System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting and analyzing real-time traffic information and calculating an optimal delivery route by generative artificial intelligence; means for monitoring an inventory level in real time by using Internet technology and collecting data; means for predicting a demand by generative artificial intelligence and automatically generating an optimal delivery plan based on prediction data; means for evaluating an environmental load of each delivery route by generative artificial intelligence and proposing a most environmentally friendly transportation method; and means for notifying a user terminal of the optimal delivery plan and the eco-friendly transportation method.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 the logistics industry, optimizing inventory management and efficient delivery plans are key challenges. Traditional manual processes result in excess inventory, out-of-stock items, and inefficient delivery plans, increasing transportation costs and time. This poses a risk of reducing customer satisfaction and competitiveness. The impact on the environment is also a major issue that cannot be ignored, and there is a demand for reducing CO2 emissions.

[0005] The present invention aims to solve these problems and provide an efficient and environmentally friendly logistics management system. [Means for solving the problem]

[0006] The present invention solves the above problems by providing a system including the following means.

[0007] 1. A means for generative AI to collect and analyze real-time traffic information and calculate optimal delivery routes.

[0008] 2. A means of monitoring inventory levels and collecting data in real time using Internet of Things technology.

[0009] 3. Generative AI performs demand forecasting and automatically generates optimal delivery plans based on the forecast data.

[0010] 4. A means for generative artificial intelligence to assess the environmental impact of each delivery route and suggest the most environmentally friendly transportation method.

[0011] 5. A means for notifying the user of the optimal delivery plan and eco-friendly transportation method on the user's terminal.

[0012] These measures will enable efficient inventory management and delivery planning, reduce transportation costs, improve customer satisfaction, and reduce the burden on the environment, making it possible to realize sustainable logistics.

[0013] "Generative AI" is an AI system that can automatically learn patterns based on data and perform predictions and optimizations.

[0014] "Internet of Things technology" refers to technology that connects physical devices and sensors to the Internet, enabling them to collect and communicate data.

[0015] "Real-time traffic information" refers to data on road congestion and traffic flow at the current time.

[0016] "Stock level" is information that indicates the quantity of a product stored in a particular warehouse or store.

[0017] "Demand forecasting" is the process of predicting future demand for a product based on past sales data and other relevant information.

[0018] The "delivery route" refers to the route from the departure point to the destination when transporting goods.

[0019] "Environmental impact" refers to the impact that a particular action or process has on the environment, particularly CO2 emissions and energy consumption.

[0020] "Method of transportation" refers to the means or technique used to transport goods to their destination.

[0021] "Eco-friendly" refers to characteristics and methods that have a low environmental impact and take sustainability into consideration.

[0022] A "user's terminal" is an electronic device used by a user to operate the device, including a smartphone, tablet, or PC. [Brief explanation of the drawings]

[0023] [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

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] 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).

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] 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.

[0043] 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."

[0044] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0045] 1. Data collection and real-time analysis

[0046] The server collects and analyzes the following data:

[0047] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[0048] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[0049] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[0050] 2. Data analysis and optimization

[0051] The server analyzes the data and generates an optimal delivery plan as follows:

[0052] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[0053] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0054] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[0055] 3. Optimal Route Generation and Evaluation

[0056] The server generates and evaluates optimal delivery routes using the following algorithm:

[0057] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic information and demand forecasts.

[0058] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[0059] 4. Notice to Users

[0060] The device will notify the user of the following:

[0061] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0062] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[0063] Specific examples

[0064] For example, an online retailer might use the system as follows:

[0065] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[0066] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time monitoring of inventory.

[0067] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[0068] 4. The server calculates the optimal delivery route based on the collected data using Dijkstra's algorithm and generates multiple route options.

[0069] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0070] 6. The device will inform the user of the optimal delivery plan and eco-friendly shipping method.

[0071] In this way, the present invention can realize efficient and environmentally friendly logistics management.

[0072] The processing flow will be explained below.

[0073] Step 1: Data collection

[0074] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[0075] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[0076] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[0077] Step 2: Data analysis

[0078] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[0079] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[0080] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[0081] Step 3: Optimal route generation

[0082] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[0083] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[0084] Step 4: Environmental impact assessment

[0085] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[0086] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[0087] Step 5: Propose eco-friendly transportation methods

[0088] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[0089] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[0090] Step 6: Notification and execution of delivery plan

[0091] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[0092] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[0093] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[0094] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[0095] Example 1

[0096] 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."

[0097] Conventional delivery management systems cannot efficiently utilize real-time traffic information or accurately monitor inventory levels, resulting in delays and errors in demand forecasts. Furthermore, they lack the functionality to automatically suggest transportation methods that take environmental impact into consideration, resulting in insufficient ecological response. To solve these problems, an efficient and environmentally friendly delivery management method is needed.

[0098] 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.

[0099] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using sensor technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient and environmentally friendly delivery management.

[0100] "Generative AI" is an AI that uses past data and algorithms to perform advanced processing such as data analysis, demand forecasting, and calculation of optimal routes.

[0101] "Real-time traffic information" refers to data that provides current traffic conditions, congestion levels, delay information, and other information in real time.

[0102] An "optimal delivery route" is a delivery route calculated based on collected traffic information and demand forecast data to minimize travel time, distance, and environmental impact.

[0103] "Sensor technology" is a general term for hardware and software technologies that monitor the physical environment and interpret it as digital data.

[0104] "Inventory level" is data that indicates the quantity and condition of products currently held in a warehouse, store, etc.

[0105] "Demand forecasting" is the process of predicting future demand based on past sales data and other relevant information.

[0106] A "delivery plan" is a detailed plan for the delivery of goods, including specific routes, departure times, estimated arrival times, and the like.

[0107] "Environmental load" is a general term for the impact on the environment, such as energy consumption and CO2 emissions associated with delivery activities.

