displayed on the terminal and makes corrections as necessary.

[1437] Input: Purchase order displayed on the terminal.

[1438] Data manipulation: The order quantity is modified based on the user's input.

[1439] Output: The modified purchase order.

[1440] Specific operation: The user checks the order details displayed on the screen and corrects the order quantity to, for example, 350 ice creams.

[1441] Step 9: Confirm and submit your order

[1442] The user confirms the corrected order information and transmits it from the terminal to the server.

[1443] Input: Revised purchase order information.

[1444] Data calculation: The order information is finalized.

[1445] Output: The final order information is sent to the server.

[1446] Specific operation: The user presses the "Confirm" button, and the revised order details are sent from the terminal to the server.

[1447] Step 10: Complete the final order process

[1448] The server receives the final order information and transmits it to the source to complete the order process.

[1449] Input: Final order information.

[1450] Data Calculation: Sends final order information to the source system.

[1451] Output: An order is sent to the source of supply.

[1452] Specific operation: The server automatically sends the revised order information to the warehouse management system and arranges for inventory.

[1453] ---

[1454] The above is a description of the specific flow of processing of the system program and the specific operation at each processing step.

[1455] (Application example 1)

[1456] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1457] Determining the appropriate product order quantity for a store requires consideration of multiple factors, including sales data, weather information, and information about local events, making it difficult to predict. In particular, employees often rely on their own experience and intuition, resulting in ordering errors and excessive or insufficient inventory. Furthermore, it is difficult to respond appropriately when sudden fluctuations in demand or unexpected events occur. This can lead to inefficient inventory management, increased food waste, and reduced profits.

[1458] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1459] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for using a generative AI model to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order orders and notifying a user terminal, means for displaying the order orders received on the user terminal, means for the user to confirm and modify order information using prompt text, and means for finalizing order information and sending it to a warehouse or supplier. This improves the accuracy of demand forecasts and enables the determination of appropriate order quantities. Furthermore, users can easily confirm and modify order information using prompt text, enabling quick and accurate ordering.

[1460] "Sales data" refers to data including the quantity of merchandise sold at a store, sales figures by category, and sales trends by date and time.

[1461] "Weather information" refers to meteorological data such as the weather forecast, temperature, precipitation, wind speed, and humidity for a specified area.

[1462] "Regional event information" is information about events such as festivals, sporting events, and exhibitions held in a specified region.

[1463] "Integrated data" is data that combines multiple datasets, such as sales data, weather information, and local event information, into a format that can be processed as a single dataset.

[1464] A "generative AI model" is an artificial intelligence algorithm that is trained to perform a specific task, such as demand forecasting, from a large dataset.

[1465] "Demand forecast result" is a forecast value of future demand calculated by the generative AI model.

[1466] "Order quantity" refers to the amount of each product to be purchased that is determined based on the demand forecast results.

[1467] An "order instruction" is an instruction document that specifies a specific product name and quantity, and is generated based on the determined order amount.

[1468] "User terminal" means an electronic device used by a store employee to receive, display, and modify order instructions.

[1469] "Prompt text" refers to guidelines or instructions that users use when checking or correcting order information.

[1470] "Final order information" refers to the final product order information that has been confirmed after the user has confirmed and corrected it.

[1471] "Warehouse or supplier" refers to the logistics facility or product supplier to which order information is sent.

[1472] This invention is a demand forecasting and optimal ordering system for stores, specifically a system that uses sales data, weather information, and local event information to forecast demand and determine order quantities, thereby improving the efficiency of store inventory management and reducing food waste.

[1473] Server Processing

[1474] The server first obtains sales data from the store's POS system. Next, it obtains weather information online using a weather forecast API, and also collects event information from a local event calendar. Statistical methods and data cleaning techniques are used to integrate and preprocess this data. The server uses a generative AI model based on this integrated data to predict product demand. The optimal order quantity is determined based on the demand forecast results, and an order order is generated.

[1475] Terminal handling

[1476] The terminal displays the order instruction received from the server on the screen. The user, who is a store employee, confirms the order details displayed on the terminal. Prompt statements are used to allow the user to confirm the order information in an easy-to-understand manner. For example, specific items and quantities such as "500ml of tea: 500 bottles" are displayed. If necessary, the user can modify the order quantity. The modified details are quickly recalculated, and the final order information is generated when the user presses the confirm button.

