System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting a storage situation of a distribution center, the number of stocks, a securing situation of a driver, and a road situation and weather on a delivery day; means for performing learning using a generation model on the basis of the collected information and calculating an optimal price for each desired delivery date of a product; means for transmitting the calculated price information to a terminal and enabling a user to check and select a price for each desired delivery date; and means for receiving a price and order information for a selected desired delivery date and performing order processing.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] In today's logistics industry, labor shortages and declining operational efficiency, predicted as problems in 2024, are becoming serious issues. In addition, it is difficult to balance customer delivery dates with logistics efficiency, which could result in lower customer satisfaction. Furthermore, there is a need for appropriate pricing that ensures a healthy working environment and improves productivity while maintaining a certain level of logistics efficiency. Because conventional systems have had difficulty effectively addressing these issues, a new system that can solve them is needed. [Means for solving the problem]

[0005] This invention is a system that includes a means for collecting information on warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery at a logistics center; a means for learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; a means for transmitting the calculated price information to a terminal so that users can confirm and select the price for each desired delivery date; and a means for receiving the price and order information for the selected desired delivery date and processing the order. Furthermore, this system effectively solves the problem by including a means for performing preprocessing to remove outliers and imputing missing data, and a means for the generative model to learn pricing patterns based on the information collected from the logistics center. This makes it possible to improve customer satisfaction and realize a healthy working environment while maintaining a certain level of logistics efficiency.

[0006] A "logistics center" is a facility that stores, organizes, and ships goods, and functions as a logistics hub.

[0007] "Storage conditions" refers to environmental data within the logistics center (temperature, humidity, product placement, etc.) and the current progress of work.

[0008] "Inventory quantity" refers to the quantity of each product stored in the logistics center.

[0009] "Driver availability status" refers to information related to drivers, such as the number of drivers performing delivery duties and shift status.

[0010] "Road conditions on the day of delivery" refers to traffic conditions, road congestion, road construction information, etc. on the day of delivery.

[0011] "Weather" refers to the current weather and forecast, including, among other things, that affect the date of delivery.

[0012] A "generative model" is an algorithm that uses machine learning and artificial intelligence techniques to learn from data and make predictions and classifications.

[0013] "Optimal price" refers to a price calculated based on collected data that maximizes inventory turnover and delivery efficiency while increasing customer satisfaction.

[0014] "Terminal" refers to a device used by a user, such as a computer, smartphone, or tablet, that functions as an interface with the system.

[0015] "Preprocessing" refers to the process of cleansing and completing collected data, and includes procedures to prepare the data so that the generative model can learn effectively.

[0016] "Missing data" refers to collected data that has not been recorded for some reason.

[0017] "Pricing patterns" refer to the criteria and rules for setting optimal prices depending on the situation that the generative model has discovered through learning. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is a dynamic pricing system that addresses the 2024 problem in the logistics industry by using a generative model to calculate the optimal price for each desired delivery date based on information such as the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and allowing users to select a delivery date.

[0040] 1. Server Processing

[0041] The server first collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0042] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0043] 2. Terminal Processing

[0044] When a user selects a product they wish to purchase using a device (smartphone, tablet, PC, etc.), the device sends a request to the server. In response to the request, the server sends price information for the selected product for each desired delivery date to the device. The device displays this information to the user, allowing them to select the desired delivery date. For example, for product A, the device presents price information such as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[0045] 3. User Operation

[0046] The user uses the terminal to select the product they wish to purchase and then select the desired delivery date. They confirm the displayed price, specify the payment method, and confirm the order. For example, if a user requests delivery of product A in one week, agrees to the price of 1,100 yen, and proceeds with the purchase, the order data is sent from the terminal to the server.

[0047] 4. Processing after order confirmation

[0048] The server verifies the received order data and checks the validity of the order (including inventory confirmation, payment confirmation, and driver availability). Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment and arrange for delivery. For example, if there is sufficient stock of product A and a driver is available, the logistics center will prepare the product and deliver it to the specified address one week later.

[0049] Specific examples

[0050] As a specific scenario, consider the following case.

[0051] 1. When inventory is abundant and traffic is smooth: The server collects data from the logistics center and determines that inventory is abundant and road conditions are good. The generative model sets prices based on this information, for example, "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." The user selects a product through their terminal, requests delivery one week later, and pays 800 yen.

[0052] 2. When inventory is low and traffic is congested: The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the price is confirmed by paying 1,500 yen, and the server sends this information to the logistics center.

[0053] In this way, logistics efficiency can be optimized while customer satisfaction can be increased.

[0054] The processing flow will be explained below.

[0055] Step 1:

[0056] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[0057] Step 2:

[0058] The server performs preprocessing on the collected information, removing outliers and filling in missing data. For example, it filters out abnormal values ​​from a temperature sensor and fills in missing data with the historical average.

[0059] Step 3:

[0060] The server inputs the preprocessed data into a generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[0061] Step 4:

[0062] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[0063] Step 5:

[0064] The server stores the calculated price information in a database and makes it available for user reference.

[0065] Step 6:

[0066] The terminal provides an interface for the user to select the product they wish to purchase, and when the user selects a product, it sends a request for information about that product to the server.

[0067] Step 7:

[0068] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[0069] Step 8:

[0070] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[0071] Step 9:

[0072] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[0073] Step 10:

[0074] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[0075] Step 11:

[0076] The server verifies the received order information, stores it in a database, and checks the validity of the order (including stock availability, payment confirmation, driver availability, etc.).

[0077] Step 12:

[0078] The server then sends the confirmed order details to the relevant departments at the logistics center to prepare for shipment and arrange for delivery. The logistics center then prepares the products based on the received information and delivers them on the specified date.

[0079] In this way, the server, terminal, and user play their respective roles at each step, realizing a system that efficiently collects data, processes data, learns data, sets prices, confirms orders, and delivers data.

[0080] Example 1

[0081] 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."

[0082] In recent years, efficient delivery management and improved customer satisfaction have become important issues in the logistics industry. However, conventional systems have had difficulty in setting prices in real time based on daily changes in inventory, road conditions, and weather. This has led to problems such as inability to set optimal prices, making it difficult to efficiently manage inventory and minimize delivery costs. In addition, customers have limited options for selecting an appropriate price based on their desired delivery date, limiting the improvement of customer satisfaction.

[0083] 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.

[0084] In this invention, the server includes a means for collecting information on the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of transportation, and weather information, a means for preprocessing the collected information to remove outliers and fill in missing data, and a means for performing learning using a generative model based on the preprocessed information to calculate the optimal price for each desired delivery date of the product. This enables optimal pricing according to conditions that change daily, minimizes inventory management and delivery costs, and provides customers with the option to purchase products at the optimal price according to their desired delivery date.

[0085] "Conditions within the logistics center" refers to environmental conditions within the logistics center, such as temperature, humidity, and storage space utilization, as well as the current state of operations within the warehouse.

[0086] "Inventory" refers to the total number and type of products stored in a particular warehouse or distribution center.

[0087] "Driver availability" refers to whether drivers for delivery work have been reliably arranged and their operating status.

[0088] "Traffic conditions on the day of transportation" refers to the degree of road congestion and traffic conditions on the day the goods are transported.

[0089] "Weather information" refers to information about the weather on the day of transportation and before and after, such as rainfall, snowfall, wind speed, temperature, etc.

[0090] "Means of collection" refers collectively to sensors used to obtain necessary data from logistics centers and external sources, as well as software and hardware for accessing databases.

[0091] "Preprocessing means" refers to a method and device in general for removing outliers and filling in missing data from collected data, preparing the data for subsequent analysis and learning.

[0092] "Outlier removal" refers to the process of eliminating obviously abnormal values ​​from collected data, such as physically impossible temperature or humidity data.

[0093] "Missing data imputation" refers to the process of filling in missing values ​​in collected data, for example, using past data or average values.

[0094] A "generative model" is an AI model that learns patterns based on collected and preprocessed data and generates appropriate outputs in response to new inputs.

[0095] "Optimal price" refers to the most economically efficient price set according to the desired delivery date of the product, based on customer demand and the logistics provider's supply conditions.

[0096] "Means for calculating" refers collectively to algorithms and computer software for calculating optimal prices using generative models.

[0097] "Terminal" refers to an electronic device that can connect to the Internet, such as a smartphone, tablet, or personal computer used by a user.

[0098] "User" refers to an individual or corporation that uses the System to purchase products and use delivery services.

[0099] "Order processing" refers to a series of processes based on a purchase request received from a user, from checking inventory to confirming payment and completing delivery arrangements.

[0100] The present invention relates to a dynamic pricing system for the logistics industry. This system aims to improve logistics efficiency and customer satisfaction by collecting variable factors, particularly the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of delivery, and weather information, in real time and setting optimal delivery prices based on the collected data.

[0101] 1. Data Collection

[0102] The server collects data in real time from various sensors and management systems within the logistics center. This data includes the warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Specifically, the central management server periodically obtains JSON-formatted data from each sensor, and uses it to manage, for example, temperature sensors, humidity sensors, inventory management systems, and driver management systems.

[0103] 2. Data Preprocessing

[0104] The server preprocesses the collected data, removing outliers and filling in missing data. For example, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), it will remove them, and missing inventory data will be filled in with the average inventory level from the past.

[0105] 3. Generative pricing

[0106] The server inputs the preprocessed data into a generative model (e.g., OpenAI GPT-4). The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. For example, the model compares prices with past days when inventory was low and sets a new price based on similar patterns. This set price is then stored in a database.

[0107] 4. Processing User Requests

[0108] When a user opens a specific product page, the device sends a request to the server. The request includes a product ID, and when a user displays the page for product A on their smartphone, the product ID is sent to the server.

[0109] 5. Price information for desired delivery date

[0110] The server receives the request sent from the device and retrieves the price information for the corresponding product for each desired delivery date from the database. The price information is sent to the device in JSON format. For example, data such as "next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen" is sent.

[0111] 6. User Purchase Process

[0112] The user checks the price information displayed on the device, selects the desired delivery date, and then selects a payment method to proceed with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card.

[0113] 7. Order confirmation and confirmation

[0114] The server verifies the purchase request received from the user, checks the product inventory, payment confirmation, and driver availability. For example, it retrieves the product inventory from the inventory database and confirms payment via the payment gateway.

[0115] 8. Arrangements after order confirmation

[0116] After the server confirms the order, it notifies the relevant departments at the logistics center. The logistics center then prepares shipment and arranges delivery based on the received information. For example, it sends picking instructions for product A to the warehouse system and updates the schedule to arrange for a driver.

[0117] Specific examples

[0118] Let's say a user wants to purchase Product A. In this case, when the user opens the page for Product A on their smartphone, the device sends Product A's ID to the server. The server retrieves price information for that product for each desired delivery date from the database and sends the following data: "Next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen." The user checks this, selects delivery one week later, agrees to the price of 1,100 yen, and proceeds with the purchase. This order request is checked for inventory and payment on the server side, and if there are no problems, a picking instruction is sent to the logistics center and a driver is arranged.

[0119] Prompt Sentence Examples

[0120] "Calculate the optimal price for each desired delivery date based on the following information: warehouse status, inventory quantity, driver availability, road conditions and weather on the delivery day. For example, please provide an example of pricing when inventory is low and road conditions are poor."

[0121] This system will enable us to optimize logistics efficiency while improving customer satisfaction.

[0122] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0123] Step 1: Data collection

[0124] The server automatically collects real-time data from various sensors and management systems within the logistics center. Input data includes warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Data is acquired in JSON format and is obtained specifically from temperature sensors, humidity sensors, inventory management systems, and driver management systems. The output is a raw data set.

[0125] Step 2: Data Preprocessing

[0126] The server performs preprocessing on the collected raw dataset. The raw dataset is input. The preprocessing involves removing outliers and filling in missing data. Specifically, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), that data is removed, and missing inventory data is filled in with the average inventory quantity from the past. As a result of the processing, a clean dataset is output.

[0127] Step 3: Generative pricing

[0128] The server inputs the clean dataset into a generative model (e.g., OpenAI GPT-4). The input is the preprocessed clean dataset. The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. This price is calculated by comparing the model with past low inventory days and prices, and setting a new price based on similar patterns. The output is pricing information for each desired delivery date.

[0129] Step 4: Process the user request

[0130] When a user opens a specific product page, the device sends a product request to the server. The input is a request that includes the product ID. For example, when a user displays the page for product A on a smartphone, the ID of product A is sent to the server. The output is a response to the corresponding product ID request.

[0131] Step 5: Submit price information for desired delivery date

[0132] The server receives the product request sent from the terminal and retrieves price information for the corresponding product for each desired delivery date from the database. The input is the product ID request. The data is sent in JSON format, and price information is sent to the terminal. Specifically, price information is provided in the form of "next day delivery: 1,500 yen," "3-day delivery: 1,300 yen," and "1 week later delivery: 1,100 yen."

[0133] Step 6: User checkout

[0134] The user checks the price information displayed on the terminal and selects the desired delivery date. The price information displayed on the terminal and the selected delivery date are input. The user then selects a payment method and proceeds with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card. The purchase request is sent to the server, and a purchase confirmation response is output.

[0135] Step 7: Order confirmation and confirmation

[0136] The server verifies the purchase request received from the user. The input is a purchase request. The server checks the product's inventory, payment confirmation, and driver availability. Specifically, it retrieves the product's inventory from the inventory database and confirms payment via the payment gateway. Once the order is confirmed, it is notified to the logistics center, and a final order confirmation response is output.

[0137] Step 8: Arrangements after order confirmation

[0138] After the server confirms the order, it notifies the relevant departments at the logistics center of the information. The confirmed order information is input. The logistics center prepares for shipment and arranges delivery based on the received information. Specifically, it sends a picking instruction for product A to the warehouse system and updates the schedule to arrange for a driver. The output is a notification that shipment preparation is complete and delivery information.

[0139] In this way, logistics operations are carried out efficiently and effectively.

[0140] (Application example 1)

[0141] 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."

[0142] The logistics industry is seeking more efficient inventory management and delivery scheduling. Real-time management is particularly important, taking into account not only warehouse conditions and inventory levels, but also driver availability, road conditions, weather, and other fluctuating factors. However, this information is not centrally managed, creating problems for staff who are unable to respond efficiently. Additionally, a system is needed that allows users to check and select prices for each desired delivery date, but current methods are insufficient.

[0143] 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.

[0144] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for sending the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for displaying information in real time within the logistics center using smart glasses to improve staff work efficiency. This makes it possible to build a system that improves the efficiency of inventory management and delivery operations within the logistics center and allows users to check the optimal price in real time.

[0145] A "logistics center" is a facility that serves as a base for storing and distributing goods.

[0146] "Warehouse status" refers to information about the current state, layout, and inventory distribution within the logistics center.

[0147] "Stock quantity" is a numerical value indicating the quantity of products stored in the logistics center.

[0148] "Driver availability" refers to the number of drivers performing delivery duties at the logistics center and their schedules.

[0149] "Road conditions" refers to information such as traffic volume and congestion on roads used as delivery routes.

[0150] "Weather" refers to the weather forecast and weather conditions on the day of delivery.

[0151] A "generative model" is a type of machine learning model that is trained to derive optimal results based on specified data.

[0152] "Optimal price" refers to the most reasonable price for the desired delivery date calculated by the generative model based on the collected data.

[0153] A "terminal" is a device that allows a user to input and check information, and specifically includes smartphones, tablets, and PCs.

[0154] "Smart glasses" are a wearable eyeglass-type device that has the ability to display information on a screen in real time.

[0155] "Users" refers to people who use the system, including general consumers and logistics center staff.

[0156] "Order processing" refers to receiving order information from a user and completing a series of procedures such as checking inventory, confirming payment, and arranging delivery.

[0157] This invention will be described as an example of application in a logistics center management system using smart glasses.

[0158] Overall system configuration

[0159] The system collects information such as warehouse conditions at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and uses a generative model to calculate the optimal price for each desired delivery date. This information is presented to staff in the logistics center in real time using smart glasses. The system also allows users to check and select prices for each desired delivery date, and processes orders.

[0160] Server Processing

[0161] The server collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0162] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0163] Smart Glasses Processing

[0164] The smart glasses are worn by staff in the distribution center and receive and display the information they need in real time while they work. Information such as collected inventory levels, driver availability, prices for each desired delivery date, road conditions, and weather is visually displayed through a HUD (head-up display). This allows staff to work efficiently while moving around the warehouse.

[0165] For example, a staff member checking an inventory list can use smart glasses to check the stock levels of each product in real time and make necessary replenishments or rearrangements. They can also instantly check the latest information on drivers scheduled for delivery and road conditions, enabling quick decision-making.

[0166] Hardware and software used

[0167] Hardware: Smart glasses such as Epson Moverio and Vuzix Blade.

[0168] Software: API communication library (requests) and HUD display library for smart glasses.

[0169] Specific examples

[0170] For example, the following scenario can occur within a logistics center:

[0171] Staff checking the inventory list can instantly check information such as "Quantity in stock: 150," "Driver availability: stable," and "Delivery price: 1,200 yen" through the smart glasses, dramatically improving work efficiency.

[0172] Prompt Sentence Examples

[0173] "A method of using smart glasses to manage inventory and deliveries within a distribution center. The glasses display real-time inventory levels, driver availability, pricing information for each desired delivery date, and road and weather conditions, improving the efficiency of staff work."

[0174] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0175] Step 1:

[0176] The server collects real-time data from various sensors and management systems within the logistics center. This data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected data is input and stored in a database.

[0177] Step 2:

[0178] The server performs preprocessing on the collected data, removing outliers and filling in missing data. For example, it filters out abnormal temperature and humidity values, and fills in missing inventory data with historical average values. The preprocessed data is used as input for the next calculation.

[0179] Step 3:

[0180] The server inputs the preprocessed data into a generative model to learn optimal pricing patterns. The generative model compares past data with the current situation to calculate the optimal price for each desired delivery date for each product. The calculated optimal price is saved as output in a database.

[0181] Step 4:

[0182] The terminal sends a request to the server to obtain price information for each desired delivery date for the product selected by the user. The terminal displays the obtained price information to the user. The user selects a desired delivery date as input and sends that information to the server.

[0183] Step 5:

[0184] The server receives the price and order information for the delivery date selected by the user. Based on the received order information, it carries out a series of order processes, including checking inventory, confirming payment, and securing a driver. Once the order process is complete, it forwards the information to the relevant department.

[0185] Step 6:

[0186] The smart glasses display information collected from the server to the operatives in real time, such as inventory levels, driver availability, delivery prices by desired delivery date, road conditions, and weather, on the HUD. This allows the operatives to work efficiently within the logistics center.

[0187] 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.

[0188] This invention combines an emotion engine with a dynamic pricing system to address labor shortages and declining operational efficiency in the logistics industry and improve customer satisfaction. The system collects data on the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, as well as user emotion data, and uses a generative model to calculate the optimal price for each desired delivery date. It also optimizes prices and desired delivery dates individually based on the user's emotion data and displays personalized marketing messages.

[0189] 1. Server Processing

[0190] First, the server collects data in real time from various sensors and management systems within the logistics center. The collected data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected information is pre-processed to remove outliers and fill in missing data.

[0191] The server also collects emotional data from the user's emotion engine, such as facial expressions, tone of voice, and analysis results of entered text, obtained from the device during user operation. The preprocessed data and emotional data are input into a generative model, which then learns optimal pricing patterns based on past data and the current situation.