[0108] "Eco-friendly transportation methods" refer to transportation means and methods that are environmentally friendly, such as being fuel-efficient and reducing CO2 emissions.

[0109] "User's device" refers to an electronic device used by a user to receive delivery plans and notifications, including a smartphone, tablet, or PC.

[0110] This invention is a system that combines generative artificial intelligence and sensor technology to automatically generate optimal delivery routes based on traffic information, inventory levels, and demand forecasts, and proposes delivery methods that take environmental impact into consideration. This system is implemented using the following hardware and software.

[0111] Major hardware and software

[0112] 1. Server

[0113] Traffic information service API: Used to collect real-time traffic information. Examples include "Google Maps API" and "HERE API."

[0114] Database: Uses the database technology required to store and manage inventory information and sales data. Examples include "MySQL" and "PostgreSQL."

[0115] Generative AI models: Used to perform demand forecasting. Machine learning libraries such as TensorFlow and PyTorch.

[0116] Optimization algorithms: Used to calculate delivery routes. Examples include "Dijkstra's algorithm" and "A algorithm."

[0117] Environmental impact assessment tools: Evaluate fuel efficiency and CO2 emissions. An example is the "Emission Calculation Toolkit."

[0118] 2. Terminal

[0119] Smartphone app: Application software that informs users about delivery plans and eco-friendly shipping methods.

[0120] IoT sensors: Devices placed in warehouses to collect inventory data and send it to a server. Examples include sensors from Zebra Technologies and Bosch Rexroth.

[0121] Specific explanation of the processing content

[0122] The server collects and analyzes real-time traffic information, inventory information, and demand forecast data. The traffic information is analyzed to predict congestion and delays on major routes. The server also receives inventory data sent from IoT sensors in the warehouse and stores it in a central database. This data is used to monitor inventory levels in real time.

[0123] Furthermore, the server uses a generative AI model to forecast future demand based on past sales data, thereby predicting where demand for a particular product will increase.

[0124] Based on the collected and analyzed data, the server calculates the optimal delivery route using Dijkstra's algorithm, and also evaluates the environmental impact of the generated route, proposing the most fuel-efficient and least CO2-emitting transportation method.

[0125] The optimal delivery plan and eco-friendly shipping method will be communicated to the user via the device. For example, a smartphone app could be used to inform the user of the specific delivery route, departure time, and estimated arrival time. Eco-friendly shipping options will also be presented via in-app and email notifications.

[0126] Specific examples

[0127] For example, if an online retailer were to use the system, it would work as follows:

[0128] 1. The server obtains real-time traffic data from a traffic information service API (e.g., Google Maps API) and analyzes busy times and routes.

[0129] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse (e.g., Bosch Rexroth) to the server, enabling real-time inventory monitoring.

[0130] 3. The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand and calculate which products are in demand in which areas.

[0131] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[0132] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0133] 6. The device will notify the user of optimal delivery plans and eco-friendly shipping methods.

[0134] Prompt Sentence Examples

[0135] Below are some example prompts to input to a generative AI model:

[0136] "Based on past sales data, predict future demand and calculate the optimal delivery route using Dijkstra's algorithm."

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Obtaining real-time traffic information

[0139] The server sends a request to a traffic information service API (e.g., Google Maps API) to obtain real-time traffic information. The input is the API request, and the output is traffic data in JSON format. The server uses this data to calculate congestion and delay predictions. Specifically, the server sends an HTTP request, analyzes the data received as a response, and generates a traffic situation map.

[0140] Step 2: Collect inventory data

[0141] The terminals transmit inventory information obtained from IoT sensors in the warehouse (e.g., "Bosch Rexroth") to a server. The input is inventory data from the IoT sensors, and the output is inventory level information stored in a central database on the server. Specifically, the sensors transmit inventory information using the MQTT protocol, which the server receives and stores in the database. The server monitors the acquired inventory data in real time.

[0142] Step 3: Generate demand forecast data

[0143] The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand. The input is past sales data, and the output is future demand forecast data. The server queries past sales data from a database and inputs it into a machine learning model to calculate the predicted value. Specifically, the server collects sales data and applies it to the predictive model to generate a list of products that will be in high demand.

[0144] Step 4: Analyze traffic data

[0145] The server analyzes real-time traffic information collected and identifies the congestion status of major routes. The input is real-time traffic information, and the output is route information that is predicted to be congested. Specifically, the server uses traffic data to predict travel times and identify congested routes.

[0146] Step 5: Analyze inventory data

[0147] The server analyzes inventory data and identifies where the required items are in stock. The input is inventory data, and the output is inventory location information for each product category. Specifically, the server calculates how much inventory is in which warehouse based on the quantity and location of the inventory items.

[0148] Step 6: Analyze the demand forecast data

[0149] The server analyzes the results of the demand forecasting model and predicts future demand. The input is the demand forecast data, and the output is a list of regions and products where demand will increase. The server aggregates the predicted demand data for each region and identifies which regions will see increased demand in the future.

[0150] Step 7: Generate delivery routes

[0151] The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the traffic information and demand forecast data collected. The input is traffic information and demand forecast data, and the output is the optimal delivery route. Specifically, the server calculates the travel time and distance for each candidate route and generates multiple route options.

[0152] Step 8: Assess the environmental impact

[0153] The server evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the most eco-friendly transportation method. The input is candidate route data, and the output is the route with the least environmental impact. The server uses the "Emission Calculation Toolkit" to calculate the fuel consumption and CO2 emissions for each route.

[0154] Step 9: Delivery plan and eco-friendly shipping notification

[0155] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the optimal delivery plan and eco-friendly transportation method, and the output is the notified information. Specifically, the content is notified to the user via a smartphone app or web portal.

[0156] (Application example 1)

[0157] 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."