[1477] User operations

[1478] The user checks and modifies the order information displayed on the terminal and finally confirms the order. The confirmed order information is sent back to the server, which then sends it to the warehouse or supplier to complete the order processing.

[1479] Hardware and software used

[1480] Hardware: Servers, user devices (tablets and smartphones)

[1481] Software: Weather forecast API, data cleaning software, generative AI models (e.g., Keras)

[1482] Specific examples

[1483] For example, consider a case study at a convenience store in Tokyo on August 15th. The server retrieves sales data up to August 14th from the POS system, and determines from weather information obtained from a weather forecast API that August 15th will be sunny and hot. It also references a local event calendar and finds that a large summer festival will be held nearby on August 15th. This integrated data is input into an AI model, which predicts an increase in demand for 500ml tea and ice cream. As a result, it generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1484] Prompt Sentence Examples

[1485] Below is an example of an actual prompt sentence.

[1486] 1. Weather information prompts:

[1487] Please enter the weather information for this weekend. Example: Sunny, temperature 30°C

[1488] 2. Event information related prompts:

[1489] Enter local event information. Example: Summer festival, 1000 people

[1490] 3. Sales data related prompts:

[1491] Please enter the sales data for the most recent week in CSV format.

[1492] This reduces the workload of employees while enabling accurate demand forecasting and efficient inventory management, reducing food waste and improving store profits.

[1493] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1494] Step 1:

[1495] The server retrieves sales data from the store's POS system. Specifically, it connects to the database and uses a query to extract sales data from the past few days. This allows data to be obtained that can be used to understand the sales trends of products in the store.

[1496] Input: Sales data from POS system

[1497] Output: Extracted sales dataset

[1498] Step 2:

[1499] The server retrieves weather information from a weather forecast API, which includes meteorological data such as weather, temperature, and precipitation for a specific region. It sends a request to the API endpoint and analyzes the data received in response. This allows it to obtain weather information that affects product demand.

[1500] Input: Weather forecast API request information (location, date and time, etc.)

[1501] Output: Obtained weather information data

[1502] Step 3:

[1503] The server collects event information from the local event calendar and stores it in a database, allowing it to consider the impact of local events on product demand.

[1504] Input: Events calendar URL or API endpoint

[1505] Output: Captured event information data

[1506] Step 4:

[1507] The server integrates sales data, weather information, and event information, performs preprocessing, cleans the data, and converts it into a format suitable for AI models by properly handling missing values ​​and outliers.

[1508] Input: Sales dataset, weather information data, event information data

[1509] Output: Unified dataset

[1510] Step 5:

[1511] The server then inputs the integrated data into a generative AI model that is pre-trained and uses statistical methods and machine learning algorithms to forecast product demand.

[1512] Input: Unified dataset

[1513] Output: Demand forecast result data

[1514] Step 6:

[1515] The server determines the optimal order quantity based on the demand forecast results, and uses a decision algorithm to calculate the order quantity of the product according to the forecasted demand.

[1516] Input: Demand forecast result data

[1517] Output: Order quantity determination data

[1518] Step 7:

[1519] The server generates an order instruction and notifies the user terminal of the order instruction, which includes the specific product name and quantity.

[1520] Input: Order quantity determination data

[1521] Output: Purchase order data

[1522] Step 8:

[1523] The terminal displays the order command received from the server on its screen, and the order information is displayed in a format that is easy for the user to understand.

[1524] Input: Purchase order data

[1525] Output: Order information displayed on the user's terminal

[1526] Step 9:

[1527] The user checks the order information displayed on the terminal and makes any necessary corrections. Prompts are displayed to assist the user in making corrections. For example, it is possible to change a 500ml order of tea from 400 bottles to 500 bottles.

[1528] Input: User modifications

[1529] Output: Corrected order information

[1530] Step 10:

[1531] The user finally confirms the revised order information by pressing the Confirm button, which sends the final order information to the server.

[1532] Enter: Confirmed order information

[1533] Output: Sends the final order information to the server

[1534] Step 11:

[1535] The server sends the final confirmed order information to the warehouse or supplier to complete the order processing.

[1536] Input: Final Order Information

[1537] Output: Send purchase order information to warehouse or supplier

[1538] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1539] ---

[1540] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information at stores such as convenience stores, and automatically determines the optimal ordering timing and order quantity, thereby improving ordering accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[1541] Server Processing

[1542] The server first obtains sales data from the POS system. Next, it obtains weather information from an online weather forecast API and event information from a local event calendar. It then integrates and pre-processes these data. The server then inputs the integrated data into an AI model to perform product demand forecasting. Based on the results of the demand forecast, it determines the optimal order quantity and generates an order instruction.