[0192] 2. Terminal Processing

[0193] When a user selects a product they wish to purchase using a terminal, the terminal sends a request to the server. The server calculates the price information for each desired delivery date for the selected product and sends it to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[0194] The device also collects real-time emotional data from the user's emotion engine and sends it to the server, which then individually optimizes product prices and desired delivery dates.

[0195] 3. User Operation

[0196] The user uses the device to select a product and a desired delivery date, confirm the displayed price, confirm the order, specify a payment method, and enter the required information. The user's emotions may also be communicated to the system, which may adjust the price and delivery date options accordingly.

[0197] 4. Processing after order confirmation

[0198] The server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order details are confirmed, the relevant information is sent to the logistics center to prepare for shipment. The logistics center prepares the product according to the instructions and delivers it on the specified date. Additionally, personalized marketing messages are displayed to users based on their emotional data.

[0199] Specific examples

[0200] As a specific scenario, consider the following case.

[0201] 1. When inventory is abundant and transportation is smooth:

[0202] The server collects data from the logistics center and determines that there is abundant inventory and road conditions are good. The generative model uses this information to set prices, determining the following: next-day delivery: 1,000 yen, three-day delivery: 900 yen, and one-week delivery: 800 yen. The user selects a product via their device and requests delivery one week later. The emotion engine determines that the user is highly satisfied, and a personalized thank-you message is displayed. The user pays 800 yen and confirms the order.

[0203] 2. When inventory is low and traffic is heavy:

[0204] The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the emotion engine determines that the user is in a hurry, and an immediate delivery service is displayed. The user pays 1,500 yen and confirms the order.

[0205] In this way, by combining the emotion engine, it becomes possible to provide flexible and efficient pricing and delivery options that respond to the user's emotions.

[0206] The processing flow will be explained below.

[0207] Step 1:

[0208] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[0209] Step 2:

[0210] The server preprocesses the collected information, filtering out outliers and filling in missing data. For example, if a temperature sensor in a warehouse reports an abnormal value, the data is filtered out. Missing inventory levels are filled in with the average value from the past.

[0211] Step 3:

[0212] The server inputs the preprocessed data into the generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[0213] Step 4:

[0214] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[0215] Step 5:

[0216] The server collects user emotion data from the emotion engine, which is obtained by facial expression recognition during user operation, tone analysis of voice, and emotion analysis of input text.

[0217] Step 6:

[0218] The server inputs the acquired emotion data into a generative model and further optimizes the price for each desired delivery date of the product based on the user's emotions.

[0219] Step 7:

[0220] The server stores the calculated price information in a database and transmits it to the terminal.

[0221] Step 8:

[0222] The terminal provides an interface for the user to select the product they wish to purchase, and once the user has selected the product, it sends a request for information about that product to the server.

[0223] Step 9:

[0224] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[0225] Step 10:

[0226] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[0227] Step 11:

[0228] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[0229] Step 12:

[0230] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[0231] Step 13:

[0232] The server checks the received order information, confirms inventory, payment, and the validity of driver availability. Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment.

[0233] Step 14:

[0234] The server generates a personalized marketing message according to the user's emotions based on the emotion engine and transmits it to the terminal.

[0235] Step 15:

[0236] The terminal displays the marketing message received from the server to the user. For example, if it is determined that the user is in a hurry, an announcement about an immediate delivery service is displayed.

[0237] Step 16:

[0238] The logistics center will prepare the product based on the received information and deliver it on the specified date.

[0239] In this way, the server, terminal, and user play their respective roles at each step, resulting in a system that efficiently collects, processes, learns, sets prices, confirms orders, and delivers. Furthermore, by collecting and utilizing emotional data, the system aims to provide more personalized services and improve customer satisfaction.

[0240] Example 2

[0241] 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."

[0242] The logistics industry is facing significant challenges due to labor shortages and declining operational efficiency, which are resulting in declining customer satisfaction. Furthermore, traditional pricing systems have difficulty providing personalized prices and delivery schedules that reflect each user's needs and emotions. This results in an unoptimized user experience, which can further worsen customer satisfaction. Therefore, there is a need for a system that collects diverse data in real time and provides optimal pricing and delivery schedules based on user emotions.

[0243] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0244] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for transmitting the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for collecting user emotion data; means for individually optimizing the price and desired delivery date based on the emotion data; and means for receiving the price and order information for the selected desired delivery date and processing the order. This makes it possible to address labor shortages and declining business efficiency and provide flexible and efficient pricing and delivery options that respond to user emotions.

[0245] A "logistics center" is a facility where packages are stored, managed, sorted, and prepared for delivery.

[0246] "Storage conditions" refers to the physical and environmental conditions inside the logistics center, including temperature, humidity, lighting, and storage space.

[0247] "Inventory quantity" refers to the quantity of products, goods, and materials stored in a logistics center.

[0248] "Driver availability" refers to delivery driver staffing, shifts, and the number of available drivers.

[0249] "Road conditions on the day of delivery" refers to the traffic and road conditions on the day that affect the delivery of goods. Specifically, this includes information on traffic congestion and prohibited activities.

[0250] "Weather" means meteorological conditions that affect the planning and execution of a Delivery, including, but not limited to, rain, snow, wind speed, and temperature.

[0251] A "generative model" is an algorithm that learns patterns and predictions from data and generates results for new data inputs.

[0252] "Emotional data" refers to information that indicates the user's emotional state as analyzed from facial expressions, tone of voice, and text.

[0253] "Terminal" refers to the device used by a user to operate the system, including smartphones, tablets, personal computers, etc.

[0254] "User" refers to an individual or organization that uses the system to purchase products and receive delivery services.

[0255] "Optimization" is the process of making adjustments to obtain the most effective and efficient results under given conditions and constraints.

[0256] "Pricing" refers to the process of determining the price of your product offerings, specifically setting prices based on cost, demand, competition, and other market factors.

[0257] "Desired delivery date" refers to the specific date on which the user wishes to receive the product.

[0258] "Order processing" refers to the series of processes that involve accepting an order from a user, communicating it to the logistics center or delivery staff, and then putting it into action.

[0259] This invention is a system for improving labor shortages and declining business efficiency in the logistics industry and improving customer satisfaction. A specific embodiment of the program for this system will be described below.

[0260] Program processing explanation

[0261] Data collection

[0262] The server collects data in real time from various sensors and management systems installed in the logistics center. For example,

[0263] Data on the state of the interior of the warehouse is obtained from temperature and humidity sensors.

[0264] Inventory quantity data is obtained from the inventory management system.

[0265] Driver availability data is obtained from the human resources management system.

[0266] Road condition data on the day of delivery is obtained from the traffic information system.

[0267] Weather data is obtained from weather information services.

[0268] Additionally, the server collects real-time emotional data from the user's device, including facial expressions, tone of voice, and analysis of input text.

[0269] Data Preprocessing

[0270] The server pre-processes the collected data, removing outliers and filling in missing data. For example, it removes inappropriate temperature sensor data and fills in missing inventory data from past data.

[0271] Learning with generative models

[0272] Preprocessed logistics data and sentiment data are input into a generative AI model. The generative model learns optimal pricing patterns based on past data and the current situation. It is preferable to use a multi-layer neural network (DNN) for the generative AI model used.

[0273] Processing user requests

[0274] When a user selects a product to purchase on the terminal, the terminal sends that information to the server. The server calculates the price of the selected product for each desired delivery date and sends that information to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[0275] Optimization and individual adjustment

[0276] The device collects the user's emotions in real time and sends the data to a server, which then individually optimizes the product price and desired delivery date based on the emotion data. For example, if the server determines that the user is in a hurry, it will present an option for immediate delivery and adjust the price.

[0277] Processing after order confirmation

[0278] When a user confirms an order, the server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order is confirmed, the information is sent to the logistics center for shipping preparation. The logistics center prepares the product according to the instructions and delivers it on the specified date. In addition, personalized marketing messages based on emotional data are displayed to the user.

[0279] Specific examples

[0280] For example, if data collected from a logistics center indicates that there is abundant inventory and road conditions are good, the generative model will set prices such as "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." On the other hand, if there is little inventory and road conditions are congested, the model will set prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[0281] In addition, the service is optimized based on the user's emotional data, and if it determines that the user is in a hurry, it will suggest immediate delivery. Such personalized suggestions will improve user satisfaction.

[0282] Prompt Sentence Examples

[0283] Here are some examples of specific prompts:

[0284] "Design a system that collects data from various sensors and management systems in a distribution center and retrieves user sentiment data from an emotion engine. Explain how you can use this data to leverage a generative AI model that learns optimal pricing patterns and provides personalized delivery options to users."

[0285] In this way, through the embodiments of the invention, it is possible to improve customer satisfaction and business efficiency.

[0286] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0287] Step 1:

[0288] The server starts collecting data.

[0289] Input: Data from various sensors in the logistics center, inventory data from the inventory management system, road condition data from the traffic information system, weather data from the weather information service, and driver availability data from the human resources management system.

[0290] Data processing: The server collects these data in real time and stores them in a database.

[0291] Output: A collection of raw data.

[0292] How it works: Every minute, the server automatically pulls sensor data and executes a script to store it in a database. It also periodically calls APIs from inventory management systems, traffic information systems, human resources management systems, and weather information services to collect data.

[0293] Step 2:

[0294] The server pre-processes the data.

[0295] Input: Raw data collected in step 1.

[0296] Data processing: Removal of outliers, imputation of missing data.

[0297] Output: Preprocessed clean data.

[0298] Specific operation: The server runs an algorithm to detect outliers, removes any detected outliers, and performs a filtering process to fill in missing data with predicted values ​​based on similar data from the past.

[0299] Step 3:

[0300] The server inputs data into the generative model and performs learning.

[0301] Input: Preprocessed clean data.

[0302] Data processing: The data input and learning process for generative AI models.

[0303] Output: Optimal pricing pattern.

[0304] How it works: The server feeds the preprocessed data into a generative AI model (a multi-layer neural network), which then learns optimal pricing patterns based on past data and current conditions. The model is periodically retrained to adapt to new data.

[0305] Step 4:

[0306] The terminal sends an input request from the user.

[0307] Input: Product selection information by the user.

[0308] Data processing: Transmission of user-entered information.

[0309] Output: The request data sent to the server.

[0310] Specific operation: The user selects the desired product on the terminal and sends the selection information to the server as a request. This request includes information about the selected product and the user ID.

[0311] Step 5:

[0312] The server calculates the pricing data and sends it to the terminal.

[0313] Input: Request data from users, optimal pricing patterns from the generative model.

[0314] Data processing: Calculate the price for each desired delivery date for the requested item.

[0315] Output: Calculated price information.

[0316] Specific operation: Based on the pricing patterns obtained from the generative model, the server calculates the price for each desired delivery date for the product corresponding to the user's request and sends the price information to the terminal.

[0317] Step 6:

[0318] The device displays the results to the user and collects emotional data in real time.

[0319] Input: Price information sent from the server, user sentiment data.

[0320] Data processing: Displaying price information and collecting sentiment data.

[0321] Output: Displayed price information, collected sentiment data.

[0322] Specific operation: The terminal displays the received price information to the user. In addition, the terminal analyzes the user's facial expressions, tone of voice, and text input, and collects real-time emotional data through the emotion engine. This data is then sent to the server.

[0323] Step 7:

[0324] The server performs optimization and determines the final price and desired delivery date.

[0325] Input: sentiment data, preprocessed logistics data, pricing patterns using a generative model.

[0326] Data processing: Optimizing price and desired delivery date based on sentiment data.

[0327] Output: Final adjusted price information and desired delivery date.

[0328] Specific operation: The server analyzes the emotion data and adjusts the price and desired delivery date based on the user's level of urgency and satisfaction. For example, if a user is in a hurry, it will present the option of same-day delivery and its price.

[0329] Step 8:

[0330] The user selects the desired delivery date and confirms the order.

[0331] Input: The last price information displayed on the device and the desired delivery date.

[0332] Data processing: Sending the user's selected delivery date and price information.

[0333] Output: Confirmed order data.

[0334] Specific operation: The user selects the desired delivery date based on the information displayed on the terminal and finalizes the order. After confirming the order, the user enters the necessary payment information and sends it to the server.

[0335] Step 9:

[0336] The server checks the order information and sends instructions to the logistics center.

[0337] Input: Confirmed order data.

[0338] Data processing: Checking inventory, payment, and driver availability.

[0339] Output: Shipping instruction data to the logistics center.

[0340] Specific operation: The server checks the received order information, checks the validity of the inventory and payment, and if there are no problems, sends instructions to the logistics center to prepare for shipment.

[0341] Step 10:

[0342] The logistics center prepares the products and delivers them on the specified date.

[0343] Input: Shipping instruction data from the server.

[0344] Data processing: Product preparation and delivery planning.

[0345] Output: The delivered item.

[0346] Specific operation: The logistics center prepares the product according to instructions from the server, and delivers the product by a delivery driver on the specified date. It also delivers personalized messages and special offers to users based on their emotional data.

[0347] (Application example 2)

[0348] 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."

[0349] Labor shortages and declining operational efficiency are serious issues in the logistics industry. Furthermore, while there is a demand for flexible service provision that responds to user emotions and individual needs, this has not been fully realized. Therefore, a method is needed to simultaneously achieve efficient management and personalized service provision.

[0350] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and user emotion data and calculating the optimal price for each desired delivery date; means for sending a personalized message based on the calculated price information and emotion data to the terminal so that the user can confirm and select a price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for collecting emotion data and performing emotion analysis in real time. This makes it possible to provide an efficient and personalized delivery service.

[0351] A "logistics center" is a facility that centralizes logistics operations such as storing, sorting, packaging, shipping, and delivering packages.

[0352] "Storage status" is data that indicates the storage status of inventory and the progress of work within the logistics center.

[0353] "Stock quantity" is data indicating the quantity of products stored in the logistics center.

[0354] "Driver availability status" is data that indicates the status and number of drivers available for delivery at the logistics center.

[0355] "Road conditions on the day of delivery" is data indicating road traffic conditions and congestion information on the day of delivery.

[0356] "Weather" is data indicating the weather conditions on the delivery date.

[0357] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, tone of voice, input text, and the like.

[0358] A "generative model" is an algorithm that uses machine learning based on collected data to generate optimal results for new data.

[0359] A "personalized message" is a personalized message created based on the emotional data and past behavior of an individual user.

[0360] A "terminal" is an electronic device that allows a user to obtain information or send instructions.

[0361] "Order information" is data including the product selected by the user, desired delivery date, price, payment method, etc.

[0362] "Emotion analysis" is a process of analyzing the user's emotional state based on collected emotional data.

[0363] This invention aims to build an efficient delivery management system in a logistics center and improve user satisfaction. A specific method for implementing each step will be described below.

[0364] System Configuration

[0365] The present invention uses the following hardware and software:

[0366] Hardware: sensors, servers, smartphones

[0367] Software: Data collection API, sentiment analysis engine, generative model

[0368] Program processing

[0369] Data collection

[0370] The server collects the following data in real time from sensors and management systems within the distribution center:

[0371] Warehouse status

[0372] Quantity in stock

[0373] Driver availability

[0374] Road conditions on the day of delivery

[0375] weather

[0376] The collected data is preprocessed to make it suitable for analysis by removing outliers and filling in missing data. If the device operated by the user is a smartphone, the user's facial expression, tone of voice, and input text are analyzed by an emotion analysis engine to extract emotional data.

[0377] Optimal price calculation using generative models

[0378] The server inputs the pre-processed data and sentiment data into a generative model to determine the optimal price based on past data and the current situation. For example, a Python script like the following can be used:

[0379] python

[0380] import numpy as np

[0381] import pandas as pd

[0382] from datetime import datetime

[0383] import requests

[0384] from sklearn.linear_model import LinearRegression

[0385] Data collection function definition

[0386] def collect_data():

[0387] Sensor data collection

[0388] warehouse_data = requests.get('https: / / api.warehouse.com / data').json()

[0389] Collecting Emotional Data

[0390] emotion_data = requests.get('https: / / api.emotionengine.com / data').json()

[0391] return warehouse_data, emotion_data

[0392] Emotional Data Analysis

[0393] def analyze_emotion(emotion_data):

[0394] Tentative emotion analysis results

[0395] emotion_score = np.mean([item['score'] for item in emotion_data])

[0396] return emotion_score

[0397] Optimal Price Calculation

[0398] def calculate_optimal_price(warehouse_data, emotion_score, delivery_days):

[0399] factors = [warehouse_data['stock_level'], warehouse_data['traffic'],

[0400] warehouse_data['driver_availability'], emotion_score]

[0401] Hypothetical pricing model

[0402] model = LinearRegression()

[0403] X = np.array(factors).reshape(-1, 1)

[0404] y = np.array([1000, 950, 900]) Historical price data

[0405] model.fit(X, y)

[0406] optimal_price = model.predict([[factors + [delivery_days]]])

[0407] return optimal_price

[0408] Displaying pricing information and messages

[0409] The terminal displays a personalized message to the user based on the price information and emotion data for each desired delivery date received from the server. The user confirms the desired delivery date and price of the product through the terminal and selects the desired delivery date.

[0410] Order confirmation and processing

[0411] The price and order information for the delivery date selected by the user are sent from the terminal to the server. Based on the received order information, the server checks inventory, confirms payment, secures a driver, and arranges delivery.

[0412] Specific examples

[0413] Consider the following real-world scenario:

[0414] If there is an abundance of stock and transportation is smooth, the server sets the prices as follows: "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." If the user selects one week later delivery, the emotion engine determines that the user is highly satisfied, and a thank you message is displayed on the device.

[0415] Prompt Sentence Examples

[0416] Here are some example prompts to input to the generative AI model:

[0417] We want to build an efficient delivery management system for our logistics center. Please calculate the optimal delivery fee based on the following data:

[0418] Warehouse conditions (inventory, traffic conditions, driver availability, weather)

[0419] Emotional data of drivers and staff (facial expressions, tone of voice, input text)

[0420] As a result, offer the best delivery price for a desired delivery date three days from now.

[0421] The above is a specific embodiment for carrying out the present invention. This system improves the operational efficiency of a logistics center and increases user satisfaction.

[0422] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0423] Step 1:

[0424] The server collects data from sensors and management systems at the logistics center. Inputs include warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. Data is collected through an API. Output is preprocessed data. Specifically, it receives list data from sensors, converts it to JSON format and saves it.

[0425] Step 2:

[0426] The server collects emotional data from the user's smartphone. Inputs include the user's facial expressions, tone of voice, and input text. The data is collected by an emotion analysis engine. The output is analyzed emotional data. Specifically, the system captures data in real time using the smartphone's camera and microphone and sends it to the analysis engine.

[0427] Step 3:

[0428] The server pre-processes the collected data. The input is the data on warehouse conditions, inventory, driver availability, road conditions, weather, and user emotions. Outliers are removed and missing data is complemented. The output is the pre-processed data. Specific operations include replacing outliers with standard values ​​and complementing missing values ​​with the average value.

[0429] Step 4:

[0430] The server inputs the preprocessed data into a generative model to calculate the optimal delivery price. The input is the preprocessed warehouse data and emotion data. The output is the calculated price information for each desired delivery date. Specifically, the data is input into a generative model (e.g., a linear regression model) and an adapted price is calculated.

[0431] Step 5:

[0432] The server sends a personalized message based on the calculated price information and emotion data to the device. The input is the calculated price information and analyzed emotion data. The output is the price information and message displayed on the user's device. Specifically, the server sends data in JSON format via an API, and the text and price information are displayed on the device.