[0158] Conventional delivery management systems do not integrate real-time traffic information collection, inventory management, demand forecasting, and environmental impact reduction functions, and are operated by multiple independent systems. This makes it difficult to calculate optimal delivery routes or propose eco-friendly transportation methods, resulting in inefficient management. Furthermore, there is a lack of means to notify users, which can lead to logistics delays and wasteful energy consumption.

[0159] 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.

[0160] In this invention, the server includes: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates optimal delivery routes; a real-time monitoring and data collection system that uses Internet of Things (IoT) technology to monitor inventory levels; a generating AI that performs demand forecasting and automatically generates optimal delivery plans based on the forecasted data; a generating AI that evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method; a notifying system that notifies a user of the optimal delivery plan and the eco-friendly transportation method via a traffic information service API; a collecting and monitoring system that collects and monitors inventory information via an IoT platform within a warehouse; a demand forecasting model that analyzes future demand; and a generating system that generates optimal delivery routes based on Dijkstra's algorithm, thereby enabling the generation of efficient, real-time delivery plans and the proposal of eco-friendly transportation methods.

[0161] "Generative AI" is an artificial intelligence technology that analyzes and predicts collected data to make optimal decisions in real time.

[0162] "Real-time traffic information" refers to data that allows for instantaneous understanding of current traffic conditions, including road congestion and delay information.

[0163] A "delivery route" is a route used to deliver goods or cargo, and aims to optimize the route from the departure point to the destination.

[0164] "Internet of Things technology" is a general term for technologies that allow various sensors and devices to send and receive data via the Internet, enabling real-time monitoring and data collection.

[0165] "Inventory levels" refer to the current amount of goods in a warehouse or stockroom, and are the basis for managing inventory according to demand.

[0166] "Demand forecasting" is the process of predicting future demand based on past data and current conditions, and is useful for determining inventory management and delivery plans.

[0167] An "eco-friendly transportation method" is a means of transportation that minimizes environmental impact, such as fuel efficiency and CO2 emissions, and is a method that aims for sustainable logistics.

[0168] "User's information terminal" is a general term for the terminal used by the user to receive information, including smartphones, tablets, and personal computers.

[0169] "API for traffic information services" refers to an application programming interface provided by a service that provides traffic data, and is used to obtain real-time traffic information.

[0170] An "IoT platform" is a system that serves as the foundation for realizing Internet of Things technology and is used to collect and manage data from sensors.

[0171] A "demand forecasting model" is a statistical or machine learning model for predicting future demand based on past sales data and market trends.

[0172] "Dijkstra's algorithm" is an algorithm that calculates the shortest path based on graph theory, and is used to calculate optimal routes on networks and maps.

[0173] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0174] The server first obtains real-time traffic data using the API of a traffic information service. Specifically, it uses a common API such as Google Maps API. This data is used to analyze traffic information and determine congestion and expected delay times.

[0175] The server then collects inventory information through the warehouse's IoT platform, using a widely used IoT platform such as AWS IoT Core. Stock levels are monitored in real time and stored in a database, enabling stockout prevention and efficient inventory management.

[0176] Generative AI uses past sales data to generate a demand forecasting model and predict future demand. This model uses machine learning frameworks such as PyTorch. Based on the results of the demand forecast, the server automatically generates an optimal delivery plan.

[0177] The server then generates the optimal delivery route using Dijkstra's algorithm, which is based on the collected traffic information and demand forecast data. After calculating the optimal route, the server evaluates the fuel efficiency and CO2 emissions of each route and suggests the most environmentally friendly transportation method.

[0178] The optimal delivery plan and eco-friendly shipping method are notified to the user's information terminal using services such as Firebase Cloud Messaging, allowing the user to check the optimal delivery plan in real time.

[0179] For example, in a logistics center using the "Smart Logistics Manager" application, logistics managers can simply open the app on their smartphones each morning to check the delivery plan for the day. The app constantly updates real-time traffic information, inventory levels, and demand forecasts, and suggests optimal delivery routes and eco-friendly transportation methods.

[0180] An example of a prompt sentence would be something like the following, which can be input into the generative AI model to provide the necessary data:

[0181] "Calculate the optimal delivery route based on current traffic conditions and inventory levels. Reference historical sales data, forecast demand, and suggest eco-friendly delivery methods."

[0182] This makes it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0184] Step 1:

[0185] The server obtains real-time traffic data using the API of a traffic information service. Specifically, it obtains current traffic information from sources such as Google Maps API, and analyzes that data to determine congestion and expected delay times. Input data includes congestion status and traffic event information for each road section. Analysis results are saved as output in JSON format or similar.

[0186] Step 2:

[0187] The server collects inventory information through the warehouse's IoT platform. Specifically, it uses a platform such as AWS IoT Core to obtain inventory level data from sensors installed in the warehouse and monitors it in real time. Input data includes product identification codes and current quantities. The output is the latest inventory level stored in a database.

[0188] Step 3:

[0189] The server uses past sales data to generate a demand forecasting model and predict future demand. Specifically, it uses a machine learning framework such as PyTorch to build the demand forecasting model and analyzes past sales data as input. Future demand forecast data is generated as output.

[0190] Step 4:

[0191] The server generates the optimal delivery route using Dijkstra's algorithm. Specifically, it calculates the optimal delivery route using the traffic information acquired in step 1 and the demand forecast data generated in step 3 as input. The algorithm calculates the shortest route based on graph theory. The optimal delivery route is generated as output, and the route information is saved in a database.

[0192] Step 5:

[0193] The server evaluates the fuel efficiency and CO2 emissions of each delivery route and proposes the most environmentally friendly transportation method. Specifically, it calculates environmental evaluation parameters using the delivery route information generated in step 4 as input. The output is the evaluation results of fuel efficiency and CO2 emissions, as well as information on the most eco-friendly route.