[1543] Terminal handling

[1544] The terminal displays the order instructions received from the server on its screen. The user (store employee) can check the order details displayed on the terminal and make any necessary corrections. In addition, the emotion engine collects the user's emotional data and evaluates the user's stress level and emotional state. This information is also sent to the server as part of the demand forecast.

[1545] User operations

[1546] The user confirms and modifies the order information displayed on the terminal and finally confirms the order. For example, if it is determined that the demand for tea is higher than expected, the order quantity can be increased manually. This confirmed order information is sent back to the server, which then sends the final order information to the warehouse or supplier to complete the order process.

[1547] Emotion engine processing

[1548] The emotion engine collects emotional data in real time when users confirm or modify order information. This emotional data is extracted from the user's facial expressions, voice, operation speed, etc. The emotion engine uses the collected data to evaluate the user's stress level and emotional state, and sends the evaluation results to the server. The server incorporates this emotional data into the demand forecasting model to improve the accuracy of the forecast.

[1549] Specific examples

[1550] For example, here is an example of this at a convenience store in Tokyo on August 15th.

[1551] 1. Server

[1552] Retrieve sales data from the POS system up to August 14th.

[1553] Using weather information obtained from the weather forecast API, we know that August 15th will be sunny and the temperature will be high.

[1554] Check the local events calendar to see if there's a big summer festival happening nearby on August 15th.

[1555] It integrates sales data, weather information, and event information, and feeds this data into an AI model to predict product demand.

[1556] As a result of the demand forecast, it is predicted that the demand for 500ml tea and ice cream will increase, so an order is generated to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1557] 2. Terminal

[1558] The terminal receives an order command from the server and displays "500ml tea: 500 bottles" and "Ice cream: 300 pieces" on the screen.

[1559] The emotion engine analyzes the user's facial expressions, voice, etc. in real time to assess their stress level and emotional state.

[1560] 3. Users

[1561] The user checks the order details displayed on the terminal.

[1562] For example, if you want to increase the predicted order quantity of ice cream by another 50 units, you can manually change it to 350 units.

[1563] After correction, the emotion engine records the user's reaction and sends it to the server.

[1564] Confirm the order information and press the Confirm button.

[1565] The confirmed order information is sent to the server, which then sends it to the warehouse or supplier to complete the order processing.

[1566] In this way, by implementing the present invention, accurate demand forecasting and efficient inventory management become possible while reducing the workload of employees, thereby reducing food waste and improving store profits. In addition, by utilizing user emotion data, further improvements in ordering accuracy can be expected.

[1567] ---

[1568] The processing flow will be explained below.

[1569] ---

[1570] Step 1:

[1571] The server periodically obtains sales data from the POS system, including information such as the date and time of product sales, the quantity sold, and the type of product.

[1572] Step 2:

[1573] The server retrieves weather information from an online weather forecast API, including the weather, temperature, and precipitation for a specific day.

[1574] Step 3:

[1575] The server refers to a local event calendar and acquires information about events held in the surrounding area, including the event name, date and time, location, expected number of participants, etc.

[1576] Step 4:

[1577] The server integrates the acquired sales data, weather information, and local event information, and performs pre-processing on the data. Specifically, it associates each data set based on its date and time, and prepares it in an analyzable format.

[1578] Step 5:

[1579] The server uses the pre-processed integrated data to input data into an AI model to perform product demand forecasting, which predicts demand for specific products based on past data and current external data.

[1580] Step 6:

[1581] The server calculates the optimal order quantity based on the demand forecast. For example, if the forecast shows that 500 bottles of 500ml tea and 300 ice creams are needed, the server determines the order quantity.

[1582] Step 7:

[1583] The server generates an order command based on the calculated order quantity and sends it to the user terminal at the store. This order command includes the product name and quantity to be ordered.

[1584] Step 8:

[1585] The terminal displays the order instruction received from the server on its screen, including the product name, order quantity, and other related information.

[1586] Step 9:

[1587] The user checks the order information displayed on the terminal, and the emotion engine analyzes the user's facial expressions, voice, and operation speed in real time to collect emotional data.

[1588] Step 10:

[1589] Check whether the order quantity confirmed by the user is appropriate and make corrections if necessary. For example, if it is determined that an order of 500 bottles of 500ml tea is insufficient, manually correct it to 600 bottles.