[0433] Step 6:

[0434] The user selects the desired delivery date and price of the product through the terminal. The input is the price information and personalized message sent from the server. The output is the selected desired delivery date and price. In concrete terms, the user operates the touch screen to select the desired delivery date and price.

[0435] Step 7:

[0436] The terminal sends the price for the selected desired delivery date and order information to the server. The input is the desired delivery date and price selected by the user. The output is the order information sent to the server. Specifically, the terminal sends the order information in JSON format to the server via the API.

[0437] Step 8:

[0438] Based on the order information received by the server, it checks inventory, confirms payment, and arranges for a driver. The input is the order information sent from the terminal. The output is the status of delivery arrangement completion. Specifically, it accesses the inventory management system and payment gateway to carry out the necessary confirmation work.

[0439] The above steps enable efficient delivery management at the logistics center, thereby improving user satisfaction.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] [Second embodiment]

[0444] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0445] 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.

[0446] 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).

[0447] 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.

[0448] 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.

[0449] 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).

[0450] 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.

[0451] 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.

[0452] 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.

[0453] 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.

[0454] In the smart glasses 214, 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.

[0455] 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."

[0456] This invention is a dynamic pricing system that addresses the 2024 problem in the logistics industry by using a generative model to calculate the optimal price for each desired delivery date based on information such as the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and allowing users to select a delivery date.

[0457] 1. Server Processing

[0458] The server first collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0459] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0460] 2. Terminal Processing

[0461] When a user selects a product they wish to purchase using a device (smartphone, tablet, PC, etc.), the device sends a request to the server. In response to the request, the server sends price information for the selected product for each desired delivery date to the device. The device displays this information to the user, allowing them to select the desired delivery date. For example, for product A, the device presents price information such as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[0462] 3. User Operation

[0463] The user uses the terminal to select the product they wish to purchase and then select the desired delivery date. They confirm the displayed price, specify the payment method, and confirm the order. For example, if a user requests delivery of product A in one week, agrees to the price of 1,100 yen, and proceeds with the purchase, the order data is sent from the terminal to the server.

[0464] 4. Processing after order confirmation

[0465] The server verifies the received order data and checks the validity of the order (including inventory confirmation, payment confirmation, and driver availability). Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment and arrange for delivery. For example, if there is sufficient stock of product A and a driver is available, the logistics center will prepare the product and deliver it to the specified address one week later.

[0466] Specific examples

[0467] As a specific scenario, consider the following case.

[0468] 1. When inventory is abundant and traffic is smooth: The server collects data from the logistics center and determines that inventory is abundant and road conditions are good. The generative model sets prices based on this information, for example, "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." The user selects a product through their terminal, requests delivery one week later, and pays 800 yen.

[0469] 2. When inventory is low and traffic is congested: The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the price is confirmed by paying 1,500 yen, and the server sends this information to the logistics center.

[0470] In this way, logistics efficiency can be optimized while customer satisfaction can be increased.

[0471] The processing flow will be explained below.

[0472] Step 1:

[0473] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[0474] Step 2:

[0475] The server performs preprocessing on the collected information, removing outliers and filling in missing data. For example, it filters out abnormal values ​​from a temperature sensor and fills in missing data with the historical average.

[0476] Step 3:

[0477] The server inputs the preprocessed data into a generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[0478] Step 4:

[0479] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[0480] Step 5:

[0481] The server stores the calculated price information in a database and makes it available for user reference.

[0482] Step 6:

[0483] The terminal provides an interface for the user to select the product they wish to purchase, and when the user selects a product, it sends a request for information about that product to the server.

[0484] Step 7:

[0485] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[0486] Step 8:

[0487] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[0488] Step 9:

[0489] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[0490] Step 10:

[0491] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[0492] Step 11:

[0493] The server verifies the received order information, stores it in a database, and checks the validity of the order (including stock availability, payment confirmation, driver availability, etc.).

[0494] Step 12:

[0495] The server then sends the confirmed order details to the relevant departments at the logistics center to prepare for shipment and arrange for delivery. The logistics center then prepares the products based on the received information and delivers them on the specified date.

[0496] In this way, the server, terminal, and user play their respective roles at each step, realizing a system that efficiently collects data, processes data, learns data, sets prices, confirms orders, and delivers data.

[0497] Example 1

[0498] 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."

[0499] In recent years, efficient delivery management and improved customer satisfaction have become important issues in the logistics industry. However, conventional systems have had difficulty in setting prices in real time based on daily changes in inventory, road conditions, and weather. This has led to problems such as inability to set optimal prices, making it difficult to efficiently manage inventory and minimize delivery costs. In addition, customers have limited options for selecting an appropriate price based on their desired delivery date, limiting the improvement of customer satisfaction.

[0500] 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.

[0501] In this invention, the server includes a means for collecting information on the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of transportation, and weather information, a means for preprocessing the collected information to remove outliers and fill in missing data, and a means for performing learning using a generative model based on the preprocessed information to calculate the optimal price for each desired delivery date of the product. This enables optimal pricing according to conditions that change daily, minimizes inventory management and delivery costs, and provides customers with the option to purchase products at the optimal price according to their desired delivery date.

[0502] "Conditions within the logistics center" refers to environmental conditions within the logistics center, such as temperature, humidity, and storage space utilization, as well as the current state of operations within the warehouse.

[0503] "Inventory" refers to the total number and type of products stored in a particular warehouse or distribution center.

[0504] "Driver availability" refers to whether drivers for delivery work have been reliably arranged and their operating status.

[0505] "Traffic conditions on the day of transportation" refers to the degree of road congestion and traffic conditions on the day the goods are transported.

[0506] "Weather information" refers to information about the weather on the day of transportation and before and after, such as rainfall, snowfall, wind speed, temperature, etc.

[0507] "Means of collection" refers collectively to sensors used to obtain necessary data from logistics centers and external sources, as well as software and hardware for accessing databases.

[0508] "Preprocessing means" refers to a method and device in general for removing outliers and filling in missing data from collected data, preparing the data for subsequent analysis and learning.

[0509] "Outlier removal" refers to the process of eliminating obviously abnormal values ​​from collected data, such as physically impossible temperature or humidity data.

[0510] "Missing data imputation" refers to the process of filling in missing values ​​in collected data, for example, using past data or average values.

[0511] A "generative model" is an AI model that learns patterns based on collected and preprocessed data and generates appropriate outputs in response to new inputs.

[0512] "Optimal price" refers to the most economically efficient price set according to the desired delivery date of the product, based on customer demand and the logistics provider's supply conditions.

[0513] "Means for calculating" refers collectively to algorithms and computer software for calculating optimal prices using generative models.

[0514] "Terminal" refers to an electronic device that can connect to the Internet, such as a smartphone, tablet, or personal computer used by a user.

[0515] "User" refers to an individual or corporation that uses the System to purchase products and use delivery services.

[0516] "Order processing" refers to a series of processes based on a purchase request received from a user, from checking inventory to confirming payment and completing delivery arrangements.

[0517] The present invention relates to a dynamic pricing system for the logistics industry. This system aims to improve logistics efficiency and customer satisfaction by collecting variable factors, particularly the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of delivery, and weather information, in real time and setting optimal delivery prices based on the collected data.

[0518] 1. Data Collection

[0519] The server collects data in real time from various sensors and management systems within the logistics center. This data includes the warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Specifically, the central management server periodically obtains JSON-formatted data from each sensor, and uses it to manage, for example, temperature sensors, humidity sensors, inventory management systems, and driver management systems.

[0520] 2. Data Preprocessing

[0521] The server preprocesses the collected data, removing outliers and filling in missing data. For example, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), it will remove them, and missing inventory data will be filled in with the average inventory level from the past.

[0522] 3. Generative pricing

[0523] The server inputs the preprocessed data into a generative model (e.g., OpenAI GPT-4). The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. For example, the model compares prices with past days when inventory was low and sets a new price based on similar patterns. This set price is then stored in a database.

[0524] 4. Processing User Requests

[0525] When a user opens a specific product page, the device sends a request to the server. The request includes a product ID, and when a user displays the page for product A on their smartphone, the product ID is sent to the server.

[0526] 5. Price information for desired delivery date

[0527] The server receives the request sent from the device and retrieves the price information for the corresponding product for each desired delivery date from the database. The price information is sent to the device in JSON format. For example, data such as "next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen" is sent.

[0528] 6. User Purchase Process

[0529] The user checks the price information displayed on the device, selects the desired delivery date, and then selects a payment method to proceed with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card.

[0530] 7. Order confirmation and confirmation

[0531] The server verifies the purchase request received from the user, checks the product inventory, payment confirmation, and driver availability. For example, it retrieves the product inventory from the inventory database and confirms payment via the payment gateway.

[0532] 8. Arrangements after order confirmation

[0533] After the server confirms the order, it notifies the relevant departments at the logistics center. The logistics center then prepares shipment and arranges delivery based on the received information. For example, it sends picking instructions for product A to the warehouse system and updates the schedule to arrange for a driver.

[0534] Specific examples

[0535] Let's say a user wants to purchase Product A. In this case, when the user opens the page for Product A on their smartphone, the device sends Product A's ID to the server. The server retrieves price information for that product for each desired delivery date from the database and sends the following data: "Next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen." The user checks this, selects delivery one week later, agrees to the price of 1,100 yen, and proceeds with the purchase. This order request is checked for inventory and payment on the server side, and if there are no problems, a picking instruction is sent to the logistics center and a driver is arranged.

[0536] Prompt Sentence Examples

[0537] "Calculate the optimal price for each desired delivery date based on the following information: warehouse status, inventory quantity, driver availability, road conditions and weather on the delivery day. For example, please provide an example of pricing when inventory is low and road conditions are poor."

[0538] This system will enable us to optimize logistics efficiency while improving customer satisfaction.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1: Data collection

[0541] The server automatically collects real-time data from various sensors and management systems within the logistics center. Input data includes warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Data is acquired in JSON format and is obtained specifically from temperature sensors, humidity sensors, inventory management systems, and driver management systems. The output is a raw data set.

[0542] Step 2: Data Preprocessing

[0543] The server performs preprocessing on the collected raw dataset. The raw dataset is input. The preprocessing involves removing outliers and filling in missing data. Specifically, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), that data is removed, and missing inventory data is filled in with the average inventory quantity from the past. As a result of the processing, a clean dataset is output.

[0544] Step 3: Generative pricing

[0545] The server inputs the clean dataset into a generative model (e.g., OpenAI GPT-4). The input is the preprocessed clean dataset. The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. This price is calculated by comparing the model with past low inventory days and prices, and setting a new price based on similar patterns. The output is pricing information for each desired delivery date.

[0546] Step 4: Process the user request

[0547] When a user opens a specific product page, the device sends a product request to the server. The input is a request that includes the product ID. For example, when a user displays the page for product A on a smartphone, the ID of product A is sent to the server. The output is a response to the corresponding product ID request.

[0548] Step 5: Submit price information for desired delivery date

[0549] The server receives the product request sent from the terminal and retrieves price information for the corresponding product for each desired delivery date from the database. The input is the product ID request. The data is sent in JSON format, and price information is sent to the terminal. Specifically, price information is provided in the form of "next day delivery: 1,500 yen," "3-day delivery: 1,300 yen," and "1 week later delivery: 1,100 yen."

[0550] Step 6: User checkout

[0551] The user checks the price information displayed on the terminal and selects the desired delivery date. The price information displayed on the terminal and the selected delivery date are input. The user then selects a payment method and proceeds with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card. The purchase request is sent to the server, and a purchase confirmation response is output.

[0552] Step 7: Order confirmation and confirmation

[0553] The server verifies the purchase request received from the user. The input is a purchase request. The server checks the product's inventory, payment confirmation, and driver availability. Specifically, it retrieves the product's inventory from the inventory database and confirms payment via the payment gateway. Once the order is confirmed, it is notified to the logistics center, and a final order confirmation response is output.

[0554] Step 8: Arrangements after order confirmation

[0555] After the server confirms the order, it notifies the relevant departments at the logistics center of the information. The confirmed order information is input. The logistics center prepares for shipment and arranges delivery based on the received information. Specifically, it sends a picking instruction for product A to the warehouse system and updates the schedule to arrange for a driver. The output is a notification that shipment preparation is complete and delivery information.

[0556] In this way, logistics operations are carried out efficiently and effectively.

[0557] (Application example 1)

[0558] 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."

[0559] The logistics industry is seeking more efficient inventory management and delivery scheduling. Real-time management is particularly important, taking into account not only warehouse conditions and inventory levels, but also driver availability, road conditions, weather, and other fluctuating factors. However, this information is not centrally managed, creating problems for staff who are unable to respond efficiently. Additionally, a system is needed that allows users to check and select prices for each desired delivery date, but current methods are insufficient.

[0560] 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.

[0561] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for sending the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for displaying information in real time within the logistics center using smart glasses to improve staff work efficiency. This makes it possible to build a system that improves the efficiency of inventory management and delivery operations within the logistics center and allows users to check the optimal price in real time.

[0562] A "logistics center" is a facility that serves as a base for storing and distributing goods.

[0563] "Warehouse status" refers to information about the current state, layout, and inventory distribution within the logistics center.

[0564] "Stock quantity" is a numerical value indicating the quantity of products stored in the logistics center.

[0565] "Driver availability" refers to the number of drivers performing delivery duties at the logistics center and their schedules.

[0566] "Road conditions" refers to information such as traffic volume and congestion on roads used as delivery routes.

[0567] "Weather" refers to the weather forecast and weather conditions on the day of delivery.

[0568] A "generative model" is a type of machine learning model that is trained to derive optimal results based on specified data.

[0569] "Optimal price" refers to the most reasonable price for the desired delivery date calculated by the generative model based on the collected data.

[0570] A "terminal" is a device that allows a user to input and check information, and specifically includes smartphones, tablets, and PCs.

[0571] "Smart glasses" are a wearable eyeglass-type device that has the ability to display information on a screen in real time.

[0572] "Users" refers to people who use the system, including general consumers and logistics center staff.

[0573] "Order processing" refers to receiving order information from a user and completing a series of procedures such as checking inventory, confirming payment, and arranging delivery.

[0574] This invention will be described as an example of application in a logistics center management system using smart glasses.

[0575] Overall system configuration

[0576] The system collects information such as warehouse conditions at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and uses a generative model to calculate the optimal price for each desired delivery date. This information is presented to staff in the logistics center in real time using smart glasses. The system also allows users to check and select prices for each desired delivery date, and processes orders.

[0577] Server Processing

[0578] The server collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0579] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0580] Smart Glasses Processing

[0581] The smart glasses are worn by staff in the distribution center and receive and display the information they need in real time while they work. Information such as collected inventory levels, driver availability, prices for each desired delivery date, road conditions, and weather is visually displayed through a HUD (head-up display). This allows staff to work efficiently while moving around the warehouse.

[0582] For example, a staff member checking an inventory list can use smart glasses to check the stock levels of each product in real time and make necessary replenishments or rearrangements. They can also instantly check the latest information on drivers scheduled for delivery and road conditions, enabling quick decision-making.

[0583] Hardware and software used

[0584] Hardware: Smart glasses such as Epson Moverio and Vuzix Blade.

[0585] Software: API communication library (requests) and HUD display library for smart glasses.

[0586] Specific examples

[0587] For example, the following scenario can occur within a logistics center:

[0588] Staff checking the inventory list can instantly check information such as "Quantity in stock: 150," "Driver availability: stable," and "Delivery price: 1,200 yen" through the smart glasses, dramatically improving work efficiency.

[0589] Prompt Sentence Examples

[0590] "A method of using smart glasses to manage inventory and deliveries within a distribution center. The glasses display real-time inventory levels, driver availability, pricing information for each desired delivery date, and road and weather conditions, improving the efficiency of staff work."

[0591] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0592] Step 1:

[0593] The server collects real-time data from various sensors and management systems within the logistics center. This data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected data is input and stored in a database.

[0594] Step 2:

[0595] The server performs preprocessing on the collected data, removing outliers and filling in missing data. For example, it filters out abnormal temperature and humidity values, and fills in missing inventory data with historical average values. The preprocessed data is used as input for the next calculation.

[0596] Step 3:

[0597] The server inputs the preprocessed data into a generative model to learn optimal pricing patterns. The generative model compares past data with the current situation to calculate the optimal price for each desired delivery date for each product. The calculated optimal price is saved as output in a database.

[0598] Step 4:

[0599] The terminal sends a request to the server to obtain price information for each desired delivery date for the product selected by the user. The terminal displays the obtained price information to the user. The user selects a desired delivery date as input and sends that information to the server.

[0600] Step 5:

[0601] The server receives the price and order information for the delivery date selected by the user. Based on the received order information, it carries out a series of order processes, including checking inventory, confirming payment, and securing a driver. Once the order process is complete, it forwards the information to the relevant department.

[0602] Step 6:

[0603] The smart glasses display information collected from the server to the operatives in real time, such as inventory levels, driver availability, delivery prices by desired delivery date, road conditions, and weather, on the HUD. This allows the operatives to work efficiently within the logistics center.

[0604] 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.

[0605] This invention combines an emotion engine with a dynamic pricing system to address labor shortages and declining operational efficiency in the logistics industry and improve customer satisfaction. The system collects data on the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, as well as user emotion data, and uses a generative model to calculate the optimal price for each desired delivery date. It also optimizes prices and desired delivery dates individually based on the user's emotion data and displays personalized marketing messages.

[0606] 1. Server Processing

[0607] First, the server collects data in real time from various sensors and management systems within the logistics center. The collected data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected information is pre-processed to remove outliers and fill in missing data.

[0608] The server also collects emotional data from the user's emotion engine, such as facial expressions, tone of voice, and analysis results of entered text, obtained from the device during user operation. The preprocessed data and emotional data are input into a generative model, which then learns optimal pricing patterns based on past data and the current situation.

[0609] 2. Terminal Processing

[0610] When a user selects a product they wish to purchase using a terminal, the terminal sends a request to the server. The server calculates the price information for each desired delivery date for the selected product and sends it to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[0611] The device also collects real-time emotional data from the user's emotion engine and sends it to the server, which then individually optimizes product prices and desired delivery dates.

[0612] 3. User Operation

[0613] The user uses the device to select a product and a desired delivery date, confirm the displayed price, confirm the order, specify a payment method, and enter the required information. The user's emotions may also be communicated to the system, which may adjust the price and delivery date options accordingly.

[0614] 4. Processing after order confirmation

[0615] The server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order details are confirmed, the relevant information is sent to the logistics center to prepare for shipment. The logistics center prepares the product according to the instructions and delivers it on the specified date. Additionally, personalized marketing messages are displayed to users based on their emotional data.

[0616] Specific examples

[0617] As a specific scenario, consider the following case.

[0618] 1. When inventory is abundant and transportation is smooth:

[0619] The server collects data from the logistics center and determines that there is abundant inventory and road conditions are good. The generative model uses this information to set prices, determining the following: next-day delivery: 1,000 yen, three-day delivery: 900 yen, and one-week delivery: 800 yen. The user selects a product via their device and requests delivery one week later. The emotion engine determines that the user is highly satisfied, and a personalized thank-you message is displayed. The user pays 800 yen and confirms the order.

[0620] 2. When inventory is low and traffic is heavy:

[0621] The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the emotion engine determines that the user is in a hurry, and an immediate delivery service is displayed. The user pays 1,500 yen and confirms the order.

[0622] In this way, by combining the emotion engine, it becomes possible to provide flexible and efficient pricing and delivery options that respond to the user's emotions.