[0194] Step 6:

[0195] The device notifies the user of the optimal delivery plan and eco-friendly shipping method. Specifically, a push notification is sent to the user's smartphone or tablet using a notification service such as Firebase Cloud Messaging. The input data includes information on the optimal delivery route and eco-friendly shipping method. The output is that the user receives a notification and can view detailed information on their device.

[0196] The above processing steps make it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0197] 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.

[0198] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology, as well as a system that includes an emotion engine that recognizes user emotions. This system not only automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and suggests eco-friendly transportation methods that take environmental impact into consideration, but also recognizes the user's emotional state and dynamically adjusts delivery plans and suggestions accordingly.

[0199] 1. Data collection and real-time analysis

[0200] The server collects and analyzes the following data:

[0201] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[0202] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[0203] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[0204] 2. Data analysis and optimization

[0205] The server analyzes the data and generates an optimal delivery plan as follows:

[0206] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[0207] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0208] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[0209] 3. Optimal Route Generation and Evaluation

[0210] The server generates and evaluates optimal delivery routes using the following algorithm:

[0211] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic data and demand forecasts.

[0212] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[0213] 4. Recognizing and adjusting user emotions

[0214] The emotion engine works as follows:

[0215] The user's emotional state is analyzed in real time based on data collected from the user's device (e.g., voice, text, facial expressions, etc.).

[0216] Based on the analysis results, the user's emotional state (e.g., stress, elation, apathy, etc.) is determined and sent to the server.

[0217] 5. Adjust delivery plans

[0218] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state:

[0219] For users who are under stress, we prioritize quick and reliable delivery routes.

[0220] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0221] 6. User Notification and Action

[0222] The device will notify the user of the following:

[0223] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0224] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[0225] Adaptation based on user emotions: Providing delivery plans and recommendations that best fit the user's emotional state.

[0226] Specific examples

[0227] For example, an online retailer might use the system as follows:

[0228] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[0229] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time inventory monitoring.

[0230] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[0231] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[0232] 5. The emotion engine analyzes the user's emotional state based on data collected from the user's device and creates delivery suggestions that are optimally tailored to the user's characteristics.

[0233] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on this.

[0234] In this way, the present invention can realize efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[0235] The processing flow will be explained below.

[0236] Step 1: Data collection

[0237] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[0238] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[0239] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[0240] Step 2: Data analysis

[0241] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[0242] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[0243] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[0244] Step 3: Optimal route generation

[0245] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[0246] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[0247] Step 4: Environmental impact assessment

[0248] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[0249] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[0250] Step 5: Propose eco-friendly transportation methods

[0251] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[0252] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[0253] Step 6: Recognizing user emotions

[0254] The device collects the user's voice input, text messages, and facial recognition data.

[0255] An emotion engine analyzes the collected data to determine the user's emotional state in real time, which can include stress, joy, anxiety, etc.

[0256] Step 7: Adjust your shipping plan

[0257] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state.

[0258] For example, a user who is under stress may be given priority in suggesting a fast and reliable delivery route.

[0259] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0260] Step 8: Notification and execution of delivery plan

[0261] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[0262] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[0263] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[0264] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[0265] Example 2

[0266] 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."

[0267] Currently, delivery management systems monitor traffic information and inventory levels, forecast demand, and perform other tasks, but do not adjust delivery plans to take user emotions into account. This poses a challenge as they are unable to respond to users' stress levels and eco-consciousness. This could also lead to a decline in user satisfaction.

[0268] 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.

[0269] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using Internet of Things technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, means for analyzing the user's emotional state using position recognition technology and adjusting the delivery plan based on that emotional state, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient, environmentally friendly, and detailed delivery management that takes user emotions into consideration.

[0270] "Generative AI" is an AI system that automatically performs tasks such as data analysis, prediction, and optimization.

[0271] "Real-time traffic information" refers to instantaneous data such as current road conditions, traffic volume, and delay information.

[0272] The "delivery route" is the route along which the product is delivered.

[0273] "Internet of Things technology" is a technology that allows data to be sent and received between physical devices over the Internet.

[0274] "Stock level" refers to the quantity of goods in a warehouse or store.

[0275] "Demand forecasting" is the prediction of future demand.

[0276] A "delivery plan" is a plan that includes detailed schedules and route settings for delivering products.

[0277] "Environmental impact" refers to the impact that a particular activity or process has on the environment.

[0278] "Transportation Method" means the means or method used to deliver the goods.

[0279] "Emotional state" refers to the user's current psychological and emotional state.

[0280] "Position recognition technology" is a technology that analyzes the user's emotions and psychological state.

[0281] A "user terminal" is an electronic device used by a user, such as a computer or smartphone.

[0282] The present invention relates to a delivery management system that combines artificial intelligence, Internet of Things technology, and position recognition technology. Specifically, the following hardware and software configuration is used.

[0283] Data collection and analysis

[0284] The server collects and analyzes various data. The main hardware used is a server with an internet connection, and the following software is used:

[0285] Real-time traffic information: Real-time traffic data is obtained using the API of a traffic information service (e.g., Google Maps API), which collects congestion and delay information and analyzes it on the server.

[0286] Inventory information: Inventory data is acquired in real time using IoT sensors in the warehouse (e.g., sensors manufactured by Zebra Technologies) and sent to a server, where it is stored in a central database.

[0287] Demand forecast data: Based on past sales data, we update the demand forecasting model (e.g., using TensorFlow) and generate new demand forecast data.

[0288] Data optimization and evaluation

[0289] The server generates an optimal delivery plan and route based on the collected data:

[0290] Traffic data analysis: The acquired traffic information is analyzed and used to understand the congestion status of major routes, which is then used to calculate predicted travel times.

[0291] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0292] Demand forecast data analysis: Predict future demand and create optimal delivery plans based on that.

[0293] Optimal route generation

[0294] The server calculates the optimal delivery route using Dijkstra's algorithm or other optimization algorithms (e.g., A algorithm). It evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the transportation method with the least environmental impact.