[1590] Step 11:

[1591] The user confirms the order information, and the emotion engine evaluates the user's stress level and emotional state and sends the data to the server.

[1592] Step 12:

[1593] The server sends an order instruction to the warehouse or supplier based on the final order information including the emotion data.

[1594] Step 13:

[1595] Once confirmation is sent from the warehouse or supplier, the server receives it and notifies the user terminal, thereby completing the order process.

[1596] ---

[1597] Example 2

[1598] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1599] Conventional demand forecasting systems make predictions based on sales data, weather information, and local event information, but because they do not take into account non-numerical factors such as users' emotions and stress levels, they have problems with low demand forecast accuracy and inefficient inventory management and ordering.In addition, because they ignore users' stress and emotions when adjusting order quantities, they place a heavy burden on the work and a high risk of incorrect ordering.

[1600] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for acquiring sales data, means for acquiring weather information, means for acquiring local event information, means for integrating and preprocessing the acquired data, means for predicting demand from the integrated data, means for determining the order quantity based on the demand forecast result, means for generating an order instruction and notifying the terminal, means for displaying the order instruction received by the terminal, means for the user to confirm and correct the order information, means for collecting and evaluating user emotion data, means for reflecting the evaluation result in the demand forecast, and means for finalizing the order information and sending it to the warehouse or supplier. This enables highly accurate demand forecasting that takes user emotion data into account and efficient order management.

[1601] "Sales data" is data obtained from a sales system that indicates the sales performance of a product during a specific period.

[1602] "Weather information" is information about a specific region and time period, including weather conditions such as temperature, chance of precipitation, and wind speed.

[1603] "Regional event information" is information about the date, time, location, and content of an event held in a specific region.

[1604] "Integrated data" is centralized data that combines sales data, weather information, and local event information.

[1605] "Preprocessing" refers to processing performed on acquired data, such as filling in missing values, removing outliers, and normalizing the data.

[1606] "Demand forecasting" refers to the use of integrated data to predict future demand for a product.

[1607] The "order quantity" is the quantity of the product to be purchased, determined based on the demand forecast.

[1608] An "order command" is a command indicating the determined order quantity, and is notified to the terminal.

[1609] A "terminal" is an electronic device that receives order orders and displays information to a user.

[1610] "User" refers to a person, such as a store employee, who operates the system and checks and modifies order information.

[1611] "Emotion data" is data that indicates the user's emotional state, extracted from the user's facial expression, tone of voice, operation speed, and the like.

[1612] The "evaluation result" is an evaluation index of the user's stress level and emotional state derived from the emotion data.

[1613] A "warehouse" is a facility where product inventory is stored.

[1614] "Supplier" refers to the supplier or manufacturer that provides the goods.

[1615] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines optimal order quantities and timing, improving prediction accuracy and work efficiency by reflecting user emotions. This system is composed of a server, terminals, users, and an emotion engine.

[1616] The server obtains sales data from the POS system. To do this, for example, the sales data collection device requests sales data for a specific period using API communication and receives it in JSON format. As a specific example, a request to the POS system is made as follows: GET / sales?start_date=2023-08-01&end_date=2023-08-14.

[1617] Next, the server retrieves weather information using a weather forecast API. For example, the API request uses the format GET / weather?location=tokyo&date=2023-08-15. The retrieved weather information includes data such as temperature, probability of precipitation, and wind speed.

[1618] The server then uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The response includes the event name, location, start time, and end time.

[1619] The acquired sales data, weather information, and local event information are centralized and treated as integrated data. This integrated data is then preprocessed. Preprocessing includes filling in missing values, removing outliers, and normalizing the data. This improves the quality of the data.

[1620] The server inputs the preprocessed integrated data into a generative AI model, such as Google Cloud's "AI Platform Prediction." The generative AI model performs demand forecasting based on a prompt, such as, "Please predict tomorrow's product demand based on today's sales data, weather information, and local event information. Please provide detailed information on demand for 500ml of tea and ice cream."

[1621] Based on the demand forecast results, the server determines the optimal order quantity. For example, it generates an order to order 500 bottles of 500ml tea and 300 ice creams. The order is notified to the terminal.

[1622] The terminal displays the ordering instructions received from the server on its screen. Specifically, for example, information such as "500 bottles of 500ml tea" and "300 ice creams" is displayed to the user on a tablet. The user can check this information and modify it as necessary.