[0623] The processing flow will be explained below.

[0624] Step 1:

[0625] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[0626] Step 2:

[0627] The server preprocesses the collected information, filtering out outliers and filling in missing data. For example, if a temperature sensor in a warehouse reports an abnormal value, the data is filtered out. Missing inventory levels are filled in with the average value from the past.

[0628] Step 3:

[0629] The server inputs the preprocessed data into the generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[0630] Step 4:

[0631] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[0632] Step 5:

[0633] The server collects user emotion data from the emotion engine, which is obtained by facial expression recognition during user operation, tone analysis of voice, and emotion analysis of input text.

[0634] Step 6:

[0635] The server inputs the acquired emotion data into a generative model and further optimizes the price for each desired delivery date of the product based on the user's emotions.

[0636] Step 7:

[0637] The server stores the calculated price information in a database and transmits it to the terminal.

[0638] Step 8:

[0639] The terminal provides an interface for the user to select the product they wish to purchase, and once the user has selected the product, it sends a request for information about that product to the server.

[0640] Step 9:

[0641] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[0642] Step 10:

[0643] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[0644] Step 11:

[0645] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[0646] Step 12:

[0647] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[0648] Step 13:

[0649] The server checks the received order information, confirms inventory, payment, and the validity of driver availability. Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment.

[0650] Step 14:

[0651] The server generates a personalized marketing message according to the user's emotions based on the emotion engine and transmits it to the terminal.

[0652] Step 15:

[0653] The terminal displays the marketing message received from the server to the user. For example, if it is determined that the user is in a hurry, an announcement about an immediate delivery service is displayed.

[0654] Step 16:

[0655] The logistics center will prepare the product based on the received information and deliver it on the specified date.

[0656] In this way, the server, terminal, and user play their respective roles at each step, resulting in a system that efficiently collects, processes, learns, sets prices, confirms orders, and delivers. Furthermore, by collecting and utilizing emotional data, the system aims to provide more personalized services and improve customer satisfaction.

[0657] Example 2

[0658] 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."

[0659] The logistics industry is facing significant challenges due to labor shortages and declining operational efficiency, which are resulting in declining customer satisfaction. Furthermore, traditional pricing systems have difficulty providing personalized prices and delivery schedules that reflect each user's needs and emotions. This results in an unoptimized user experience, which can further worsen customer satisfaction. Therefore, there is a need for a system that collects diverse data in real time and provides optimal pricing and delivery schedules based on user emotions.

[0660] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0661] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for transmitting the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for collecting user emotion data; means for individually optimizing the price and desired delivery date based on the emotion data; and means for receiving the price and order information for the selected desired delivery date and processing the order. This makes it possible to address labor shortages and declining business efficiency and provide flexible and efficient pricing and delivery options that respond to user emotions.

[0662] A "logistics center" is a facility where packages are stored, managed, sorted, and prepared for delivery.

[0663] "Storage conditions" refers to the physical and environmental conditions inside the logistics center, including temperature, humidity, lighting, and storage space.

[0664] "Inventory quantity" refers to the quantity of products, goods, and materials stored in a logistics center.

[0665] "Driver availability" refers to delivery driver staffing, shifts, and the number of available drivers.

[0666] "Road conditions on the day of delivery" refers to the traffic and road conditions on the day that affect the delivery of goods. Specifically, this includes information on traffic congestion and prohibited activities.

[0667] "Weather" means meteorological conditions that affect the planning and execution of a Delivery, including, but not limited to, rain, snow, wind speed, and temperature.

[0668] A "generative model" is an algorithm that learns patterns and predictions from data and generates results for new data inputs.

[0669] "Emotional data" refers to information that indicates the user's emotional state as analyzed from facial expressions, tone of voice, and text.

[0670] "Terminal" refers to the device used by a user to operate the system, including smartphones, tablets, personal computers, etc.

[0671] "User" refers to an individual or organization that uses the system to purchase products and receive delivery services.

[0672] "Optimization" is the process of making adjustments to obtain the most effective and efficient results under given conditions and constraints.

[0673] "Pricing" refers to the process of determining the price of your product offerings, specifically setting prices based on cost, demand, competition, and other market factors.

[0674] "Desired delivery date" refers to the specific date on which the user wishes to receive the product.

[0675] "Order processing" refers to the series of processes that involve accepting an order from a user, communicating it to the logistics center or delivery staff, and then putting it into action.

[0676] This invention is a system for improving labor shortages and declining business efficiency in the logistics industry and improving customer satisfaction. A specific embodiment of the program for this system will be described below.

[0677] Program processing explanation

[0678] Data collection

[0679] The server collects data in real time from various sensors and management systems installed in the logistics center. For example,

[0680] Data on the state of the interior of the warehouse is obtained from temperature and humidity sensors.

[0681] Inventory quantity data is obtained from the inventory management system.

[0682] Driver availability data is obtained from the human resources management system.

[0683] Road condition data on the day of delivery is obtained from the traffic information system.

[0684] Weather data is obtained from weather information services.

[0685] Additionally, the server collects real-time emotional data from the user's device, including facial expressions, tone of voice, and analysis of input text.

[0686] Data Preprocessing

[0687] The server pre-processes the collected data, removing outliers and filling in missing data. For example, it removes inappropriate temperature sensor data and fills in missing inventory data from past data.

[0688] Learning with generative models

[0689] Preprocessed logistics data and sentiment data are input into a generative AI model. The generative model learns optimal pricing patterns based on past data and the current situation. It is preferable to use a multi-layer neural network (DNN) for the generative AI model used.

[0690] Processing user requests

[0691] When a user selects a product to purchase on the terminal, the terminal sends that information to the server. The server calculates the price of the selected product for each desired delivery date and sends that information to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[0692] Optimization and individual adjustment

[0693] The device collects the user's emotions in real time and sends the data to a server, which then individually optimizes the product price and desired delivery date based on the emotion data. For example, if the server determines that the user is in a hurry, it will present an option for immediate delivery and adjust the price.

[0694] Processing after order confirmation

[0695] When a user confirms an order, the server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order is confirmed, the information is sent to the logistics center for shipping preparation. The logistics center prepares the product according to the instructions and delivers it on the specified date. In addition, personalized marketing messages based on emotional data are displayed to the user.

[0696] Specific examples

[0697] For example, if data collected from a logistics center indicates that there is abundant inventory and road conditions are good, the generative model will set prices such as "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." On the other hand, if there is little inventory and road conditions are congested, the model will set prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[0698] In addition, the service is optimized based on the user's emotional data, and if it determines that the user is in a hurry, it will suggest immediate delivery. Such personalized suggestions will improve user satisfaction.

[0699] Prompt Sentence Examples

[0700] Here are some examples of specific prompts:

[0701] "Design a system that collects data from various sensors and management systems in a distribution center and retrieves user sentiment data from an emotion engine. Explain how you can use this data to leverage a generative AI model that learns optimal pricing patterns and provides personalized delivery options to users."

[0702] In this way, through the embodiments of the invention, it is possible to improve customer satisfaction and business efficiency.

[0703] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0704] Step 1:

[0705] The server starts collecting data.

[0706] Input: Data from various sensors in the logistics center, inventory data from the inventory management system, road condition data from the traffic information system, weather data from the weather information service, and driver availability data from the human resources management system.

[0707] Data processing: The server collects these data in real time and stores them in a database.

[0708] Output: A collection of raw data.

[0709] How it works: Every minute, the server automatically pulls sensor data and executes a script to store it in a database. It also periodically calls APIs from inventory management systems, traffic information systems, human resources management systems, and weather information services to collect data.

[0710] Step 2:

[0711] The server pre-processes the data.

[0712] Input: Raw data collected in step 1.

[0713] Data processing: Removal of outliers, imputation of missing data.

[0714] Output: Preprocessed clean data.

[0715] Specific operation: The server runs an algorithm to detect outliers, removes any detected outliers, and performs a filtering process to fill in missing data with predicted values ​​based on similar data from the past.

[0716] Step 3:

[0717] The server inputs data into the generative model and performs learning.

[0718] Input: Preprocessed clean data.

[0719] Data processing: The data input and learning process for generative AI models.

[0720] Output: Optimal pricing pattern.

[0721] How it works: The server feeds the preprocessed data into a generative AI model (a multi-layer neural network), which then learns optimal pricing patterns based on past data and current conditions. The model is periodically retrained to adapt to new data.

[0722] Step 4:

[0723] The terminal sends an input request from the user.

[0724] Input: Product selection information by the user.

[0725] Data processing: Transmission of user-entered information.

[0726] Output: The request data sent to the server.

[0727] Specific operation: The user selects the desired product on the terminal and sends the selection information to the server as a request. This request includes information about the selected product and the user ID.

[0728] Step 5:

[0729] The server calculates the pricing data and sends it to the terminal.

[0730] Input: Request data from users, optimal pricing patterns from the generative model.

[0731] Data processing: Calculate the price for each desired delivery date for the requested item.

[0732] Output: Calculated price information.

[0733] Specific operation: Based on the pricing patterns obtained from the generative model, the server calculates the price for each desired delivery date for the product corresponding to the user's request and sends the price information to the terminal.

[0734] Step 6:

[0735] The device displays the results to the user and collects emotional data in real time.

[0736] Input: Price information sent from the server, user sentiment data.

[0737] Data processing: Displaying price information and collecting sentiment data.

[0738] Output: Displayed price information, collected sentiment data.

[0739] Specific operation: The terminal displays the received price information to the user. In addition, the terminal analyzes the user's facial expressions, tone of voice, and text input, and collects real-time emotional data through the emotion engine. This data is then sent to the server.

[0740] Step 7:

[0741] The server performs optimization and determines the final price and desired delivery date.

[0742] Input: sentiment data, preprocessed logistics data, pricing patterns using a generative model.

[0743] Data processing: Optimizing price and desired delivery date based on sentiment data.

[0744] Output: Final adjusted price information and desired delivery date.

[0745] Specific operation: The server analyzes the emotion data and adjusts the price and desired delivery date based on the user's level of urgency and satisfaction. For example, if a user is in a hurry, it will present the option of same-day delivery and its price.

[0746] Step 8:

[0747] The user selects the desired delivery date and confirms the order.

[0748] Input: The last price information displayed on the device and the desired delivery date.

[0749] Data processing: Sending the user's selected delivery date and price information.

[0750] Output: Confirmed order data.

[0751] Specific operation: The user selects the desired delivery date based on the information displayed on the terminal and finalizes the order. After confirming the order, the user enters the necessary payment information and sends it to the server.

[0752] Step 9:

[0753] The server checks the order information and sends instructions to the logistics center.

[0754] Input: Confirmed order data.

[0755] Data processing: Checking inventory, payment, and driver availability.

[0756] Output: Shipping instruction data to the logistics center.

[0757] Specific operation: The server checks the received order information, checks the validity of the inventory and payment, and if there are no problems, sends instructions to the logistics center to prepare for shipment.

[0758] Step 10:

[0759] The logistics center prepares the products and delivers them on the specified date.

[0760] Input: Shipping instruction data from the server.

[0761] Data processing: Product preparation and delivery planning.

[0762] Output: The delivered item.

[0763] Specific operation: The logistics center prepares the product according to instructions from the server, and delivers the product by a delivery driver on the specified date. It also delivers personalized messages and special offers to users based on their emotional data.

[0764] (Application example 2)

[0765] 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."

[0766] Labor shortages and declining operational efficiency are serious issues in the logistics industry. Furthermore, while there is a demand for flexible service provision that responds to user emotions and individual needs, this has not been fully realized. Therefore, a method is needed to simultaneously achieve efficient management and personalized service provision.

[0767] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and user emotion data and calculating the optimal price for each desired delivery date; means for sending a personalized message based on the calculated price information and emotion data to the terminal so that the user can confirm and select a price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for collecting emotion data and performing emotion analysis in real time. This makes it possible to provide an efficient and personalized delivery service.

[0768] A "logistics center" is a facility that centralizes logistics operations such as storing, sorting, packaging, shipping, and delivering packages.

[0769] "Storage status" is data that indicates the storage status of inventory and the progress of work within the logistics center.

[0770] "Stock quantity" is data indicating the quantity of products stored in the logistics center.

[0771] "Driver availability status" is data that indicates the status and number of drivers available for delivery at the logistics center.

[0772] "Road conditions on the day of delivery" is data indicating road traffic conditions and congestion information on the day of delivery.

[0773] "Weather" is data indicating the weather conditions on the delivery date.

[0774] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, tone of voice, input text, and the like.

[0775] A "generative model" is an algorithm that uses machine learning based on collected data to generate optimal results for new data.

[0776] A "personalized message" is a personalized message created based on the emotional data and past behavior of an individual user.

[0777] A "terminal" is an electronic device that allows a user to obtain information or send instructions.

[0778] "Order information" is data including the product selected by the user, desired delivery date, price, payment method, etc.

[0779] "Emotion analysis" is a process of analyzing the user's emotional state based on collected emotional data.

[0780] This invention aims to build an efficient delivery management system in a logistics center and improve user satisfaction. A specific method for implementing each step will be described below.

[0781] System Configuration

[0782] The present invention uses the following hardware and software:

[0783] Hardware: sensors, servers, smartphones

[0784] Software: Data collection API, sentiment analysis engine, generative model

[0785] Program processing

[0786] Data collection

[0787] The server collects the following data in real time from sensors and management systems within the distribution center:

[0788] Warehouse status

[0789] Quantity in stock

[0790] Driver availability

[0791] Road conditions on the day of delivery

[0792] weather

[0793] The collected data is preprocessed to make it suitable for analysis by removing outliers and filling in missing data. If the device operated by the user is a smartphone, the user's facial expression, tone of voice, and input text are analyzed by an emotion analysis engine to extract emotional data.

[0794] Optimal price calculation using generative models

[0795] The server inputs the pre-processed data and sentiment data into a generative model to determine the optimal price based on past data and the current situation. For example, a Python script like the following can be used:

[0796] python

[0797] import numpy as np

[0798] import pandas as pd

[0799] from datetime import datetime

[0800] import requests

[0801] from sklearn.linear_model import LinearRegression

[0802] Data collection function definition

[0803] def collect_data():

[0804] Sensor data collection

[0805] warehouse_data = requests.get('https: / / api.warehouse.com / data').json()

[0806] Collecting Emotional Data

[0807] emotion_data = requests.get('https: / / api.emotionengine.com / data').json()

[0808] return warehouse_data, emotion_data

[0809] Emotional Data Analysis

[0810] def analyze_emotion(emotion_data):

[0811] Tentative emotion analysis results

[0812] emotion_score = np.mean([item['score'] for item in emotion_data])

[0813] return emotion_score

[0814] Optimal Price Calculation

[0815] def calculate_optimal_price(warehouse_data, emotion_score, delivery_days):

[0816] factors = [warehouse_data['stock_level'], warehouse_data['traffic'],

[0817] warehouse_data['driver_availability'], emotion_score]

[0818] Hypothetical pricing model

[0819] model = LinearRegression()

[0820] X = np.array(factors).reshape(-1, 1)

[0821] y = np.array([1000, 950, 900]) Historical price data

[0822] model.fit(X, y)

[0823] optimal_price = model.predict([[factors + [delivery_days]]])

[0824] return optimal_price

[0825] Displaying pricing information and messages

[0826] The terminal displays a personalized message to the user based on the price information and emotion data for each desired delivery date received from the server. The user confirms the desired delivery date and price of the product through the terminal and selects the desired delivery date.

[0827] Order confirmation and processing

[0828] The price and order information for the delivery date selected by the user are sent from the terminal to the server. Based on the received order information, the server checks inventory, confirms payment, secures a driver, and arranges delivery.

[0829] Specific examples

[0830] Consider the following real-world scenario:

[0831] If there is an abundance of stock and transportation is smooth, the server sets the prices as follows: "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." If the user selects one week later delivery, the emotion engine determines that the user is highly satisfied, and a thank you message is displayed on the device.

[0832] Prompt Sentence Examples

[0833] Here are some example prompts to input to the generative AI model:

[0834] We want to build an efficient delivery management system for our logistics center. Please calculate the optimal delivery fee based on the following data:

[0835] Warehouse conditions (inventory, traffic conditions, driver availability, weather)

[0836] Emotional data of drivers and staff (facial expressions, tone of voice, input text)

[0837] As a result, offer the best delivery price for a desired delivery date three days from now.

[0838] The above is a specific embodiment for carrying out the present invention. This system improves the operational efficiency of a logistics center and increases user satisfaction.

[0839] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0840] Step 1:

[0841] The server collects data from sensors and management systems at the logistics center. Inputs include warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. Data is collected through an API. Output is preprocessed data. Specifically, it receives list data from sensors, converts it to JSON format and saves it.

[0842] Step 2:

[0843] The server collects emotional data from the user's smartphone. Inputs include the user's facial expressions, tone of voice, and input text. The data is collected by an emotion analysis engine. The output is analyzed emotional data. Specifically, the system captures data in real time using the smartphone's camera and microphone and sends it to the analysis engine.

[0844] Step 3:

[0845] The server pre-processes the collected data. The input is the data on warehouse conditions, inventory, driver availability, road conditions, weather, and user emotions. Outliers are removed and missing data is complemented. The output is the pre-processed data. Specific operations include replacing outliers with standard values ​​and complementing missing values ​​with the average value.

[0846] Step 4:

[0847] The server inputs the preprocessed data into a generative model to calculate the optimal delivery price. The input is the preprocessed warehouse data and emotion data. The output is the calculated price information for each desired delivery date. Specifically, the data is input into a generative model (e.g., a linear regression model) and an adapted price is calculated.

[0848] Step 5:

[0849] The server sends a personalized message based on the calculated price information and emotion data to the device. The input is the calculated price information and analyzed emotion data. The output is the price information and message displayed on the user's device. Specifically, the server sends data in JSON format via an API, and the text and price information are displayed on the device.

[0850] Step 6:

[0851] The user selects the desired delivery date and price of the product through the terminal. The input is the price information and personalized message sent from the server. The output is the selected desired delivery date and price. In concrete terms, the user operates the touch screen to select the desired delivery date and price.

[0852] Step 7:

[0853] The terminal sends the price for the selected desired delivery date and order information to the server. The input is the desired delivery date and price selected by the user. The output is the order information sent to the server. Specifically, the terminal sends the order information in JSON format to the server via the API.

[0854] Step 8:

[0855] Based on the order information received by the server, it checks inventory, confirms payment, and arranges for a driver. The input is the order information sent from the terminal. The output is the status of delivery arrangement completion. Specifically, it accesses the inventory management system and payment gateway to carry out the necessary confirmation work.

[0856] The above steps enable efficient delivery management at the logistics center, thereby improving user satisfaction.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] [Third embodiment]

[0861] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0862] 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.

[0863] 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).

[0864] 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.

[0865] 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.

[0866] 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).

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] 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.

[0872] 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."

[0873] This invention is a dynamic pricing system that addresses the 2024 problem in the logistics industry by using a generative model to calculate the optimal price for each desired delivery date based on information such as the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and allowing users to select a delivery date.

[0874] 1. Server Processing

[0875] The server first collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0876] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0877] 2. Terminal Processing

[0878] When a user selects a product they wish to purchase using a device (smartphone, tablet, PC, etc.), the device sends a request to the server. In response to the request, the server sends price information for the selected product for each desired delivery date to the device. The device displays this information to the user, allowing them to select the desired delivery date. For example, for product A, the device presents price information such as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[0879] 3. User Operation

[0880] The user uses the terminal to select the product they wish to purchase and then select the desired delivery date. They confirm the displayed price, specify the payment method, and confirm the order. For example, if a user requests delivery of product A in one week, agrees to the price of 1,100 yen, and proceeds with the purchase, the order data is sent from the terminal to the server.