[0295] User Emotion Recognition

[0296] The emotion engine analyzes the user's emotional state in real time using voice, text, and facial expression data collected from the user's device. The emotion analysis uses Microsoft Azure's Emotion API. The analysis results are sent to the server, and the delivery plan is adjusted based on the user's emotional state.

[0297] Notification and execution of delivery plans

[0298] The device notifies the user of the following information:

[0299] Delivery plan: A detailed plan including specific delivery routes, departure times, and estimated arrival times.

[0300] Eco-friendly shipping methods: Offer environmentally friendly options (e.g., using electric trucks or shared deliveries).

[0301] Emotional adjustment: Providing delivery plans and recommendations that best fit the user's emotional state.

[0302] Specific examples

[0303] For example, an online retailer might use the system as follows:

[0304] 1. The server obtains current traffic data from a traffic information service (Google Maps API) and analyzes busy times and routes.

[0305] 2. The terminal transmits inventory information obtained from IoT sensors (manufactured by Zebra Technologies) in the warehouse to the server, enabling real-time inventory monitoring.

[0306] 3. The server updates the demand forecasting model (using TensorFlow) based on past sales data, predicts future demand, and calculates which products are needed in which areas.

[0307] 4. The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the collected data and generate multiple route options.

[0308] 5. The emotion engine analyzes the voice and facial expression data collected from the user's device using Microsoft Azure's Emotion API to determine the user's emotional state in real time.

[0309] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on that information.

[0310] Prompt Sentence Examples

[0311] "Generate an algorithm that optimizes delivery plans, taking into account the following:"

[0312] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0313] Step 1: Data collection

[0314] A server collects real-time traffic information, inventory data, and historical sales data.

[0315] Input: Traffic information service API, IoT sensors in warehouses, past sales data

[0316] Specific operation:

[0317] The server uses the Google Maps API to obtain real-time traffic data.

[0318] The server collects inventory data from Zebra Technologies sensors and stores it in a central database.

[0319] The server retrieves past sales data from the database.

[0320] Output: Traffic data, inventory data, past sales data

[0321] Step 2: Real-time analysis

[0322] The server performs real-time analysis based on the data collected.

[0323] Input: Collected traffic data, inventory data, historical sales data

[0324] Specific operation:

[0325] The server analyzes traffic data to identify congestion and delays.

[0326] The server analyzes the inventory data and determines the current inventory levels.

[0327] The server uses past sales data to update the demand forecasting model (TensorFlow).

[0328] Output: Analyzed traffic data, inventory levels, and up-to-date demand forecast data

[0329] Step 3: Data analysis and supply and demand forecasting

[0330] The server analyzes demand forecasts and supply availability to generate optimal delivery plans.

[0331] Inputs: Parsed traffic data, inventory levels, and the latest demand forecast data

[0332] Specific operation:

[0333] The server calculates the congestion status and travel time for each route based on the latest traffic data.

[0334] The server analyzes the inventory level for each item and determines whether the item is in stock.

[0335] The server uses the demand forecasting model to predict future demand.

[0336] Output: supply and demand balance, recommended inventory levels, predictive delivery plans

[0337] Step 4: Optimal route generation and evaluation

[0338] The server generates the optimal delivery route and evaluates the environmental impact.

[0339] Input: Data analysis results, predicted delivery plan

[0340] Specific operation:

[0341] The server uses Dijkstra's algorithm to calculate the optimal route.

[0342] The server calculates the fuel efficiency and CO2 emissions of each route and evaluates the environmental impact.

[0343] Output: Optimal delivery route, environmental impact assessment results

[0344] Step 5: Recognizing user emotions

[0345] An emotion engine analyzes the user's emotional state.

[0346] Input: User's voice data, text data, facial expression data

[0347] Specific operation:

[0348] The emotion engine uses Microsoft Azure's Emotion API to analyze the user's emotional state in real time.

[0349] The analysis results are sent to the server.

[0350] Output: User sentiment analysis results

[0351] Step 6: Adjust your shipping plan

[0352] The server dynamically adjusts the delivery plan based on the user's emotional state.

[0353] Input: User sentiment analysis results, optimal delivery route, environmental impact assessment results

[0354] Specific operation:

[0355] For users in a stressed state, the server generates a delivery plan that prioritizes the route that can be reached in the shortest time.

[0356] For eco-conscious users, the server adjusts the delivery plan by selecting a transportation method that minimizes the environmental load.

[0357] Output: Adjusted delivery plan

[0358] Step 7: Notify users and take action

[0359] The terminal notifies the user of the adjusted delivery plan and executes it.

[0360] Input: Adjusted delivery plan

[0361] Specific operation:

[0362] The device will send a push notification to the user and display a detailed delivery plan.

[0363] The terminal suggests eco-friendly transportation methods.

[0364] Output: User notification, executed dispatch plan

[0365] (Application example 2)

[0366] 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."

[0367] In food delivery services, the challenge is to flexibly adjust delivery plans and transportation methods based on the user's emotional state, thereby increasing user satisfaction and reducing environmental impact. Current delivery systems calculate optimal delivery routes taking into account real-time traffic and inventory information, but it is difficult to dynamically adjust routes to reflect the user's emotional state. As a result, they are unable to provide detailed support for users who are in a hurry or environmentally conscious.

[0368] 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: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates an optimal delivery route; a means that monitors inventory levels in real time using Internet of Things technology and collects data; a generating AI that performs demand forecasting and automatically generates an optimal delivery plan based on the forecast data; a generating AI that evaluates the environmental impact of each delivery route and suggests the most environmentally friendly transportation method; a means that recognizes the user's emotional state and dynamically adjusts the delivery plan and transportation method based on the emotional state; and a means that notifies the user's terminal of the optimal delivery plan and eco-friendly transportation method. This enables flexible delivery plans that reflect the user's emotional state, thereby improving user satisfaction and reducing environmental impact.