[1623] The device is equipped with an emotion engine that uses Microsoft's Azure Emotion API to collect user emotion data, which is extracted from the user's facial expressions, tone of voice, and operation speed, and analyzed in real time.

[1624] The user checks the order information displayed on the terminal and modifies the order quantity if necessary. For example, the user can change the predicted order quantity of ice cream to 350. The emotion engine records the modifications made by the user and their emotional state at the time, and sends them to the server.

[1625] Finally, once the user has finalized the order information, it is sent to the server, which then sends it to the warehouse or supplier to complete the order process.

[1626] This will enable highly accurate demand forecasting and efficient order management that takes into account user emotional data. Utilizing emotional data will also reduce user stress and significantly reduce the risk of incorrect orders.

[1627] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1628] Step 1:

[1629] The server obtains sales data from the POS system. Specifically, it requests sales data for a specific period via API communication and receives it in JSON format. For example, a request is made in the format GET / sales?start_date=2023-08-01&end_date=2023-08-14. The input is an API request with a specified period, and the output is sales data for the specified period. Data processing includes normalization and missing value completion.

[1630] Step 2:

[1631] The server obtains weather information using the weather forecast API. Using the API key, it makes a request in the format GET / weather?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is weather information such as temperature, precipitation probability, and wind speed. The server converts this data into the required format and performs preprocessing.

[1632] Step 3:

[1633] The server uses the local event calendar API to collect local event information. For example, a request is made in the format GET / events?location=tokyo&date=2023-08-15. The input is an API request specifying the region and date, and the output is event information such as the event name, location, start time, and end time. The server organizes and preprocesses the acquired event information.

[1634] Step 4:

[1635] The server integrates sales data, weather information, and local event information to generate a unified dataset. The input is the various data that has been acquired and preprocessed up to that point, and the output is the integrated data. Data processing includes filling in missing values, removing outliers, and normalizing the data. For example, data frames are manipulated using the Python Pandas library.

[1636] Step 5:

[1637] The server inputs the integrated data into a generative AI model (for example, Google Cloud's "AI Platform Prediction") and performs demand forecasting. The input is the integrated dataset, and the output is a supply and demand forecast for each product. The prompt used is, "Based on today's sales data, weather information, and local event information, please predict tomorrow's product demand. Please tell me in detail the demand for 500ml of tea and ice cream in particular."

[1638] Step 6:

[1639] The server determines the optimal order quantity based on the results of the demand forecast. The input is the demand forecast result, and the output is an order command. For example, it generates a command to order 500 bottles of 500ml tea and 300 ice creams. The server converts this command data into JSON format and notifies the terminal.

[1640] Step 7:

[1641] The terminal displays the ordering command received from the server on its screen. The input is the ordering command sent from the server, and the output is the ordering information displayed on the terminal screen. For example, "500ml tea: 500 bottles" and "300 ice creams" are displayed on the tablet.

[1642] Step 8:

[1643] The user checks the order information displayed on the terminal and modifies it as necessary. The input is the order information displayed on the screen, and the output is the order information modified by the user. For example, the user can modify the order quantity to 350 ice creams.

[1644] Step 9:

[1645] The device uses an emotion engine (for example, Microsoft's "Azure Emotion API") to collect and evaluate the user's emotional data. The input is the user's facial expression, tone of voice, operation speed, etc., and the output is an evaluation of the user's stress level and emotional state. The evaluation results are sent from the device to a server.

[1646] Step 10:

[1647] The server reflects the user's emotional data and the revised order information in the demand forecasting model and performs a new forecast. The input is the user's emotional data and the revised order information, and the output is the revised demand forecast result. This allows the final order quantity to be reevaluated.

[1648] Step 11:

[1649] The user finally confirms the order information and presses the "Confirm" button on the terminal. The input is the confirmation instruction by the user's operation, and the output is the confirmed order information.

[1650] Step 12:

[1651] The server then sends the confirmed order information to the warehouse or supplier to complete the order processing. The input is the confirmed order information, and the output is the status of delivery preparation or supply instruction. This ensures the smooth running of the product supply chain.