[0881] 4. Processing after order confirmation

[0882] The server verifies the received order data and checks the validity of the order (including inventory confirmation, payment confirmation, and driver availability). Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment and arrange for delivery. For example, if there is sufficient stock of product A and a driver is available, the logistics center will prepare the product and deliver it to the specified address one week later.

[0883] Specific examples

[0884] As a specific scenario, consider the following case.

[0885] 1. When inventory is abundant and traffic is smooth: The server collects data from the logistics center and determines that inventory is abundant and road conditions are good. The generative model sets prices based on this information, for example, "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." The user selects a product through their terminal, requests delivery one week later, and pays 800 yen.

[0886] 2. When inventory is low and traffic is congested: The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the price is confirmed by paying 1,500 yen, and the server sends this information to the logistics center.

[0887] In this way, logistics efficiency can be optimized while customer satisfaction can be increased.

[0888] The processing flow will be explained below.

[0889] Step 1:

[0890] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[0891] Step 2:

[0892] The server performs preprocessing on the collected information, removing outliers and filling in missing data. For example, it filters out abnormal values ​​from a temperature sensor and fills in missing data with the historical average.

[0893] Step 3:

[0894] The server inputs the preprocessed data into a generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[0895] Step 4:

[0896] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[0897] Step 5:

[0898] The server stores the calculated price information in a database and makes it available for user reference.

[0899] Step 6:

[0900] The terminal provides an interface for the user to select the product they wish to purchase, and when the user selects a product, it sends a request for information about that product to the server.

[0901] Step 7:

[0902] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[0903] Step 8:

[0904] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[0905] Step 9:

[0906] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[0907] Step 10:

[0908] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[0909] Step 11:

[0910] The server verifies the received order information, stores it in a database, and checks the validity of the order (including stock availability, payment confirmation, driver availability, etc.).

[0911] Step 12:

[0912] The server then sends the confirmed order details to the relevant departments at the logistics center to prepare for shipment and arrange for delivery. The logistics center then prepares the products based on the received information and delivers them on the specified date.

[0913] In this way, the server, terminal, and user play their respective roles at each step, realizing a system that efficiently collects data, processes data, learns data, sets prices, confirms orders, and delivers data.

[0914] Example 1

[0915] 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."

[0916] In recent years, efficient delivery management and improved customer satisfaction have become important issues in the logistics industry. However, conventional systems have had difficulty in setting prices in real time based on daily changes in inventory, road conditions, and weather. This has led to problems such as inability to set optimal prices, making it difficult to efficiently manage inventory and minimize delivery costs. In addition, customers have limited options for selecting an appropriate price based on their desired delivery date, limiting the improvement of customer satisfaction.

[0917] 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.

[0918] In this invention, the server includes a means for collecting information on the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of transportation, and weather information, a means for preprocessing the collected information to remove outliers and fill in missing data, and a means for performing learning using a generative model based on the preprocessed information to calculate the optimal price for each desired delivery date of the product. This enables optimal pricing according to conditions that change daily, minimizes inventory management and delivery costs, and provides customers with the option to purchase products at the optimal price according to their desired delivery date.

[0919] "Conditions within the logistics center" refers to environmental conditions within the logistics center, such as temperature, humidity, and storage space utilization, as well as the current state of operations within the warehouse.

[0920] "Inventory" refers to the total number and type of products stored in a particular warehouse or distribution center.

[0921] "Driver availability" refers to whether drivers for delivery work have been reliably arranged and their operating status.

[0922] "Traffic conditions on the day of transportation" refers to the degree of road congestion and traffic conditions on the day the goods are transported.

[0923] "Weather information" refers to information about the weather on the day of transportation and before and after, such as rainfall, snowfall, wind speed, temperature, etc.

[0924] "Means of collection" refers collectively to sensors used to obtain necessary data from logistics centers and external sources, as well as software and hardware for accessing databases.

[0925] "Preprocessing means" refers to a method and device in general for removing outliers and filling in missing data from collected data, preparing the data for subsequent analysis and learning.

[0926] "Outlier removal" refers to the process of eliminating obviously abnormal values ​​from collected data, such as physically impossible temperature or humidity data.

[0927] "Missing data imputation" refers to the process of filling in missing values ​​in collected data, for example, using past data or average values.

[0928] A "generative model" is an AI model that learns patterns based on collected and preprocessed data and generates appropriate outputs in response to new inputs.

[0929] "Optimal price" refers to the most economically efficient price set according to the desired delivery date of the product, based on customer demand and the logistics provider's supply conditions.

[0930] "Means for calculating" refers collectively to algorithms and computer software for calculating optimal prices using generative models.

[0931] "Terminal" refers to an electronic device that can connect to the Internet, such as a smartphone, tablet, or personal computer used by a user.

[0932] "User" refers to an individual or corporation that uses the System to purchase products and use delivery services.

[0933] "Order processing" refers to a series of processes based on a purchase request received from a user, from checking inventory to confirming payment and completing delivery arrangements.

[0934] The present invention relates to a dynamic pricing system for the logistics industry. This system aims to improve logistics efficiency and customer satisfaction by collecting variable factors, particularly the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of delivery, and weather information, in real time and setting optimal delivery prices based on the collected data.

[0935] 1. Data Collection

[0936] The server collects data in real time from various sensors and management systems within the logistics center. This data includes the warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Specifically, the central management server periodically obtains JSON-formatted data from each sensor, and uses it to manage, for example, temperature sensors, humidity sensors, inventory management systems, and driver management systems.

[0937] 2. Data Preprocessing

[0938] The server preprocesses the collected data, removing outliers and filling in missing data. For example, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), it will remove them, and missing inventory data will be filled in with the average inventory level from the past.

[0939] 3. Generative pricing

[0940] The server inputs the preprocessed data into a generative model (e.g., OpenAI GPT-4). The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. For example, the model compares prices with past days when inventory was low and sets a new price based on similar patterns. This set price is then stored in a database.

[0941] 4. Processing User Requests

[0942] When a user opens a specific product page, the device sends a request to the server. The request includes a product ID, and when a user displays the page for product A on their smartphone, the product ID is sent to the server.

[0943] 5. Price information for desired delivery date

[0944] The server receives the request sent from the device and retrieves the price information for the corresponding product for each desired delivery date from the database. The price information is sent to the device in JSON format. For example, data such as "next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen" is sent.

[0945] 6. User Purchase Process

[0946] The user checks the price information displayed on the device, selects the desired delivery date, and then selects a payment method to proceed with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card.

[0947] 7. Order confirmation and confirmation

[0948] The server verifies the purchase request received from the user, checks the product inventory, payment confirmation, and driver availability. For example, it retrieves the product inventory from the inventory database and confirms payment via the payment gateway.

[0949] 8. Arrangements after order confirmation

[0950] After the server confirms the order, it notifies the relevant departments at the logistics center. The logistics center then prepares shipment and arranges delivery based on the received information. For example, it sends picking instructions for product A to the warehouse system and updates the schedule to arrange for a driver.

[0951] Specific examples

[0952] Let's say a user wants to purchase Product A. In this case, when the user opens the page for Product A on their smartphone, the device sends Product A's ID to the server. The server retrieves price information for that product for each desired delivery date from the database and sends the following data: "Next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen." The user checks this, selects delivery one week later, agrees to the price of 1,100 yen, and proceeds with the purchase. This order request is checked for inventory and payment on the server side, and if there are no problems, a picking instruction is sent to the logistics center and a driver is arranged.

[0953] Prompt Sentence Examples

[0954] "Calculate the optimal price for each desired delivery date based on the following information: warehouse status, inventory quantity, driver availability, road conditions and weather on the delivery day. For example, please provide an example of pricing when inventory is low and road conditions are poor."

[0955] This system will enable us to optimize logistics efficiency while improving customer satisfaction.

[0956] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0957] Step 1: Data collection

[0958] The server automatically collects real-time data from various sensors and management systems within the logistics center. Input data includes warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Data is acquired in JSON format and is obtained specifically from temperature sensors, humidity sensors, inventory management systems, and driver management systems. The output is a raw data set.

[0959] Step 2: Data Preprocessing

[0960] The server performs preprocessing on the collected raw dataset. The raw dataset is input. The preprocessing involves removing outliers and filling in missing data. Specifically, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), that data is removed, and missing inventory data is filled in with the average inventory quantity from the past. As a result of the processing, a clean dataset is output.

[0961] Step 3: Generative pricing

[0962] The server inputs the clean dataset into a generative model (e.g., OpenAI GPT-4). The input is the preprocessed clean dataset. The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. This price is calculated by comparing the model with past low inventory days and prices, and setting a new price based on similar patterns. The output is pricing information for each desired delivery date.

[0963] Step 4: Process the user request

[0964] When a user opens a specific product page, the device sends a product request to the server. The input is a request that includes the product ID. For example, when a user displays the page for product A on a smartphone, the ID of product A is sent to the server. The output is a response to the corresponding product ID request.

[0965] Step 5: Submit price information for desired delivery date

[0966] The server receives the product request sent from the terminal and retrieves price information for the corresponding product for each desired delivery date from the database. The input is the product ID request. The data is sent in JSON format, and price information is sent to the terminal. Specifically, price information is provided in the form of "next day delivery: 1,500 yen," "3-day delivery: 1,300 yen," and "1 week later delivery: 1,100 yen."

[0967] Step 6: User checkout

[0968] The user checks the price information displayed on the terminal and selects the desired delivery date. The price information displayed on the terminal and the selected delivery date are input. The user then selects a payment method and proceeds with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card. The purchase request is sent to the server, and a purchase confirmation response is output.

[0969] Step 7: Order confirmation and confirmation

[0970] The server verifies the purchase request received from the user. The input is a purchase request. The server checks the product's inventory, payment confirmation, and driver availability. Specifically, it retrieves the product's inventory from the inventory database and confirms payment via the payment gateway. Once the order is confirmed, it is notified to the logistics center, and a final order confirmation response is output.

[0971] Step 8: Arrangements after order confirmation

[0972] After the server confirms the order, it notifies the relevant departments at the logistics center of the information. The confirmed order information is input. The logistics center prepares for shipment and arranges delivery based on the received information. Specifically, it sends a picking instruction for product A to the warehouse system and updates the schedule to arrange for a driver. The output is a notification that shipment preparation is complete and delivery information.

[0973] In this way, logistics operations are carried out efficiently and effectively.

[0974] (Application example 1)

[0975] 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."

[0976] The logistics industry is seeking more efficient inventory management and delivery scheduling. Real-time management is particularly important, taking into account not only warehouse conditions and inventory levels, but also driver availability, road conditions, weather, and other fluctuating factors. However, this information is not centrally managed, creating problems for staff who are unable to respond efficiently. Additionally, a system is needed that allows users to check and select prices for each desired delivery date, but current methods are insufficient.

[0977] 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.

[0978] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for sending the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for displaying information in real time within the logistics center using smart glasses to improve staff work efficiency. This makes it possible to build a system that improves the efficiency of inventory management and delivery operations within the logistics center and allows users to check the optimal price in real time.

[0979] A "logistics center" is a facility that serves as a base for storing and distributing goods.

[0980] "Warehouse status" refers to information about the current state, layout, and inventory distribution within the logistics center.

[0981] "Stock quantity" is a numerical value indicating the quantity of products stored in the logistics center.

[0982] "Driver availability" refers to the number of drivers performing delivery duties at the logistics center and their schedules.

[0983] "Road conditions" refers to information such as traffic volume and congestion on roads used as delivery routes.

[0984] "Weather" refers to the weather forecast and weather conditions on the day of delivery.

[0985] A "generative model" is a type of machine learning model that is trained to derive optimal results based on specified data.

[0986] "Optimal price" refers to the most reasonable price for the desired delivery date calculated by the generative model based on the collected data.

[0987] A "terminal" is a device that allows a user to input and check information, and specifically includes smartphones, tablets, and PCs.

[0988] "Smart glasses" are a wearable eyeglass-type device that has the ability to display information on a screen in real time.

[0989] "Users" refers to people who use the system, including general consumers and logistics center staff.

[0990] "Order processing" refers to receiving order information from a user and completing a series of procedures such as checking inventory, confirming payment, and arranging delivery.

[0991] This invention will be described as an example of application in a logistics center management system using smart glasses.

[0992] Overall system configuration

[0993] The system collects information such as warehouse conditions at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and uses a generative model to calculate the optimal price for each desired delivery date. This information is presented to staff in the logistics center in real time using smart glasses. The system also allows users to check and select prices for each desired delivery date, and processes orders.

[0994] Server Processing

[0995] The server collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[0996] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[0997] Smart Glasses Processing

[0998] The smart glasses are worn by staff in the distribution center and receive and display the information they need in real time while they work. Information such as collected inventory levels, driver availability, prices for each desired delivery date, road conditions, and weather is visually displayed through a HUD (head-up display). This allows staff to work efficiently while moving around the warehouse.

[0999] For example, a staff member checking an inventory list can use smart glasses to check the stock levels of each product in real time and make necessary replenishments or rearrangements. They can also instantly check the latest information on drivers scheduled for delivery and road conditions, enabling quick decision-making.

[1000] Hardware and software used

[1001] Hardware: Smart glasses such as Epson Moverio and Vuzix Blade.

[1002] Software: API communication library (requests) and HUD display library for smart glasses.

[1003] Specific examples

[1004] For example, the following scenario can occur within a logistics center:

[1005] Staff checking the inventory list can instantly check information such as "Quantity in stock: 150," "Driver availability: stable," and "Delivery price: 1,200 yen" through the smart glasses, dramatically improving work efficiency.

[1006] Prompt Sentence Examples

[1007] "A method of using smart glasses to manage inventory and deliveries within a distribution center. The glasses display real-time inventory levels, driver availability, pricing information for each desired delivery date, and road and weather conditions, improving the efficiency of staff work."

[1008] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1009] Step 1:

[1010] The server collects real-time data from various sensors and management systems within the logistics center. This data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected data is input and stored in a database.

[1011] Step 2:

[1012] The server performs preprocessing on the collected data, removing outliers and filling in missing data. For example, it filters out abnormal temperature and humidity values, and fills in missing inventory data with historical average values. The preprocessed data is used as input for the next calculation.

[1013] Step 3:

[1014] The server inputs the preprocessed data into a generative model to learn optimal pricing patterns. The generative model compares past data with the current situation to calculate the optimal price for each desired delivery date for each product. The calculated optimal price is saved as output in a database.

[1015] Step 4:

[1016] The terminal sends a request to the server to obtain price information for each desired delivery date for the product selected by the user. The terminal displays the obtained price information to the user. The user selects a desired delivery date as input and sends that information to the server.

[1017] Step 5:

[1018] The server receives the price and order information for the delivery date selected by the user. Based on the received order information, it carries out a series of order processes, including checking inventory, confirming payment, and securing a driver. Once the order process is complete, it forwards the information to the relevant department.

[1019] Step 6:

[1020] The smart glasses display information collected from the server to the operatives in real time, such as inventory levels, driver availability, delivery prices by desired delivery date, road conditions, and weather, on the HUD. This allows the operatives to work efficiently within the logistics center.

[1021] 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.

[1022] This invention combines an emotion engine with a dynamic pricing system to address labor shortages and declining operational efficiency in the logistics industry and improve customer satisfaction. The system collects data on the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, as well as user emotion data, and uses a generative model to calculate the optimal price for each desired delivery date. It also optimizes prices and desired delivery dates individually based on the user's emotion data and displays personalized marketing messages.

[1023] 1. Server Processing

[1024] First, the server collects data in real time from various sensors and management systems within the logistics center. The collected data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected information is pre-processed to remove outliers and fill in missing data.

[1025] The server also collects emotional data from the user's emotion engine, such as facial expressions, tone of voice, and analysis results of entered text, obtained from the device during user operation. The preprocessed data and emotional data are input into a generative model, which then learns optimal pricing patterns based on past data and the current situation.

[1026] 2. Terminal Processing

[1027] When a user selects a product they wish to purchase using a terminal, the terminal sends a request to the server. The server calculates the price information for each desired delivery date for the selected product and sends it to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[1028] The device also collects real-time emotional data from the user's emotion engine and sends it to the server, which then individually optimizes product prices and desired delivery dates.

[1029] 3. User Operation

[1030] The user uses the device to select a product and a desired delivery date, confirm the displayed price, confirm the order, specify a payment method, and enter the required information. The user's emotions may also be communicated to the system, which may adjust the price and delivery date options accordingly.

[1031] 4. Processing after order confirmation

[1032] The server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order details are confirmed, the relevant information is sent to the logistics center to prepare for shipment. The logistics center prepares the product according to the instructions and delivers it on the specified date. Additionally, personalized marketing messages are displayed to users based on their emotional data.

[1033] Specific examples

[1034] As a specific scenario, consider the following case.

[1035] 1. When inventory is abundant and transportation is smooth:

[1036] The server collects data from the logistics center and determines that there is abundant inventory and road conditions are good. The generative model uses this information to set prices, determining the following: next-day delivery: 1,000 yen, three-day delivery: 900 yen, and one-week delivery: 800 yen. The user selects a product via their device and requests delivery one week later. The emotion engine determines that the user is highly satisfied, and a personalized thank-you message is displayed. The user pays 800 yen and confirms the order.

[1037] 2. When inventory is low and traffic is heavy:

[1038] The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the emotion engine determines that the user is in a hurry, and an immediate delivery service is displayed. The user pays 1,500 yen and confirms the order.

[1039] In this way, by combining the emotion engine, it becomes possible to provide flexible and efficient pricing and delivery options that respond to the user's emotions.

[1040] The processing flow will be explained below.

[1041] Step 1:

[1042] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[1043] Step 2:

[1044] The server preprocesses the collected information, filtering out outliers and filling in missing data. For example, if a temperature sensor in a warehouse reports an abnormal value, the data is filtered out. Missing inventory levels are filled in with the average value from the past.

[1045] Step 3:

[1046] The server inputs the preprocessed data into the generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[1047] Step 4:

[1048] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[1049] Step 5:

[1050] The server collects user emotion data from the emotion engine, which is obtained by facial expression recognition during user operation, tone analysis of voice, and emotion analysis of input text.

[1051] Step 6:

[1052] The server inputs the acquired emotion data into a generative model and further optimizes the price for each desired delivery date of the product based on the user's emotions.

[1053] Step 7:

[1054] The server stores the calculated price information in a database and transmits it to the terminal.

[1055] Step 8:

[1056] The terminal provides an interface for the user to select the product they wish to purchase, and once the user has selected the product, it sends a request for information about that product to the server.

[1057] Step 9:

[1058] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[1059] Step 10:

[1060] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[1061] Step 11:

[1062] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[1063] Step 12:

[1064] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[1065] Step 13:

[1066] The server checks the received order information, confirms inventory, payment, and the validity of driver availability. Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment.

[1067] Step 14:

[1068] The server generates a personalized marketing message according to the user's emotions based on the emotion engine and transmits it to the terminal.

[1069] Step 15:

[1070] The terminal displays the marketing message received from the server to the user. For example, if it is determined that the user is in a hurry, an announcement about an immediate delivery service is displayed.