[0369] "Generative AI" refers to AI that makes predictions and analyses based on data and automatically generates optimal plans.

[0370] "Real-time traffic information" refers to data that instantly acquires current traffic conditions and shows congestion and road conditions.

[0371] The "optimal delivery route" is a route selected to minimize delivery time and costs based on collected traffic information, inventory information, and demand forecasts.

[0372] "Internet of Things technology" refers to technology that allows physical devices and sensors to exchange information over the Internet.

[0373] "Inventory level" refers to data that indicates the current amount of goods or materials stored in a warehouse or the like.

[0374] "Demand forecasting" is the process of predicting future demand based on past sales data and market trends.

[0375] A "delivery plan" is a plan that shows the specific schedule, routes, and resource allocation for product delivery.

[0376] "Environmental impact" refers to the impact that activities such as transportation and delivery have on the environment, particularly CO2 emissions and energy consumption.

[0377] "User's emotional state" refers to information that indicates the emotions and mental state that the user is currently feeling.

[0378] "Dynamic adjustment" refers to the flexible modification of plans and methods in response to changing situations and conditions in real time.

[0379] "User terminal" refers to a device through which a user receives information, such as a smartphone or tablet.

[0380] "Eco-friendly transportation" refers to the use of transportation methods that have a lower impact on the environment, such as electric vehicles and bicycles.

[0381] This invention is a system that dynamically adjusts delivery plans and proposes environmentally friendly transportation methods, primarily for food delivery services, taking into account the user's emotional state. Specifically, the system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecast data, and provides flexible delivery plans that reflect the user's emotional state.

[0382] 1. Data collection and real-time analysis

[0383] The server collects and analyzes data using the following means:

[0384] Real-time traffic information: Collected using the API of a traffic information service. For example, an API key from an external traffic information service (e.g., TomTom Traffic) is used to obtain current congestion and delay information.

[0385] Inventory Information: Using Internet of Things technology, real-time inventory data is collected from sensors in the warehouse. Specifically, IoT sensors are used to monitor the stock levels of each product and store them in a central database.

[0386] Demand forecast data: A generative AI model is used to generate a demand forecast model from past sales data and calculate new demand forecast data. For example, a demand forecasting algorithm using TensorFlow is used.

[0387] 2. Data analysis and optimization

[0388] The server analyzes the data and generates an optimal delivery plan using the following methods:

[0389] Traffic data analysis: Analyzes real-time traffic information and predicts congestion and travel times on major routes based on the acquired data.

[0390] Inventory Data Analysis: Analyze collected inventory data to identify where needed items are in stock.

[0391] Demand forecasting data analysis: Uses generative AI models to predict future demand and use the results to create optimal delivery plans.

[0392] 3. Optimal Route Generation and Evaluation

[0393] The server uses Dijkstra's algorithm and other optimization algorithms to calculate optimal delivery routes based on collected traffic data and demand forecast data. It also evaluates the fuel efficiency and CO2 emissions of the selected routes and proposes the transportation method with the least environmental impact.

[0394] 4. Recognizing and adjusting user emotions

[0395] The user's device (e.g., smartphone) recognizes the user's emotional state using the following means:

[0396] Emotional data collection: Analyze the user's emotional state in real time based on data such as voice, text, and facial expressions.

[0397] Emotional state determination: Based on the analysis results, the user's emotional state (e.g., stress, elation, indifference, etc.) is determined and sent to the server.

[0398] 5. Dynamic adjustment of delivery plans

[0399] The server dynamically adjusts its delivery plan and transportation suggestions based on the user's emotional state using the following means:

[0400] For users under stress, we prioritize quick and reliable delivery routes.

[0401] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0402] 6. User Notification and Action

[0403] The terminal will notify the user:

[0404] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0405] Eco-friendly transport methods: Environmentally friendly options such as using electric vehicles and offering shared deliveries.

[0406] Adjustments based on user emotions: Delivery plans and suggestions are optimized to the user's emotional state.

[0407] As a specific example, if a user is judged to be "tired," they will be notified, "Please relax and wait, we will deliver the item as quickly as possible by car," and if a user requests an "eco-friendly delivery method," they will be notified, "We will deliver the item by electric motorcycle."

[0408] Example prompts to input to the generative AI model

[0409] "If the user is fatigued, provide them with the best delivery route and associated plan to respond quickly."

[0410] "For users who wish to use EcoMute, please provide a delivery method that minimizes the environmental impact."

[0411] As a result, the present invention realizes efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[0412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0413] Step 1:

[0414] The server collects real-time traffic information. Specifically, it uses the API of the traffic information service to obtain traffic data (e.g., congestion status and delay information). The input is real-time traffic data from the API, and the output is the congestion status and predicted travel time as an analysis result. Data processing involves analyzing the congestion level after collecting traffic information and calculating predicted travel times for each major route.

[0415] Step 2:

[0416] The server uses Internet of Things technology to monitor inventory levels in real time and collect data. Specifically, it obtains inventory data from IoT sensors in the warehouse and stores it in a central database. The input is inventory data from the sensors, and the output is real-time inventory levels. Data processing involves collecting data from the sensors to create and update the current inventory status of products.

[0417] Step 3:

[0418] The server uses a generative AI model to perform demand forecasting. The input is past sales data, and the output is future demand forecast data. Specifically, an AI model (e.g., TensorFlow) is used to analyze past sales data and generate a demand forecasting model. Data calculation involves training the model based on past sales trends and calculating a new demand forecast.

[0419] Step 4:

[0420] The server automatically generates optimal delivery routes based on collected traffic data and demand forecast data. The input is real-time traffic data and demand forecast data, and the output is the optimal delivery route proposal. Specifically, it uses Dijkstra's algorithm and other optimization algorithms to calculate the optimal route taking fuel efficiency and travel time into consideration. Data calculations combine the congestion status of each route with demand forecasts to generate effective routes.