[1652] (Application example 2)

[1653] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1654] Conventional product demand forecasting and order management systems for convenience stores and other retailers use sales data, weather information, local event information, and other data to perform automated demand forecasting. However, these systems still sometimes result in incorrect orders, which impacts the work environment and mental stress of users (store employees). Furthermore, the process of checking and correcting demand forecast results is cumbersome, requiring more efficient work. Furthermore, there is a lack of means to visually check order information in real time using wearable devices. The problem that this invention aims to solve is to provide a system that solves these problems and allows users to intuitively and efficiently perform demand forecasting and order management.

[1655] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1656] In this invention, the server includes means for acquiring sales data, means for acquiring weather information, and means for acquiring local event information. This allows the server to forecast demand from the integrated data, means for determining order quantities based on the demand forecast results, means for generating order instructions and notifying a user terminal, means for displaying the order instructions received on the user terminal, means for the user to confirm and modify order information, means for finalizing order information and sending it to a warehouse or supplier, means for collecting emotional data and evaluating the emotional state, means for incorporating the emotional data into demand forecasting to improve order accuracy, and means for using a wearable device for the user to visually check order information displayed in real time. This allows the user to intuitively and efficiently perform demand forecasting and order management, improve order accuracy, reduce the user's workload, and improve the work environment.

[1657] "Sales data" is data that records the sales performance of each product in a store.

[1658] "Weather information" is data related to weather conditions and is information used to predict demand for stores.

[1659] "Regional event information" is data related to events held in the target region.

[1660] "Integrated data" refers to data that integrates sales data, weather information, and local event information.

[1661] "Demand forecasting" refers to predicting future demand for a product based on integrated data.

[1662] An "order command" is a command that specifies the order quantity determined based on the demand forecast results.

[1663] A "user terminal" is a device operated by a user, which displays order instructions and allows modification and confirmation of orders.

[1664] "Emotion data" refers to data relating to the emotional state of a user extracted from facial expressions, voice, and the like.

[1665] "Emotional state" is an evaluation that indicates the user's emotional state, and includes stress level, satisfaction level, and the like.

[1666] A "wearable device" is a device worn by a user, such as smart glasses.

[1667] This invention combines an emotion engine with a system that predicts product demand based on sales data, weather information, and local event information, and determines the optimal order timing and order quantity. This system allows users to intuitively and efficiently perform demand forecasting and order management. It also uses a wearable device that allows users to visually check order information displayed in real time.

[1668] Program Generation

[1669] The server is configured as follows:

[1670] 1. The means of obtaining sales data is connected to a POS system, which has the function of automatically collecting daily sales data.

[1671] 2. To obtain weather information, use an online weather forecast API (e.g., OpenWeatherMap API) to obtain the necessary weather information.

[1672] 3. To obtain local event information, use a local event calendar API (e.g., Google Calendar API) to collect information on events occurring in the area.

[1673] The means for integrating and preprocessing this data is integrated with a database system to clean the data and standardize the format. The means for predicting demand from the integrated data is to use a generative AI model using TensorFlow or PyTorch to perform demand forecasting. The means for determining order quantities based on the demand forecast results is an algorithm that calculates the optimal order quantity from the prediction results of the AI ​​model.

[1674] The means of collecting emotional data and evaluating emotional states are to use sensors built into smart glasses and wearable devices, as well as the Affectiva SDK and Microsoft Azure's Emotion API, to collect and evaluate emotional data from the user's facial expressions and voice in real time. By incorporating the results of this evaluation into demand forecasts, the accuracy of ordering can be improved.

[1675] The system notifies the user terminal of the order order and allows the user to confirm and modify it by displaying the order information in real time on the display of smart glasses (e.g., HoloLens or Google Glass). The user can confirm the displayed order details and modify them as necessary. The final order information is automatically sent to the server and transmitted to the warehouse or supplier.

[1676] Specific examples

[1677] For example, a demand forecast is made for a store in an urban area on August 15th based on sales data, weather information, and local event information. Based on sales data obtained from the POS system, high temperature forecasts obtained from a weather forecast API, and information about local summer festivals, it is predicted that demand for 500ml of tea and ice cream will increase. The generative AI model generates an order to order an additional 500 bottles of 500ml tea and 300 ice creams.

[1678] Users wear smart glasses and check order information in real time. The emotion engine detects the user's stress level from their facial expressions and can automatically adjust the order quantity if the stress level is high. If the user wants to manually increase the order quantity, they can make the adjustment through the smart glasses and the information is sent back to the server.

[1679] Prompt Sentence Examples

[1680] "Use the smart glasses to check the order quantity for 500ml of tea and manually adjust it based on demand forecast and emotion data. The emotion engine will detect stress levels from facial expressions and optimize the ordering process as needed."