[1071] Step 16:

[1072] The logistics center will prepare the product based on the received information and deliver it on the specified date.

[1073] In this way, the server, terminal, and user play their respective roles at each step, resulting in a system that efficiently collects, processes, learns, sets prices, confirms orders, and delivers. Furthermore, by collecting and utilizing emotional data, the system aims to provide more personalized services and improve customer satisfaction.

[1074] Example 2

[1075] 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."

[1076] The logistics industry is facing significant challenges due to labor shortages and declining operational efficiency, which are resulting in declining customer satisfaction. Furthermore, traditional pricing systems have difficulty providing personalized prices and delivery schedules that reflect each user's needs and emotions. This results in an unoptimized user experience, which can further worsen customer satisfaction. Therefore, there is a need for a system that collects diverse data in real time and provides optimal pricing and delivery schedules based on user emotions.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1078] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for transmitting the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for collecting user emotion data; means for individually optimizing the price and desired delivery date based on the emotion data; and means for receiving the price and order information for the selected desired delivery date and processing the order. This makes it possible to address labor shortages and declining business efficiency and provide flexible and efficient pricing and delivery options that respond to user emotions.

[1079] A "logistics center" is a facility where packages are stored, managed, sorted, and prepared for delivery.

[1080] "Storage conditions" refers to the physical and environmental conditions inside the logistics center, including temperature, humidity, lighting, and storage space.

[1081] "Inventory quantity" refers to the quantity of products, goods, and materials stored in a logistics center.

[1082] "Driver availability" refers to delivery driver staffing, shifts, and the number of available drivers.

[1083] "Road conditions on the day of delivery" refers to the traffic and road conditions on the day that affect the delivery of goods. Specifically, this includes information on traffic congestion and prohibited activities.

[1084] "Weather" means meteorological conditions that affect the planning and execution of a Delivery, including, but not limited to, rain, snow, wind speed, and temperature.

[1085] A "generative model" is an algorithm that learns patterns and predictions from data and generates results for new data inputs.

[1086] "Emotional data" refers to information that indicates the user's emotional state as analyzed from facial expressions, tone of voice, and text.

[1087] "Terminal" refers to the device used by a user to operate the system, including smartphones, tablets, personal computers, etc.

[1088] "User" refers to an individual or organization that uses the system to purchase products and receive delivery services.

[1089] "Optimization" is the process of making adjustments to obtain the most effective and efficient results under given conditions and constraints.

[1090] "Pricing" refers to the process of determining the price of your product offerings, specifically setting prices based on cost, demand, competition, and other market factors.

[1091] "Desired delivery date" refers to the specific date on which the user wishes to receive the product.

[1092] "Order processing" refers to the series of processes that involve accepting an order from a user, communicating it to the logistics center or delivery staff, and then putting it into action.

[1093] This invention is a system for improving labor shortages and declining business efficiency in the logistics industry and improving customer satisfaction. A specific embodiment of the program for this system will be described below.

[1094] Program processing explanation

[1095] Data collection

[1096] The server collects data in real time from various sensors and management systems installed in the logistics center. For example,

[1097] Data on the state of the interior of the warehouse is obtained from temperature and humidity sensors.

[1098] Inventory quantity data is obtained from the inventory management system.

[1099] Driver availability data is obtained from the human resources management system.

[1100] Road condition data on the day of delivery is obtained from the traffic information system.

[1101] Weather data is obtained from weather information services.

[1102] Additionally, the server collects real-time emotional data from the user's device, including facial expressions, tone of voice, and analysis of input text.

[1103] Data Preprocessing

[1104] The server pre-processes the collected data, removing outliers and filling in missing data. For example, it removes inappropriate temperature sensor data and fills in missing inventory data from past data.

[1105] Learning with generative models

[1106] Preprocessed logistics data and sentiment data are input into a generative AI model. The generative model learns optimal pricing patterns based on past data and the current situation. It is preferable to use a multi-layer neural network (DNN) for the generative AI model used.

[1107] Processing user requests

[1108] When a user selects a product to purchase on the terminal, the terminal sends that information to the server. The server calculates the price of the selected product for each desired delivery date and sends that information to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[1109] Optimization and individual adjustment

[1110] The device collects the user's emotions in real time and sends the data to a server, which then individually optimizes the product price and desired delivery date based on the emotion data. For example, if the server determines that the user is in a hurry, it will present an option for immediate delivery and adjust the price.

[1111] Processing after order confirmation

[1112] When a user confirms an order, the server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order is confirmed, the information is sent to the logistics center for shipping preparation. The logistics center prepares the product according to the instructions and delivers it on the specified date. In addition, personalized marketing messages based on emotional data are displayed to the user.

[1113] Specific examples

[1114] For example, if data collected from a logistics center indicates that there is abundant inventory and road conditions are good, the generative model will set prices such as "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." On the other hand, if there is little inventory and road conditions are congested, the model will set prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[1115] In addition, the service is optimized based on the user's emotional data, and if it determines that the user is in a hurry, it will suggest immediate delivery. Such personalized suggestions will improve user satisfaction.

[1116] Prompt Sentence Examples

[1117] Here are some examples of specific prompts:

[1118] "Design a system that collects data from various sensors and management systems in a distribution center and retrieves user sentiment data from an emotion engine. Explain how you can use this data to leverage a generative AI model that learns optimal pricing patterns and provides personalized delivery options to users."

[1119] In this way, through the embodiments of the invention, it is possible to improve customer satisfaction and business efficiency.

[1120] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1121] Step 1:

[1122] The server starts collecting data.

[1123] Input: Data from various sensors in the logistics center, inventory data from the inventory management system, road condition data from the traffic information system, weather data from the weather information service, and driver availability data from the human resources management system.

[1124] Data processing: The server collects these data in real time and stores them in a database.

[1125] Output: A collection of raw data.

[1126] How it works: Every minute, the server automatically pulls sensor data and executes a script to store it in a database. It also periodically calls APIs from inventory management systems, traffic information systems, human resources management systems, and weather information services to collect data.

[1127] Step 2:

[1128] The server pre-processes the data.

[1129] Input: Raw data collected in step 1.

[1130] Data processing: Removal of outliers, imputation of missing data.

[1131] Output: Preprocessed clean data.

[1132] Specific operation: The server runs an algorithm to detect outliers, removes any detected outliers, and performs a filtering process to fill in missing data with predicted values ​​based on similar data from the past.

[1133] Step 3:

[1134] The server inputs data into the generative model and performs learning.

[1135] Input: Preprocessed clean data.

[1136] Data processing: The data input and learning process for generative AI models.

[1137] Output: Optimal pricing pattern.

[1138] How it works: The server feeds the preprocessed data into a generative AI model (a multi-layer neural network), which then learns optimal pricing patterns based on past data and current conditions. The model is periodically retrained to adapt to new data.

[1139] Step 4:

[1140] The terminal sends an input request from the user.

[1141] Input: Product selection information by the user.

[1142] Data processing: Transmission of user-entered information.

[1143] Output: The request data sent to the server.

[1144] Specific operation: The user selects the desired product on the terminal and sends the selection information to the server as a request. This request includes information about the selected product and the user ID.

[1145] Step 5:

[1146] The server calculates the pricing data and sends it to the terminal.

[1147] Input: Request data from users, optimal pricing patterns from the generative model.

[1148] Data processing: Calculate the price for each desired delivery date for the requested item.

[1149] Output: Calculated price information.

[1150] Specific operation: Based on the pricing patterns obtained from the generative model, the server calculates the price for each desired delivery date for the product corresponding to the user's request and sends the price information to the terminal.

[1151] Step 6:

[1152] The device displays the results to the user and collects emotional data in real time.

[1153] Input: Price information sent from the server, user sentiment data.

[1154] Data processing: Displaying price information and collecting sentiment data.

[1155] Output: Displayed price information, collected sentiment data.

[1156] Specific operation: The terminal displays the received price information to the user. In addition, the terminal analyzes the user's facial expressions, tone of voice, and text input, and collects real-time emotional data through the emotion engine. This data is then sent to the server.

[1157] Step 7:

[1158] The server performs optimization and determines the final price and desired delivery date.

[1159] Input: sentiment data, preprocessed logistics data, pricing patterns using a generative model.

[1160] Data processing: Optimizing price and desired delivery date based on sentiment data.

[1161] Output: Final adjusted price information and desired delivery date.

[1162] Specific operation: The server analyzes the emotion data and adjusts the price and desired delivery date based on the user's level of urgency and satisfaction. For example, if a user is in a hurry, it will present the option of same-day delivery and its price.

[1163] Step 8:

[1164] The user selects the desired delivery date and confirms the order.

[1165] Input: The last price information displayed on the device and the desired delivery date.

[1166] Data processing: Sending the user's selected delivery date and price information.

[1167] Output: Confirmed order data.

[1168] Specific operation: The user selects the desired delivery date based on the information displayed on the terminal and finalizes the order. After confirming the order, the user enters the necessary payment information and sends it to the server.

[1169] Step 9:

[1170] The server checks the order information and sends instructions to the logistics center.

[1171] Input: Confirmed order data.

[1172] Data processing: Checking inventory, payment, and driver availability.

[1173] Output: Shipping instruction data to the logistics center.

[1174] Specific operation: The server checks the received order information, checks the validity of the inventory and payment, and if there are no problems, sends instructions to the logistics center to prepare for shipment.

[1175] Step 10:

[1176] The logistics center prepares the products and delivers them on the specified date.

[1177] Input: Shipping instruction data from the server.

[1178] Data processing: Product preparation and delivery planning.

[1179] Output: The delivered item.

[1180] Specific operation: The logistics center prepares the product according to instructions from the server, and delivers the product by a delivery driver on the specified date. It also delivers personalized messages and special offers to users based on their emotional data.

[1181] (Application example 2)

[1182] 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."

[1183] Labor shortages and declining operational efficiency are serious issues in the logistics industry. Furthermore, while there is a demand for flexible service provision that responds to user emotions and individual needs, this has not been fully realized. Therefore, a method is needed to simultaneously achieve efficient management and personalized service provision.

[1184] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and user emotion data and calculating the optimal price for each desired delivery date; means for sending a personalized message based on the calculated price information and emotion data to the terminal so that the user can confirm and select a price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for collecting emotion data and performing emotion analysis in real time. This makes it possible to provide an efficient and personalized delivery service.

[1185] A "logistics center" is a facility that centralizes logistics operations such as storing, sorting, packaging, shipping, and delivering packages.

[1186] "Storage status" is data that indicates the storage status of inventory and the progress of work within the logistics center.

[1187] "Stock quantity" is data indicating the quantity of products stored in the logistics center.

[1188] "Driver availability status" is data that indicates the status and number of drivers available for delivery at the logistics center.

[1189] "Road conditions on the day of delivery" is data indicating road traffic conditions and congestion information on the day of delivery.

[1190] "Weather" is data indicating the weather conditions on the delivery date.

[1191] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, tone of voice, input text, and the like.

[1192] A "generative model" is an algorithm that uses machine learning based on collected data to generate optimal results for new data.

[1193] A "personalized message" is a personalized message created based on the emotional data and past behavior of an individual user.

[1194] A "terminal" is an electronic device that allows a user to obtain information or send instructions.

[1195] "Order information" is data including the product selected by the user, desired delivery date, price, payment method, etc.

[1196] "Emotion analysis" is a process of analyzing the user's emotional state based on collected emotional data.

[1197] This invention aims to build an efficient delivery management system in a logistics center and improve user satisfaction. A specific method for implementing each step will be described below.

[1198] System Configuration

[1199] The present invention uses the following hardware and software:

[1200] Hardware: sensors, servers, smartphones

[1201] Software: Data collection API, sentiment analysis engine, generative model

[1202] Program processing

[1203] Data collection

[1204] The server collects the following data in real time from sensors and management systems within the distribution center:

[1205] Warehouse status

[1206] Quantity in stock

[1207] Driver availability

[1208] Road conditions on the day of delivery

[1209] weather

[1210] The collected data is preprocessed to make it suitable for analysis by removing outliers and filling in missing data. If the device operated by the user is a smartphone, the user's facial expression, tone of voice, and input text are analyzed by an emotion analysis engine to extract emotional data.

[1211] Optimal price calculation using generative models

[1212] The server inputs the pre-processed data and sentiment data into a generative model to determine the optimal price based on past data and the current situation. For example, a Python script like the following can be used:

[1213] python

[1214] import numpy as np

[1215] import pandas as pd

[1216] from datetime import datetime

[1217] import requests

[1218] from sklearn.linear_model import LinearRegression

[1219] Data collection function definition

[1220] def collect_data():

[1221] Sensor data collection

[1222] warehouse_data = requests.get('https: / / api.warehouse.com / data').json()

[1223] Collecting Emotional Data

[1224] emotion_data = requests.get('https: / / api.emotionengine.com / data').json()

[1225] return warehouse_data, emotion_data

[1226] Emotional Data Analysis

[1227] def analyze_emotion(emotion_data):

[1228] Tentative emotion analysis results

[1229] emotion_score = np.mean([item['score'] for item in emotion_data])

[1230] return emotion_score

[1231] Optimal Price Calculation

[1232] def calculate_optimal_price(warehouse_data, emotion_score, delivery_days):

[1233] factors = [warehouse_data['stock_level'], warehouse_data['traffic'],

[1234] warehouse_data['driver_availability'], emotion_score]

[1235] Hypothetical pricing model

[1236] model = LinearRegression()

[1237] X = np.array(factors).reshape(-1, 1)

[1238] y = np.array([1000, 950, 900]) Historical price data

[1239] model.fit(X, y)

[1240] optimal_price = model.predict([[factors + [delivery_days]]])

[1241] return optimal_price

[1242] Displaying pricing information and messages

[1243] The terminal displays a personalized message to the user based on the price information and emotion data for each desired delivery date received from the server. The user confirms the desired delivery date and price of the product through the terminal and selects the desired delivery date.

[1244] Order confirmation and processing

[1245] The price and order information for the delivery date selected by the user are sent from the terminal to the server. Based on the received order information, the server checks inventory, confirms payment, secures a driver, and arranges delivery.

[1246] Specific examples

[1247] Consider the following real-world scenario:

[1248] If there is an abundance of stock and transportation is smooth, the server sets the prices as follows: "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." If the user selects one week later delivery, the emotion engine determines that the user is highly satisfied, and a thank you message is displayed on the device.

[1249] Prompt Sentence Examples

[1250] Here are some example prompts to input to the generative AI model:

[1251] We want to build an efficient delivery management system for our logistics center. Please calculate the optimal delivery fee based on the following data:

[1252] Warehouse conditions (inventory, traffic conditions, driver availability, weather)

[1253] Emotional data of drivers and staff (facial expressions, tone of voice, input text)

[1254] As a result, offer the best delivery price for a desired delivery date three days from now.

[1255] The above is a specific embodiment for carrying out the present invention. This system improves the operational efficiency of a logistics center and increases user satisfaction.

[1256] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1257] Step 1:

[1258] The server collects data from sensors and management systems at the logistics center. Inputs include warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. Data is collected through an API. Output is preprocessed data. Specifically, it receives list data from sensors, converts it to JSON format and saves it.

[1259] Step 2:

[1260] The server collects emotional data from the user's smartphone. Inputs include the user's facial expressions, tone of voice, and input text. The data is collected by an emotion analysis engine. The output is analyzed emotional data. Specifically, the system captures data in real time using the smartphone's camera and microphone and sends it to the analysis engine.

[1261] Step 3:

[1262] The server pre-processes the collected data. The input is the data on warehouse conditions, inventory, driver availability, road conditions, weather, and user emotions. Outliers are removed and missing data is complemented. The output is the pre-processed data. Specific operations include replacing outliers with standard values ​​and complementing missing values ​​with the average value.

[1263] Step 4:

[1264] The server inputs the preprocessed data into a generative model to calculate the optimal delivery price. The input is the preprocessed warehouse data and emotion data. The output is the calculated price information for each desired delivery date. Specifically, the data is input into a generative model (e.g., a linear regression model) and an adapted price is calculated.

[1265] Step 5:

[1266] The server sends a personalized message based on the calculated price information and emotion data to the device. The input is the calculated price information and analyzed emotion data. The output is the price information and message displayed on the user's device. Specifically, the server sends data in JSON format via an API, and the text and price information are displayed on the device.

[1267] Step 6:

[1268] The user selects the desired delivery date and price of the product through the terminal. The input is the price information and personalized message sent from the server. The output is the selected desired delivery date and price. In concrete terms, the user operates the touch screen to select the desired delivery date and price.

[1269] Step 7:

[1270] The terminal sends the price for the selected desired delivery date and order information to the server. The input is the desired delivery date and price selected by the user. The output is the order information sent to the server. Specifically, the terminal sends the order information in JSON format to the server via the API.

[1271] Step 8:

[1272] Based on the order information received by the server, it checks inventory, confirms payment, and arranges for a driver. The input is the order information sent from the terminal. The output is the status of delivery arrangement completion. Specifically, it accesses the inventory management system and payment gateway to carry out the necessary confirmation work.

[1273] The above steps enable efficient delivery management at the logistics center, thereby improving user satisfaction.

[1274] 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.

[1275] 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.

[1276] 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.

[1277] [Fourth embodiment]

[1278] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1279] 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.

[1280] 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).

[1281] 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.

[1282] 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.

[1283] 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).

[1284] 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.

[1285] 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.

[1286] 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.

[1287] 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.

[1288] 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.

[1289] 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.

[1290] 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."

[1291] This invention is a dynamic pricing system that addresses the 2024 problem in the logistics industry by using a generative model to calculate the optimal price for each desired delivery date based on information such as the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and allowing users to select a delivery date.

[1292] 1. Server Processing

[1293] The server first collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[1294] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[1295] 2. Terminal Processing

[1296] When a user selects a product they wish to purchase using a device (smartphone, tablet, PC, etc.), the device sends a request to the server. In response to the request, the server sends price information for the selected product for each desired delivery date to the device. The device displays this information to the user, allowing them to select the desired delivery date. For example, for product A, the device presents price information such as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[1297] 3. User Operation

[1298] The user uses the terminal to select the product they wish to purchase and then select the desired delivery date. They confirm the displayed price, specify the payment method, and confirm the order. For example, if a user requests delivery of product A in one week, agrees to the price of 1,100 yen, and proceeds with the purchase, the order data is sent from the terminal to the server.

[1299] 4. Processing after order confirmation

[1300] The server verifies the received order data and checks the validity of the order (including inventory confirmation, payment confirmation, and driver availability). Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment and arrange for delivery. For example, if there is sufficient stock of product A and a driver is available, the logistics center will prepare the product and deliver it to the specified address one week later.

[1301] Specific examples

[1302] As a specific scenario, consider the following case.

[1303] 1. When inventory is abundant and traffic is smooth: The server collects data from the logistics center and determines that inventory is abundant and road conditions are good. The generative model sets prices based on this information, for example, "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." The user selects a product through their terminal, requests delivery one week later, and pays 800 yen.

[1304] 2. When inventory is low and traffic is congested: The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the price is confirmed by paying 1,500 yen, and the server sends this information to the logistics center.

[1305] In this way, logistics efficiency can be optimized while customer satisfaction can be increased.

[1306] The processing flow will be explained below.

[1307] Step 1:

[1308] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[1309] Step 2:

[1310] The server performs preprocessing on the collected information, removing outliers and filling in missing data. For example, it filters out abnormal values ​​from a temperature sensor and fills in missing data with the historical average.