[0421] Step 5:

[0422] The device recognizes the user's emotional state. Specifically, it collects data such as voice, text, and facial expressions, and analyzes the emotional state in real time based on this. The input is voice, text, and facial expression data from the device, and the output is the user's emotional state as an analysis result. Data processing involves analyzing the data using an emotion recognition engine (e.g., Affectiva) to determine the current emotional state.

[0423] Step 6:

[0424] The server dynamically adjusts the delivery plan based on the user's emotional state. The input is the user's emotional state data, and the output is an adjusted delivery plan according to the emotion. Specifically, the delivery route and transportation method are changed according to the user's emotional state. For example, a fast delivery route is proposed for a stressed user, and a route with a low environmental impact is proposed for an eco-conscious user. Data calculation involves analyzing the user's emotional data and dynamically updating the delivery plan based on that data.

[0425] Step 7:

[0426] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the adjusted delivery plan, and the output is the notification to the user. Specifically, notifications are sent to smartphones, tablets, etc., providing the user with detailed delivery information (departure time, estimated arrival time, transportation method, etc.). In operation, the system improves user satisfaction by notifying the user of delivery information tailored to the user in real time.

[0427] 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.

[0428] 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.

[0429] 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.

[0430] [Second embodiment]

[0431] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0432] 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.

[0433] 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).

[0434] 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.

[0435] 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.

[0436] 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).

[0437] 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.

[0438] 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.

[0439] 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.

[0440] 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.

[0441] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0442] 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."

[0443] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0444] 1. Data collection and real-time analysis

[0445] The server collects and analyzes the following data:

[0446] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[0447] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[0448] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[0449] 2. Data analysis and optimization

[0450] The server analyzes the data and generates an optimal delivery plan as follows:

[0451] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[0452] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0453] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[0454] 3. Optimal Route Generation and Evaluation

[0455] The server generates and evaluates optimal delivery routes using the following algorithm:

[0456] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic information and demand forecasts.

[0457] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[0458] 4. Notice to Users

[0459] The device will notify the user of the following:

[0460] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0461] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[0462] Specific examples

[0463] For example, an online retailer might use the system as follows:

[0464] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[0465] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time monitoring of inventory.

[0466] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[0467] 4. The server calculates the optimal delivery route based on the collected data using Dijkstra's algorithm and generates multiple route options.

[0468] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0469] 6. The device will inform the user of the optimal delivery plan and eco-friendly shipping method.

[0470] In this way, the present invention can realize efficient and environmentally friendly logistics management.

[0471] The processing flow will be explained below.

[0472] Step 1: Data collection

[0473] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[0474] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[0475] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[0476] Step 2: Data analysis

[0477] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[0478] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[0479] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[0480] Step 3: Optimal route generation

[0481] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[0482] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[0483] Step 4: Environmental impact assessment

[0484] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[0485] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[0486] Step 5: Propose eco-friendly transportation methods

[0487] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[0488] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[0489] Step 6: Notification and execution of delivery plan

[0490] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[0491] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[0492] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[0493] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[0494] Example 1

[0495] 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."

[0496] Conventional delivery management systems cannot efficiently utilize real-time traffic information or accurately monitor inventory levels, resulting in delays and errors in demand forecasts. Furthermore, they lack the functionality to automatically suggest transportation methods that take environmental impact into consideration, resulting in insufficient ecological response. To solve these problems, an efficient and environmentally friendly delivery management method is needed.

[0497] 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.

[0498] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using sensor technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient and environmentally friendly delivery management.

[0499] "Generative AI" is an AI that uses past data and algorithms to perform advanced processing such as data analysis, demand forecasting, and calculation of optimal routes.

[0500] "Real-time traffic information" refers to data that provides current traffic conditions, congestion levels, delay information, and other information in real time.

[0501] An "optimal delivery route" is a delivery route calculated based on collected traffic information and demand forecast data to minimize travel time, distance, and environmental impact.

[0502] "Sensor technology" is a general term for hardware and software technologies that monitor the physical environment and interpret it as digital data.

[0503] "Inventory level" is data that indicates the quantity and condition of products currently held in a warehouse, store, etc.

[0504] "Demand forecasting" is the process of predicting future demand based on past sales data and other relevant information.

[0505] A "delivery plan" is a detailed plan for the delivery of goods, including specific routes, departure times, estimated arrival times, and the like.

[0506] "Environmental load" is a general term for the impact on the environment, such as energy consumption and CO2 emissions associated with delivery activities.

[0507] "Eco-friendly transportation methods" refer to transportation means and methods that are environmentally friendly, such as being fuel-efficient and reducing CO2 emissions.

[0508] "User's device" refers to an electronic device used by a user to receive delivery plans and notifications, including a smartphone, tablet, or PC.

[0509] This invention is a system that combines generative artificial intelligence and sensor technology to automatically generate optimal delivery routes based on traffic information, inventory levels, and demand forecasts, and proposes delivery methods that take environmental impact into consideration. This system is implemented using the following hardware and software.

[0510] Major hardware and software

[0511] 1. Server

[0512] Traffic information service API: Used to collect real-time traffic information. Examples include "Google Maps API" and "HERE API."

[0513] Database: Uses the database technology required to store and manage inventory information and sales data. Examples include "MySQL" and "PostgreSQL."

[0514] Generative AI models: Used to perform demand forecasting. Machine learning libraries such as TensorFlow and PyTorch.

[0515] Optimization algorithms: Used to calculate delivery routes. Examples include "Dijkstra's algorithm" and "A algorithm."

[0516] Environmental impact assessment tools: Evaluate fuel efficiency and CO2 emissions. An example is the "Emission Calculation Toolkit."