[1681] This improves ordering accuracy, reduces the user's workload, and enables efficient inventory management. Utilizing user emotion data also enables more detailed demand forecasts, contributing to increased store profits.

[1682] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1683] Step 1:

[1684] The server retrieves sales data from the POS system. This sales data includes sales records for each product and is used as information necessary for the next demand forecast. Specifically, the most recent sales data is extracted from the database using a query.

[1685] Step 2:

[1686] The server retrieves weather information from an online weather forecast API (e.g., OpenWeatherMap API). The retrieved information includes temperature, probability of precipitation, humidity, etc., and combines this information with sales data to input into the next forecast model. The weather data retrieved from the API is parsed in JSON format, and the necessary information is extracted.

[1687] Step 3:

[1688] The server retrieves local event information from a local event calendar API (e.g., Google Calendar API). It collects information such as the event type, date, time, and location, and combines this with sales data and weather information. The event information is also retrieved in JSON format, and the necessary data is extracted by parsing it.

[1689] Step 4:

[1690] The server combines sales data, weather information, and local event information, and performs preprocessing. It normalizes the data, removes outliers, and standardizes formats to create a combined dataset that is ready to be input into the AI ​​model.

[1691] Step 5:

[1692] The server inputs the integrated data into a generative AI model (using, for example, TensorFlow or PyTorch) to perform demand forecasting. The AI ​​model predicts product demand from the integrated data and outputs the results. Specifically, a regression analysis is performed using a neural network, and the predicted sales volume for each product is output.

[1693] Step 6:

[1694] The server determines the optimal order quantity based on the demand forecast results. This order quantity is calculated taking into account forecast sales volume and inventory information, and is generated as an order instruction. The algorithm adjusts the order quantity so that the optimal inventory level is maintained.

[1695] Step 7:

[1696] The server notifies the user terminal of the generated order command. The order command includes the product type, order quantity, delivery date, etc., and is sent to the user terminal. The notification is sent in real time via a cloud service.

[1697] Step 8:

[1698] The user terminal displays the order instruction received from the server. The order information is displayed on the display of the smart glasses or wearable device, and the user confirms it. The UI is designed to display the order details in a format that is easy to visually confirm.

[1699] Step 9:

[1700] The user can check the order information displayed on the device and make any necessary changes. If necessary, the user can change the order quantity through the smart glasses interface. During this process, the emotion engine analyzes the user's facial expressions and voice to collect emotional data such as stress level.

[1701] Step 10:

[1702] The user terminal sends the final confirmed order information to the server, which then forwards the received confirmed order information to the warehouse or supplier and completes the actual order processing. This ensures that the appropriate quantity of products is ordered at the appropriate time.

[1703] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1704] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1705] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1706] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1707] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1708] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1709] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1710] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1711] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1712] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1713] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1714] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1715] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1716] 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.

[1717] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1718] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1719] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1720] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1721] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1722] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1723] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1724] The following is further disclosed regarding the above embodiment.

[1725] ---

[1726] (Claim 1)

[1727] A means of obtaining sales data;

[1728] A means for obtaining weather information;

[1729] A means for obtaining local event information;

[1730] a means for integrating and pre-processing the acquired data;

[1731] A means of forecasting demand from integrated data;

[1732] A means for determining an order quantity based on the demand forecast result;

[1733] means for generating an order instruction and notifying the user terminal;

[1734] means for displaying the received order instruction at the user terminal;

[1735] A means for users to review and modify order information;

[1736] A means for finalizing and transmitting final purchase order information to the warehouse or supplier;

[1737] A system including:

[1738] (Claim 2)

[1739] 2. The system according to claim 1, further comprising means for acquiring the sales data from a POS system.

[1740] (Claim 3)

[1741] 10. The system of claim 1, further comprising: means for obtaining the weather information from an online API.

[1742] "Example 1"

[1743] ---

[1744] (Claim 1)

[1745] A means of obtaining sales data;

[1746] A means for obtaining weather information;

[1747] A means for obtaining local event information;

[1748] a means for integrating and pre-processing the acquired data;

[1749] Using generative AI models to predict demand from integrated data; and

[1750] A means for determining an order quantity based on the demand forecast result;

[1751] means for generating an order instruction and notifying the terminal;

[1752] means for displaying the received order instruction at the terminal;

[1753] A means for users to review and modify order information;

[1754] means for determining and transmitting final order information to the source;

[1755] A system including:

[1756] (Claim 2)

[1757] 2. The system according to claim 1, further comprising means for acquiring the sales data from a POS system.