[1311] Step 3:

[1312] The server inputs the preprocessed data into a generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[1313] Step 4:

[1314] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[1315] Step 5:

[1316] The server stores the calculated price information in a database and makes it available for user reference.

[1317] Step 6:

[1318] The terminal provides an interface for the user to select the product they wish to purchase, and when the user selects a product, it sends a request for information about that product to the server.

[1319] Step 7:

[1320] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[1321] Step 8:

[1322] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[1323] Step 9:

[1324] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[1325] Step 10:

[1326] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[1327] Step 11:

[1328] The server verifies the received order information, stores it in a database, and checks the validity of the order (including stock availability, payment confirmation, driver availability, etc.).

[1329] Step 12:

[1330] The server then sends the confirmed order details to the relevant departments at the logistics center to prepare for shipment and arrange for delivery. The logistics center then prepares the products based on the received information and delivers them on the specified date.

[1331] In this way, the server, terminal, and user play their respective roles at each step, realizing a system that efficiently collects data, processes data, learns data, sets prices, confirms orders, and delivers data.

[1332] Example 1

[1333] 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."

[1334] In recent years, efficient delivery management and improved customer satisfaction have become important issues in the logistics industry. However, conventional systems have had difficulty in setting prices in real time based on daily changes in inventory, road conditions, and weather. This has led to problems such as inability to set optimal prices, making it difficult to efficiently manage inventory and minimize delivery costs. In addition, customers have limited options for selecting an appropriate price based on their desired delivery date, limiting the improvement of customer satisfaction.

[1335] 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.

[1336] In this invention, the server includes a means for collecting information on the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of transportation, and weather information, a means for preprocessing the collected information to remove outliers and fill in missing data, and a means for performing learning using a generative model based on the preprocessed information to calculate the optimal price for each desired delivery date of the product. This enables optimal pricing according to conditions that change daily, minimizes inventory management and delivery costs, and provides customers with the option to purchase products at the optimal price according to their desired delivery date.

[1337] "Conditions within the logistics center" refers to environmental conditions within the logistics center, such as temperature, humidity, and storage space utilization, as well as the current state of operations within the warehouse.

[1338] "Inventory" refers to the total number and type of products stored in a particular warehouse or distribution center.

[1339] "Driver availability" refers to whether drivers for delivery work have been reliably arranged and their operating status.

[1340] "Traffic conditions on the day of transportation" refers to the degree of road congestion and traffic conditions on the day the goods are transported.

[1341] "Weather information" refers to information about the weather on the day of transportation and before and after, such as rainfall, snowfall, wind speed, temperature, etc.

[1342] "Means of collection" refers collectively to sensors used to obtain necessary data from logistics centers and external sources, as well as software and hardware for accessing databases.

[1343] "Preprocessing means" refers to a method and device in general for removing outliers and filling in missing data from collected data, preparing the data for subsequent analysis and learning.

[1344] "Outlier removal" refers to the process of eliminating obviously abnormal values ​​from collected data, such as physically impossible temperature or humidity data.

[1345] "Missing data imputation" refers to the process of filling in missing values ​​in collected data, for example, using past data or average values.

[1346] A "generative model" is an AI model that learns patterns based on collected and preprocessed data and generates appropriate outputs in response to new inputs.

[1347] "Optimal price" refers to the most economically efficient price set according to the desired delivery date of the product, based on customer demand and the logistics provider's supply conditions.

[1348] "Means for calculating" refers collectively to algorithms and computer software for calculating optimal prices using generative models.

[1349] "Terminal" refers to an electronic device that can connect to the Internet, such as a smartphone, tablet, or personal computer used by a user.

[1350] "User" refers to an individual or corporation that uses the System to purchase products and use delivery services.

[1351] "Order processing" refers to a series of processes based on a purchase request received from a user, from checking inventory to confirming payment and completing delivery arrangements.

[1352] The present invention relates to a dynamic pricing system for the logistics industry. This system aims to improve logistics efficiency and customer satisfaction by collecting variable factors, particularly the status of logistics centers, inventory levels, driver availability, traffic conditions on the day of delivery, and weather information, in real time and setting optimal delivery prices based on the collected data.

[1353] 1. Data Collection

[1354] The server collects data in real time from various sensors and management systems within the logistics center. This data includes the warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Specifically, the central management server periodically obtains JSON-formatted data from each sensor, and uses it to manage, for example, temperature sensors, humidity sensors, inventory management systems, and driver management systems.

[1355] 2. Data Preprocessing

[1356] The server preprocesses the collected data, removing outliers and filling in missing data. For example, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), it will remove them, and missing inventory data will be filled in with the average inventory level from the past.

[1357] 3. Generative pricing

[1358] The server inputs the preprocessed data into a generative model (e.g., OpenAI GPT-4). The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. For example, the model compares prices with past days when inventory was low and sets a new price based on similar patterns. This set price is then stored in a database.

[1359] 4. Processing User Requests

[1360] When a user opens a specific product page, the device sends a request to the server. The request includes a product ID, and when a user displays the page for product A on their smartphone, the product ID is sent to the server.

[1361] 5. Price information for desired delivery date

[1362] The server receives the request sent from the device and retrieves the price information for the corresponding product for each desired delivery date from the database. The price information is sent to the device in JSON format. For example, data such as "next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen" is sent.

[1363] 6. User Purchase Process

[1364] The user checks the price information displayed on the device, selects the desired delivery date, and then selects a payment method to proceed with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card.

[1365] 7. Order confirmation and confirmation

[1366] The server verifies the purchase request received from the user, checks the product inventory, payment confirmation, and driver availability. For example, it retrieves the product inventory from the inventory database and confirms payment via the payment gateway.

[1367] 8. Arrangements after order confirmation

[1368] After the server confirms the order, it notifies the relevant departments at the logistics center. The logistics center then prepares shipment and arranges delivery based on the received information. For example, it sends picking instructions for product A to the warehouse system and updates the schedule to arrange for a driver.

[1369] Specific examples

[1370] Let's say a user wants to purchase Product A. In this case, when the user opens the page for Product A on their smartphone, the device sends Product A's ID to the server. The server retrieves price information for that product for each desired delivery date from the database and sends the following data: "Next day delivery: 1,500 yen," "3 days later delivery: 1,300 yen," and "1 week later delivery: 1,100 yen." The user checks this, selects delivery one week later, agrees to the price of 1,100 yen, and proceeds with the purchase. This order request is checked for inventory and payment on the server side, and if there are no problems, a picking instruction is sent to the logistics center and a driver is arranged.

[1371] Prompt Sentence Examples

[1372] "Calculate the optimal price for each desired delivery date based on the following information: warehouse status, inventory quantity, driver availability, road conditions and weather on the delivery day. For example, please provide an example of pricing when inventory is low and road conditions are poor."

[1373] This system will enable us to optimize logistics efficiency while improving customer satisfaction.

[1374] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1375] Step 1: Data collection

[1376] The server automatically collects real-time data from various sensors and management systems within the logistics center. Input data includes warehouse conditions (temperature, humidity, etc.), inventory levels, driver availability, traffic conditions on the day of transportation, and weather information. Data is acquired in JSON format and is obtained specifically from temperature sensors, humidity sensors, inventory management systems, and driver management systems. The output is a raw data set.

[1377] Step 2: Data Preprocessing

[1378] The server performs preprocessing on the collected raw dataset. The raw dataset is input. The preprocessing involves removing outliers and filling in missing data. Specifically, if the recorded temperature data shows extreme values ​​(e.g., 50°C or -20°C), that data is removed, and missing inventory data is filled in with the average inventory quantity from the past. As a result of the processing, a clean dataset is output.

[1379] Step 3: Generative pricing

[1380] The server inputs the clean dataset into a generative model (e.g., OpenAI GPT-4). The input is the preprocessed clean dataset. The generative model learns from past data and the current situation and calculates the optimal price for each desired delivery date. This price is calculated by comparing the model with past low inventory days and prices, and setting a new price based on similar patterns. The output is pricing information for each desired delivery date.

[1381] Step 4: Process the user request

[1382] When a user opens a specific product page, the device sends a product request to the server. The input is a request that includes the product ID. For example, when a user displays the page for product A on a smartphone, the ID of product A is sent to the server. The output is a response to the corresponding product ID request.

[1383] Step 5: Submit price information for desired delivery date

[1384] The server receives the product request sent from the terminal and retrieves price information for the corresponding product for each desired delivery date from the database. The input is the product ID request. The data is sent in JSON format, and price information is sent to the terminal. Specifically, price information is provided in the form of "next day delivery: 1,500 yen," "3-day delivery: 1,300 yen," and "1 week later delivery: 1,100 yen."

[1385] Step 6: User checkout

[1386] The user checks the price information displayed on the terminal and selects the desired delivery date. The price information displayed on the terminal and the selected delivery date are input. The user then selects a payment method and proceeds with the purchase. For example, the user selects next-day delivery and clicks the option to pay by credit card. The purchase request is sent to the server, and a purchase confirmation response is output.

[1387] Step 7: Order confirmation and confirmation

[1388] The server verifies the purchase request received from the user. The input is a purchase request. The server checks the product's inventory, payment confirmation, and driver availability. Specifically, it retrieves the product's inventory from the inventory database and confirms payment via the payment gateway. Once the order is confirmed, it is notified to the logistics center, and a final order confirmation response is output.

[1389] Step 8: Arrangements after order confirmation

[1390] After the server confirms the order, it notifies the relevant departments at the logistics center of the information. The confirmed order information is input. The logistics center prepares for shipment and arranges delivery based on the received information. Specifically, it sends a picking instruction for product A to the warehouse system and updates the schedule to arrange for a driver. The output is a notification that shipment preparation is complete and delivery information.

[1391] In this way, logistics operations are carried out efficiently and effectively.

[1392] (Application example 1)

[1393] 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."

[1394] The logistics industry is seeking more efficient inventory management and delivery scheduling. Real-time management is particularly important, taking into account not only warehouse conditions and inventory levels, but also driver availability, road conditions, weather, and other fluctuating factors. However, this information is not centrally managed, creating problems for staff who are unable to respond efficiently. Additionally, a system is needed that allows users to check and select prices for each desired delivery date, but current methods are insufficient.

[1395] 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.

[1396] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for sending the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for displaying information in real time within the logistics center using smart glasses to improve staff work efficiency. This makes it possible to build a system that improves the efficiency of inventory management and delivery operations within the logistics center and allows users to check the optimal price in real time.

[1397] A "logistics center" is a facility that serves as a base for storing and distributing goods.

[1398] "Warehouse status" refers to information about the current state, layout, and inventory distribution within the logistics center.

[1399] "Stock quantity" is a numerical value indicating the quantity of products stored in the logistics center.

[1400] "Driver availability" refers to the number of drivers performing delivery duties at the logistics center and their schedules.

[1401] "Road conditions" refers to information such as traffic volume and congestion on roads used as delivery routes.

[1402] "Weather" refers to the weather forecast and weather conditions on the day of delivery.

[1403] A "generative model" is a type of machine learning model that is trained to derive optimal results based on specified data.

[1404] "Optimal price" refers to the most reasonable price for the desired delivery date calculated by the generative model based on the collected data.

[1405] A "terminal" is a device that allows a user to input and check information, and specifically includes smartphones, tablets, and PCs.

[1406] "Smart glasses" are a wearable eyeglass-type device that has the ability to display information on a screen in real time.

[1407] "Users" refers to people who use the system, including general consumers and logistics center staff.

[1408] "Order processing" refers to receiving order information from a user and completing a series of procedures such as checking inventory, confirming payment, and arranging delivery.

[1409] This invention will be described as an example of application in a logistics center management system using smart glasses.

[1410] Overall system configuration

[1411] The system collects information such as warehouse conditions at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, and uses a generative model to calculate the optimal price for each desired delivery date. This information is presented to staff in the logistics center in real time using smart glasses. The system also allows users to check and select prices for each desired delivery date, and processes orders.

[1412] Server Processing

[1413] The server collects real-time data from various sensors and management systems within the logistics center. This data includes warehouse conditions, inventory levels, driver availability, road conditions, and weather on the day of delivery. The collected data is preprocessed to remove outliers and fill in missing data. For example, abnormal temperature and humidity values ​​are filtered out, and missing inventory data is filled in with historical average values.

[1414] The preprocessed data is input into a generative model, which learns optimal pricing patterns by comparing past data with the current situation. For example, if the desired delivery date is the next day, the price will be higher for items with low stock, while if the desired delivery date is one week later, the price will be set lower. In this way, the optimal price for each desired delivery date for each item is calculated and stored in a database.

[1415] Smart Glasses Processing

[1416] The smart glasses are worn by staff in the distribution center and receive and display the information they need in real time while they work. Information such as collected inventory levels, driver availability, prices for each desired delivery date, road conditions, and weather is visually displayed through a HUD (head-up display). This allows staff to work efficiently while moving around the warehouse.

[1417] For example, a staff member checking an inventory list can use smart glasses to check the stock levels of each product in real time and make necessary replenishments or rearrangements. They can also instantly check the latest information on drivers scheduled for delivery and road conditions, enabling quick decision-making.

[1418] Hardware and software used

[1419] Hardware: Smart glasses such as Epson Moverio and Vuzix Blade.

[1420] Software: API communication library (requests) and HUD display library for smart glasses.

[1421] Specific examples

[1422] For example, the following scenario can occur within a logistics center:

[1423] Staff checking the inventory list can instantly check information such as "Quantity in stock: 150," "Driver availability: stable," and "Delivery price: 1,200 yen" through the smart glasses, dramatically improving work efficiency.

[1424] Prompt Sentence Examples

[1425] "A method of using smart glasses to manage inventory and deliveries within a distribution center. The glasses display real-time inventory levels, driver availability, pricing information for each desired delivery date, and road and weather conditions, improving the efficiency of staff work."

[1426] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1427] Step 1:

[1428] The server collects real-time data from various sensors and management systems within the logistics center. This data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected data is input and stored in a database.

[1429] Step 2:

[1430] The server performs preprocessing on the collected data, removing outliers and filling in missing data. For example, it filters out abnormal temperature and humidity values, and fills in missing inventory data with historical average values. The preprocessed data is used as input for the next calculation.

[1431] Step 3:

[1432] The server inputs the preprocessed data into a generative model to learn optimal pricing patterns. The generative model compares past data with the current situation to calculate the optimal price for each desired delivery date for each product. The calculated optimal price is saved as output in a database.

[1433] Step 4:

[1434] The terminal sends a request to the server to obtain price information for each desired delivery date for the product selected by the user. The terminal displays the obtained price information to the user. The user selects a desired delivery date as input and sends that information to the server.

[1435] Step 5:

[1436] The server receives the price and order information for the delivery date selected by the user. Based on the received order information, it carries out a series of order processes, including checking inventory, confirming payment, and securing a driver. Once the order process is complete, it forwards the information to the relevant department.

[1437] Step 6:

[1438] The smart glasses display information collected from the server to the operatives in real time, such as inventory levels, driver availability, delivery prices by desired delivery date, road conditions, and weather, on the HUD. This allows the operatives to work efficiently within the logistics center.

[1439] 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.

[1440] This invention combines an emotion engine with a dynamic pricing system to address labor shortages and declining operational efficiency in the logistics industry and improve customer satisfaction. The system collects data on the warehouse situation at the logistics center, inventory levels, driver availability, road conditions and weather on the day of delivery, as well as user emotion data, and uses a generative model to calculate the optimal price for each desired delivery date. It also optimizes prices and desired delivery dates individually based on the user's emotion data and displays personalized marketing messages.

[1441] 1. Server Processing

[1442] First, the server collects data in real time from various sensors and management systems within the logistics center. The collected data includes the warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. The collected information is pre-processed to remove outliers and fill in missing data.

[1443] The server also collects emotional data from the user's emotion engine, such as facial expressions, tone of voice, and analysis results of entered text, obtained from the device during user operation. The preprocessed data and emotional data are input into a generative model, which then learns optimal pricing patterns based on past data and the current situation.

[1444] 2. Terminal Processing

[1445] When a user selects a product they wish to purchase using a terminal, the terminal sends a request to the server. The server calculates the price information for each desired delivery date for the selected product and sends it to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[1446] The device also collects real-time emotional data from the user's emotion engine and sends it to the server, which then individually optimizes product prices and desired delivery dates.

[1447] 3. User Operation

[1448] The user uses the device to select a product and a desired delivery date, confirm the displayed price, confirm the order, specify a payment method, and enter the required information. The user's emotions may also be communicated to the system, which may adjust the price and delivery date options accordingly.

[1449] 4. Processing after order confirmation

[1450] The server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order details are confirmed, the relevant information is sent to the logistics center to prepare for shipment. The logistics center prepares the product according to the instructions and delivers it on the specified date. Additionally, personalized marketing messages are displayed to users based on their emotional data.

[1451] Specific examples

[1452] As a specific scenario, consider the following case.

[1453] 1. When inventory is abundant and transportation is smooth:

[1454] The server collects data from the logistics center and determines that there is abundant inventory and road conditions are good. The generative model uses this information to set prices, determining the following: next-day delivery: 1,000 yen, three-day delivery: 900 yen, and one-week delivery: 800 yen. The user selects a product via their device and requests delivery one week later. The emotion engine determines that the user is highly satisfied, and a personalized thank-you message is displayed. The user pays 800 yen and confirms the order.

[1455] 2. When inventory is low and traffic is heavy:

[1456] The server similarly collects data and confirms that inventory is low and road conditions are congested. The generative model learns this and sets the prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen." If the user selects next day delivery, the emotion engine determines that the user is in a hurry, and an immediate delivery service is displayed. The user pays 1,500 yen and confirms the order.

[1457] In this way, by combining the emotion engine, it becomes possible to provide flexible and efficient pricing and delivery options that respond to the user's emotions.

[1458] The processing flow will be explained below.

[1459] Step 1:

[1460] The server collects real-time information from various sensors and management systems at the logistics center, including warehouse conditions, inventory levels, driver availability, road conditions and weather information on the day of delivery.

[1461] Step 2:

[1462] The server preprocesses the collected information, filtering out outliers and filling in missing data. For example, if a temperature sensor in a warehouse reports an abnormal value, the data is filtered out. Missing inventory levels are filled in with the average value from the past.

[1463] Step 3:

[1464] The server inputs the preprocessed data into the generative model, which then trains it to generate optimal pricing patterns based on past data and the current situation.

[1465] Step 4:

[1466] The server calculates the optimal price for each desired delivery date for each product based on the learning results obtained from the generative model. For example, the price is set higher for next-day delivery and lower for a desired delivery date one week later.

[1467] Step 5:

[1468] The server collects user emotion data from the emotion engine, which is obtained by facial expression recognition during user operation, tone analysis of voice, and emotion analysis of input text.

[1469] Step 6:

[1470] The server inputs the acquired emotion data into a generative model and further optimizes the price for each desired delivery date of the product based on the user's emotions.

[1471] Step 7:

[1472] The server stores the calculated price information in a database and transmits it to the terminal.

[1473] Step 8:

[1474] The terminal provides an interface for the user to select the product they wish to purchase, and once the user has selected the product, it sends a request for information about that product to the server.

[1475] Step 9:

[1476] The server receives the request from the terminal and transmits price information for the selected product for each desired delivery date to the terminal.

[1477] Step 10:

[1478] The terminal displays the price information received from the server to the user, allowing the user to check the price and select the desired delivery date.

[1479] Step 11:

[1480] The user selects the desired delivery date through the terminal, confirms the price offered, and confirms the order. The user then selects the payment method and enters the necessary information.