[1758] (Claim 3)

[1759] 10. The system of claim 1, further comprising: means for obtaining the weather information from an online API.

[1760] (Claim 4)

[1761] The system of claim 1, further comprising means for integrating sales data, weather information, and local event information and inputting the information into a generative AI model to forecast the demand.

[1762] (Claim 5)

[1763] 2. The system according to claim 1, further comprising means for allowing a user to confirm and modify order information using a terminal, and to transmit final order information to the server after confirmation.

[1764] ---

[1765] The above is the content of adding the characteristic parts of the system to the claims.

[1766] "Application Example 1"

[1767] (Claim 1)

[1768] A means of obtaining sales data;

[1769] A means for obtaining weather information;

[1770] A means for obtaining local event information;

[1771] a means for integrating and pre-processing the acquired data;

[1772] a means of using generative AI models to forecast demand from the integrated data; and

[1773] A means for determining an order quantity based on the demand forecast result;

[1774] means for generating an order instruction and notifying the user terminal;

[1775] means for displaying the received order instruction at the user terminal;

[1776] A means for the user to confirm and modify order information using prompt statements;

[1777] A means for finalizing and transmitting final purchase order information to the warehouse or supplier;

[1778] A system including:

[1779] (Claim 2)

[1780] 2. The system according to claim 1, further comprising means for acquiring the sales data from a POS system.

[1781] (Claim 3)

[1782] 10. The system of claim 1, further comprising: means for obtaining the weather information from an online API.

[1783] "Example 2: Combining Emotion Engines"

[1784] (Claim 1)

[1785] A means of obtaining sales data;

[1786] A means for obtaining weather information;

[1787] A means for obtaining local event information;

[1788] a means for integrating and pre-processing the acquired data;

[1789] A means of forecasting demand from integrated data;

[1790] A means for determining an order quantity based on the demand forecast result;

[1791] means for generating an order instruction and notifying the terminal;

[1792] means for displaying the received order instruction at the terminal;

[1793] A means for users to review and modify order information;

[1794] means for collecting and evaluating user emotion data;

[1795] A means for reflecting the evaluation results in demand forecasts;

[1796] a means for determining and transmitting final order information to a warehouse or supplier;

[1797] A system including:

[1798] (Claim 2)

[1799] 10. The system of claim 1, further comprising: means for obtaining the sales data from a sales data collection device.

[1800] (Claim 3)

[1801] 2. The system according to claim 1, further comprising means for obtaining the weather information via the Internet.

[1802] "Application example 2 when combining emotion engines"

[1803] (Claim 1)

[1804] A means of obtaining sales data;

[1805] A means for obtaining weather information;

[1806] A means for obtaining local event information;

[1807] a means for integrating and pre-processing the acquired data;

[1808] A means of forecasting demand from integrated data;

[1809] A means for determining an order quantity based on the demand forecast result;

[1810] means for generating an order instruction and notifying the user terminal;

[1811] means for displaying the received order instruction at the user terminal;

[1812] A means for users to review and modify order information;

[1813] A means for finalizing and transmitting final purchase order information to the warehouse or supplier;

[1814] a means for collecting emotional data and assessing emotional states;

[1815] A means to incorporate this emotional data into demand forecasting to improve the accuracy of orders, and

[1816] A means for using a wearable device to allow the user to visually check the order information displayed in real time;

[1817] A system including:

[1818] (Claim 2)

[1819] 2. The system according to claim 1, further comprising means for acquiring the sales data from a POS system.

[1820] (Claim 3)

[1821] 10. The system of claim 1, further comprising: means for obtaining the weather information from an online API. [Explanation of symbols]

[1822] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of obtaining sales data; A means for obtaining weather information; A means for obtaining local event information; a means for integrating and pre-processing the acquired data; A means of forecasting demand from integrated data; A means for determining an order quantity based on the demand forecast result; means for generating an order instruction and notifying the user terminal; means for displaying the received order instruction at the user terminal; A means for users to review and modify order information; A means for finalizing and transmitting final purchase order information to the warehouse or supplier; A system including:

2. 2. The system according to claim 1, further comprising means for acquiring said sales data from a POS system.

3. The system of claim 1 , further comprising: means for obtaining the weather information from an online API.

Images