[1481] Step 12:

[1482] The terminal sends the order information confirmed by the user to the server, including the product ID, desired delivery date, price, and payment information.

[1483] Step 13:

[1484] The server checks the received order information, confirms inventory, payment, and the validity of driver availability. Once the order is confirmed, the information is sent to the relevant department at the logistics center to prepare for shipment.

[1485] Step 14:

[1486] The server generates a personalized marketing message according to the user's emotions based on the emotion engine and transmits it to the terminal.

[1487] Step 15:

[1488] The terminal displays the marketing message received from the server to the user. For example, if it is determined that the user is in a hurry, an announcement about an immediate delivery service is displayed.

[1489] Step 16:

[1490] The logistics center will prepare the product based on the received information and deliver it on the specified date.

[1491] In this way, the server, terminal, and user play their respective roles at each step, resulting in a system that efficiently collects, processes, learns, sets prices, confirms orders, and delivers. Furthermore, by collecting and utilizing emotional data, the system aims to provide more personalized services and improve customer satisfaction.

[1492] Example 2

[1493] 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."

[1494] The logistics industry is facing significant challenges due to labor shortages and declining operational efficiency, which are resulting in declining customer satisfaction. Furthermore, traditional pricing systems have difficulty providing personalized prices and delivery schedules that reflect each user's needs and emotions. This results in an unoptimized user experience, which can further worsen customer satisfaction. Therefore, there is a need for a system that collects diverse data in real time and provides optimal pricing and delivery schedules based on user emotions.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1496] In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date; means for transmitting the calculated price information to a terminal so that the user can confirm and select the price for each desired delivery date; means for collecting user emotion data; means for individually optimizing the price and desired delivery date based on the emotion data; and means for receiving the price and order information for the selected desired delivery date and processing the order. This makes it possible to address labor shortages and declining business efficiency and provide flexible and efficient pricing and delivery options that respond to user emotions.

[1497] A "logistics center" is a facility where packages are stored, managed, sorted, and prepared for delivery.

[1498] "Storage conditions" refers to the physical and environmental conditions inside the logistics center, including temperature, humidity, lighting, and storage space.

[1499] "Inventory quantity" refers to the quantity of products, goods, and materials stored in a logistics center.

[1500] "Driver availability" refers to delivery driver staffing, shifts, and the number of available drivers.

[1501] "Road conditions on the day of delivery" refers to the traffic and road conditions on the day that affect the delivery of goods. Specifically, this includes information on traffic congestion and prohibited activities.

[1502] "Weather" means meteorological conditions that affect the planning and execution of a Delivery, including, but not limited to, rain, snow, wind speed, and temperature.

[1503] A "generative model" is an algorithm that learns patterns and predictions from data and generates results for new data inputs.

[1504] "Emotional data" refers to information that indicates the user's emotional state as analyzed from facial expressions, tone of voice, and text.

[1505] "Terminal" refers to the device used by a user to operate the system, including smartphones, tablets, personal computers, etc.

[1506] "User" refers to an individual or organization that uses the system to purchase products and receive delivery services.

[1507] "Optimization" is the process of making adjustments to obtain the most effective and efficient results under given conditions and constraints.

[1508] "Pricing" refers to the process of determining the price of your product offerings, specifically setting prices based on cost, demand, competition, and other market factors.

[1509] "Desired delivery date" refers to the specific date on which the user wishes to receive the product.

[1510] "Order processing" refers to the series of processes that involve accepting an order from a user, communicating it to the logistics center or delivery staff, and then putting it into action.

[1511] This invention is a system for improving labor shortages and declining business efficiency in the logistics industry and improving customer satisfaction. A specific embodiment of the program for this system will be described below.

[1512] Program processing explanation

[1513] Data collection

[1514] The server collects data in real time from various sensors and management systems installed in the logistics center. For example,

[1515] Data on the state of the interior of the warehouse is obtained from temperature and humidity sensors.

[1516] Inventory quantity data is obtained from the inventory management system.

[1517] Driver availability data is obtained from the human resources management system.

[1518] Road condition data on the day of delivery is obtained from the traffic information system.

[1519] Weather data is obtained from weather information services.

[1520] Additionally, the server collects real-time emotional data from the user's device, including facial expressions, tone of voice, and analysis of input text.

[1521] Data Preprocessing

[1522] The server pre-processes the collected data, removing outliers and filling in missing data. For example, it removes inappropriate temperature sensor data and fills in missing inventory data from past data.

[1523] Learning with generative models

[1524] Preprocessed logistics data and sentiment data are input into a generative AI model. The generative model learns optimal pricing patterns based on past data and the current situation. It is preferable to use a multi-layer neural network (DNN) for the generative AI model used.

[1525] Processing user requests

[1526] When a user selects a product to purchase on the terminal, the terminal sends that information to the server. The server calculates the price of the selected product for each desired delivery date and sends that information to the terminal. The terminal displays this information to the user, allowing the user to select the desired delivery date.

[1527] Optimization and individual adjustment

[1528] The device collects the user's emotions in real time and sends the data to a server, which then individually optimizes the product price and desired delivery date based on the emotion data. For example, if the server determines that the user is in a hurry, it will present an option for immediate delivery and adjust the price.

[1529] Processing after order confirmation

[1530] When a user confirms an order, the server checks the received order information and checks the validity of inventory, payment, and driver availability. Once the order is confirmed, the information is sent to the logistics center for shipping preparation. The logistics center prepares the product according to the instructions and delivers it on the specified date. In addition, personalized marketing messages based on emotional data are displayed to the user.

[1531] Specific examples

[1532] For example, if data collected from a logistics center indicates that there is abundant inventory and road conditions are good, the generative model will set prices such as "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." On the other hand, if there is little inventory and road conditions are congested, the model will set prices as "next day delivery: 1,500 yen," "three days later delivery: 1,300 yen," and "one week later delivery: 1,100 yen."

[1533] In addition, the service is optimized based on the user's emotional data, and if it determines that the user is in a hurry, it will suggest immediate delivery. Such personalized suggestions will improve user satisfaction.

[1534] Prompt Sentence Examples

[1535] Here are some examples of specific prompts:

[1536] "Design a system that collects data from various sensors and management systems in a distribution center and retrieves user sentiment data from an emotion engine. Explain how you can use this data to leverage a generative AI model that learns optimal pricing patterns and provides personalized delivery options to users."

[1537] In this way, through the embodiments of the invention, it is possible to improve customer satisfaction and business efficiency.

[1538] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1539] Step 1:

[1540] The server starts collecting data.

[1541] Input: Data from various sensors in the logistics center, inventory data from the inventory management system, road condition data from the traffic information system, weather data from the weather information service, and driver availability data from the human resources management system.

[1542] Data processing: The server collects these data in real time and stores them in a database.

[1543] Output: A collection of raw data.

[1544] How it works: Every minute, the server automatically pulls sensor data and executes a script to store it in a database. It also periodically calls APIs from inventory management systems, traffic information systems, human resources management systems, and weather information services to collect data.

[1545] Step 2:

[1546] The server pre-processes the data.

[1547] Input: Raw data collected in step 1.

[1548] Data processing: Removal of outliers, imputation of missing data.

[1549] Output: Preprocessed clean data.

[1550] Specific operation: The server runs an algorithm to detect outliers, removes any detected outliers, and performs a filtering process to fill in missing data with predicted values ​​based on similar data from the past.

[1551] Step 3:

[1552] The server inputs data into the generative model and performs learning.

[1553] Input: Preprocessed clean data.

[1554] Data processing: The data input and learning process for generative AI models.

[1555] Output: Optimal pricing pattern.

[1556] How it works: The server feeds the preprocessed data into a generative AI model (a multi-layer neural network), which then learns optimal pricing patterns based on past data and current conditions. The model is periodically retrained to adapt to new data.

[1557] Step 4:

[1558] The terminal sends an input request from the user.

[1559] Input: Product selection information by the user.

[1560] Data processing: Transmission of user-entered information.

[1561] Output: The request data sent to the server.

[1562] Specific operation: The user selects the desired product on the terminal and sends the selection information to the server as a request. This request includes information about the selected product and the user ID.

[1563] Step 5:

[1564] The server calculates the pricing data and sends it to the terminal.

[1565] Input: Request data from users, optimal pricing patterns from the generative model.

[1566] Data processing: Calculate the price for each desired delivery date for the requested item.

[1567] Output: Calculated price information.

[1568] Specific operation: Based on the pricing patterns obtained from the generative model, the server calculates the price for each desired delivery date for the product corresponding to the user's request and sends the price information to the terminal.

[1569] Step 6:

[1570] The device displays the results to the user and collects emotional data in real time.

[1571] Input: Price information sent from the server, user sentiment data.

[1572] Data processing: Displaying price information and collecting sentiment data.

[1573] Output: Displayed price information, collected sentiment data.

[1574] Specific operation: The terminal displays the received price information to the user. In addition, the terminal analyzes the user's facial expressions, tone of voice, and text input, and collects real-time emotional data through the emotion engine. This data is then sent to the server.

[1575] Step 7:

[1576] The server performs optimization and determines the final price and desired delivery date.

[1577] Input: sentiment data, preprocessed logistics data, pricing patterns using a generative model.

[1578] Data processing: Optimizing price and desired delivery date based on sentiment data.

[1579] Output: Final adjusted price information and desired delivery date.

[1580] Specific operation: The server analyzes the emotion data and adjusts the price and desired delivery date based on the user's level of urgency and satisfaction. For example, if a user is in a hurry, it will present the option of same-day delivery and its price.

[1581] Step 8:

[1582] The user selects the desired delivery date and confirms the order.

[1583] Input: The last price information displayed on the device and the desired delivery date.

[1584] Data processing: Sending the user's selected delivery date and price information.

[1585] Output: Confirmed order data.

[1586] Specific operation: The user selects the desired delivery date based on the information displayed on the terminal and finalizes the order. After confirming the order, the user enters the necessary payment information and sends it to the server.

[1587] Step 9:

[1588] The server checks the order information and sends instructions to the logistics center.

[1589] Input: Confirmed order data.

[1590] Data processing: Checking inventory, payment, and driver availability.

[1591] Output: Shipping instruction data to the logistics center.

[1592] Specific operation: The server checks the received order information, checks the validity of the inventory and payment, and if there are no problems, sends instructions to the logistics center to prepare for shipment.

[1593] Step 10:

[1594] The logistics center prepares the products and delivers them on the specified date.

[1595] Input: Shipping instruction data from the server.

[1596] Data processing: Product preparation and delivery planning.

[1597] Output: The delivered item.

[1598] Specific operation: The logistics center prepares the product according to instructions from the server, and delivers the product by a delivery driver on the specified date. It also delivers personalized messages and special offers to users based on their emotional data.

[1599] (Application example 2)

[1600] 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."

[1601] Labor shortages and declining operational efficiency are serious issues in the logistics industry. Furthermore, while there is a demand for flexible service provision that responds to user emotions and individual needs, this has not been fully realized. Therefore, a method is needed to simultaneously achieve efficient management and personalized service provision.

[1602] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting information on the warehouse status, inventory quantity, driver availability, road conditions, and weather on the day of delivery at the logistics center; means for performing learning using a generative model based on the collected information and user emotion data and calculating the optimal price for each desired delivery date; means for sending a personalized message based on the calculated price information and emotion data to the terminal so that the user can confirm and select a price for each desired delivery date; means for receiving the price and order information for the selected desired delivery date and processing the order; and means for collecting emotion data and performing emotion analysis in real time. This makes it possible to provide an efficient and personalized delivery service.

[1603] A "logistics center" is a facility that centralizes logistics operations such as storing, sorting, packaging, shipping, and delivering packages.

[1604] "Storage status" is data that indicates the storage status of inventory and the progress of work within the logistics center.

[1605] "Stock quantity" is data indicating the quantity of products stored in the logistics center.

[1606] "Driver availability status" is data that indicates the status and number of drivers available for delivery at the logistics center.

[1607] "Road conditions on the day of delivery" is data indicating road traffic conditions and congestion information on the day of delivery.

[1608] "Weather" is data indicating the weather conditions on the delivery date.

[1609] "Emotion data" is data that indicates the emotional state of the user, analyzed from facial expressions, tone of voice, input text, and the like.

[1610] A "generative model" is an algorithm that uses machine learning based on collected data to generate optimal results for new data.

[1611] A "personalized message" is a personalized message created based on the emotional data and past behavior of an individual user.

[1612] A "terminal" is an electronic device that allows a user to obtain information or send instructions.

[1613] "Order information" is data including the product selected by the user, desired delivery date, price, payment method, etc.

[1614] "Emotion analysis" is a process of analyzing the user's emotional state based on collected emotional data.

[1615] This invention aims to build an efficient delivery management system in a logistics center and improve user satisfaction. A specific method for implementing each step will be described below.

[1616] System Configuration

[1617] The present invention uses the following hardware and software:

[1618] Hardware: sensors, servers, smartphones

[1619] Software: Data collection API, sentiment analysis engine, generative model

[1620] Program processing

[1621] Data collection

[1622] The server collects the following data in real time from sensors and management systems within the distribution center:

[1623] Warehouse status

[1624] Quantity in stock

[1625] Driver availability

[1626] Road conditions on the day of delivery

[1627] weather

[1628] The collected data is preprocessed to make it suitable for analysis by removing outliers and filling in missing data. If the device operated by the user is a smartphone, the user's facial expression, tone of voice, and input text are analyzed by an emotion analysis engine to extract emotional data.

[1629] Optimal price calculation using generative models

[1630] The server inputs the pre-processed data and sentiment data into a generative model to determine the optimal price based on past data and the current situation. For example, a Python script like the following can be used:

[1631] python

[1632] import numpy as np

[1633] import pandas as pd

[1634] from datetime import datetime

[1635] import requests

[1636] from sklearn.linear_model import LinearRegression

[1637] Data collection function definition

[1638] def collect_data():

[1639] Sensor data collection

[1640] warehouse_data = requests.get('https: / / api.warehouse.com / data').json()

[1641] Collecting Emotional Data

[1642] emotion_data = requests.get('https: / / api.emotionengine.com / data').json()

[1643] return warehouse_data, emotion_data

[1644] Emotional Data Analysis

[1645] def analyze_emotion(emotion_data):

[1646] Tentative emotion analysis results

[1647] emotion_score = np.mean([item['score'] for item in emotion_data])

[1648] return emotion_score

[1649] Optimal Price Calculation

[1650] def calculate_optimal_price(warehouse_data, emotion_score, delivery_days):

[1651] factors = [warehouse_data['stock_level'], warehouse_data['traffic'],

[1652] warehouse_data['driver_availability'], emotion_score]

[1653] Hypothetical pricing model

[1654] model = LinearRegression()

[1655] X = np.array(factors).reshape(-1, 1)

[1656] y = np.array([1000, 950, 900]) Historical price data

[1657] model.fit(X, y)

[1658] optimal_price = model.predict([[factors + [delivery_days]]])

[1659] return optimal_price

[1660] Displaying pricing information and messages

[1661] The terminal displays a personalized message to the user based on the price information and emotion data for each desired delivery date received from the server. The user confirms the desired delivery date and price of the product through the terminal and selects the desired delivery date.

[1662] Order confirmation and processing

[1663] The price and order information for the delivery date selected by the user are sent from the terminal to the server. Based on the received order information, the server checks inventory, confirms payment, secures a driver, and arranges delivery.

[1664] Specific examples

[1665] Consider the following real-world scenario:

[1666] If there is an abundance of stock and transportation is smooth, the server sets the prices as follows: "next day delivery: 1,000 yen," "three days later delivery: 900 yen," and "one week later delivery: 800 yen." If the user selects one week later delivery, the emotion engine determines that the user is highly satisfied, and a thank you message is displayed on the device.

[1667] Prompt Sentence Examples

[1668] Here are some example prompts to input to the generative AI model:

[1669] We want to build an efficient delivery management system for our logistics center. Please calculate the optimal delivery fee based on the following data:

[1670] Warehouse conditions (inventory, traffic conditions, driver availability, weather)

[1671] Emotional data of drivers and staff (facial expressions, tone of voice, input text)

[1672] As a result, offer the best delivery price for a desired delivery date three days from now.

[1673] The above is a specific embodiment for carrying out the present invention. This system improves the operational efficiency of a logistics center and increases user satisfaction.

[1674] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1675] Step 1:

[1676] The server collects data from sensors and management systems at the logistics center. Inputs include warehouse status, inventory levels, driver availability, road conditions and weather on the day of delivery. Data is collected through an API. Output is preprocessed data. Specifically, it receives list data from sensors, converts it to JSON format and saves it.

[1677] Step 2:

[1678] The server collects emotional data from the user's smartphone. Inputs include the user's facial expressions, tone of voice, and input text. The data is collected by an emotion analysis engine. The output is analyzed emotional data. Specifically, the system captures data in real time using the smartphone's camera and microphone and sends it to the analysis engine.

[1679] Step 3:

[1680] The server pre-processes the collected data. The input is the data on warehouse conditions, inventory, driver availability, road conditions, weather, and user emotions. Outliers are removed and missing data is complemented. The output is the pre-processed data. Specific operations include replacing outliers with standard values ​​and complementing missing values ​​with the average value.

[1681] Step 4:

[1682] The server inputs the preprocessed data into a generative model to calculate the optimal delivery price. The input is the preprocessed warehouse data and emotion data. The output is the calculated price information for each desired delivery date. Specifically, the data is input into a generative model (e.g., a linear regression model) and an adapted price is calculated.

[1683] Step 5:

[1684] The server sends a personalized message based on the calculated price information and emotion data to the device. The input is the calculated price information and analyzed emotion data. The output is the price information and message displayed on the user's device. Specifically, the server sends data in JSON format via an API, and the text and price information are displayed on the device.

[1685] Step 6:

[1686] The user selects the desired delivery date and price of the product through the terminal. The input is the price information and personalized message sent from the server. The output is the selected desired delivery date and price. In concrete terms, the user operates the touch screen to select the desired delivery date and price.

[1687] Step 7:

[1688] The terminal sends the price for the selected desired delivery date and order information to the server. The input is the desired delivery date and price selected by the user. The output is the order information sent to the server. Specifically, the terminal sends the order information in JSON format to the server via the API.

[1689] Step 8:

[1690] Based on the order information received by the server, it checks inventory, confirms payment, and arranges for a driver. The input is the order information sent from the terminal. The output is the status of delivery arrangement completion. Specifically, it accesses the inventory management system and payment gateway to carry out the necessary confirmation work.

[1691] The above steps enable efficient delivery management at the logistics center, thereby improving user satisfaction.

[1692] 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.

[1693] 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.

[1694] 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.

[1695] 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.

[1696] 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.

[1697] 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.

[1698] 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).

[1699] 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.

[1700] 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."

[1701] 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.

[1702] 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).

[1703] 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.

[1704] 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...

Claims

1. A means of collecting information on the warehouse status of the logistics center, the number of stocks, the availability of drivers, the road conditions and weather on the day of delivery; A means for learning using a generative model based on the collected information and calculating the optimal price for each desired delivery date of the product; A means for transmitting the calculated price information to a terminal, allowing the user to confirm and select a price for each desired delivery date; A means for receiving the price and order information for the selected desired delivery date and processing the order; A system including:

2. The system of claim 1 , further comprising means for performing preprocessing to remove outliers and impute missing data.

3. The system of claim 1 , further comprising means for the generative model to learn pricing patterns based on information collected from distribution centers.

Images