[0517] 2. Terminal

[0518] Smartphone app: Application software that informs users about delivery plans and eco-friendly shipping methods.

[0519] IoT sensors: Devices placed in warehouses to collect inventory data and send it to a server. Examples include sensors from Zebra Technologies and Bosch Rexroth.

[0520] Specific explanation of the processing content

[0521] The server collects and analyzes real-time traffic information, inventory information, and demand forecast data. The traffic information is analyzed to predict congestion and delays on major routes. The server also receives inventory data sent from IoT sensors in the warehouse and stores it in a central database. This data is used to monitor inventory levels in real time.

[0522] Furthermore, the server uses a generative AI model to forecast future demand based on past sales data, thereby predicting where demand for a particular product will increase.

[0523] Based on the collected and analyzed data, the server calculates the optimal delivery route using Dijkstra's algorithm, and also evaluates the environmental impact of the generated route, proposing the most fuel-efficient and least CO2-emitting transportation method.

[0524] The optimal delivery plan and eco-friendly shipping method will be communicated to the user via the device. For example, a smartphone app could be used to inform the user of the specific delivery route, departure time, and estimated arrival time. Eco-friendly shipping options will also be presented via in-app and email notifications.

[0525] Specific examples

[0526] For example, if an online retailer were to use the system, it would work as follows:

[0527] 1. The server obtains real-time traffic data from a traffic information service API (e.g., Google Maps API) and analyzes busy times and routes.

[0528] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse (e.g., Bosch Rexroth) to the server, enabling real-time inventory monitoring.

[0529] 3. The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand and calculate which products are in demand in which areas.

[0530] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[0531] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0532] 6. The device will notify the user of optimal delivery plans and eco-friendly shipping methods.

[0533] Prompt Sentence Examples

[0534] Below are some example prompts to input to a generative AI model:

[0535] "Based on past sales data, predict future demand and calculate the optimal delivery route using Dijkstra's algorithm."

[0536] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0537] Step 1: Obtaining real-time traffic information

[0538] The server sends a request to a traffic information service API (e.g., Google Maps API) to obtain real-time traffic information. The input is the API request, and the output is traffic data in JSON format. The server uses this data to calculate congestion and delay predictions. Specifically, the server sends an HTTP request, analyzes the data received as a response, and generates a traffic situation map.

[0539] Step 2: Collect inventory data

[0540] The terminals transmit inventory information obtained from IoT sensors in the warehouse (e.g., "Bosch Rexroth") to a server. The input is inventory data from the IoT sensors, and the output is inventory level information stored in a central database on the server. Specifically, the sensors transmit inventory information using the MQTT protocol, which the server receives and stores in the database. The server monitors the acquired inventory data in real time.

[0541] Step 3: Generate demand forecast data

[0542] The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand. The input is past sales data, and the output is future demand forecast data. The server queries past sales data from a database and inputs it into a machine learning model to calculate the predicted value. Specifically, the server collects sales data and applies it to the predictive model to generate a list of products that will be in high demand.

[0543] Step 4: Analyze traffic data

[0544] The server analyzes real-time traffic information collected and identifies the congestion status of major routes. The input is real-time traffic information, and the output is route information that is predicted to be congested. Specifically, the server uses traffic data to predict travel times and identify congested routes.

[0545] Step 5: Analyze inventory data

[0546] The server analyzes inventory data and identifies where the required items are in stock. The input is inventory data, and the output is inventory location information for each product category. Specifically, the server calculates how much inventory is in which warehouse based on the quantity and location of the inventory items.

[0547] Step 6: Analyze the demand forecast data

[0548] The server analyzes the results of the demand forecasting model and predicts future demand. The input is the demand forecast data, and the output is a list of regions and products where demand will increase. The server aggregates the predicted demand data for each region and identifies which regions will see increased demand in the future.

[0549] Step 7: Generate delivery routes

[0550] The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the traffic information and demand forecast data collected. The input is traffic information and demand forecast data, and the output is the optimal delivery route. Specifically, the server calculates the travel time and distance for each candidate route and generates multiple route options.

[0551] Step 8: Assess the environmental impact

[0552] The server evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the most eco-friendly transportation method. The input is candidate route data, and the output is the route with the least environmental impact. The server uses the "Emission Calculation Toolkit" to calculate the fuel consumption and CO2 emissions for each route.

[0553] Step 9: Delivery plan and eco-friendly shipping notification

[0554] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the optimal delivery plan and eco-friendly transportation method, and the output is the notified information. Specifically, the content is notified to the user via a smartphone app or web portal.

[0555] (Application example 1)

[0556] 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."

[0557] Conventional delivery management systems do not integrate real-time traffic information collection, inventory management, demand forecasting, and environmental impact reduction functions, and are operated by multiple independent systems. This makes it difficult to calculate optimal delivery routes or propose eco-friendly transportation methods, resulting in inefficient management. Furthermore, there is a lack of means to notify users, which can lead to logistics delays and wasteful energy consumption.

[0558] 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.

[0559] In this invention, the server includes: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates optimal delivery routes; a real-time monitoring and data collection system that uses Internet of Things (IoT) technology to monitor inventory levels; a generating AI that performs demand forecasting and automatically generates optimal delivery plans based on the forecasted data; a generating AI that evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method; a notifying system that notifies a user of the optimal delivery plan and the eco-friendly transportation method via a traffic information service API; a collecting and monitoring system that collects and monitors inventory information via an IoT platform within a warehouse; a demand forecasting model that analyzes future demand; and a generating system that generates optimal delivery routes based on Dijkstra's algorithm, thereby enabling the generation of efficient, real-time delivery plans and the proposal of eco-friendly transportation methods.

[0560] "Generative AI" is an artificial intelligence technology that analyzes and predicts collected data to make optimal decisions in real time.

[0561] "Real-time traffic information" refers to data that allows for instantaneous understanding of current traffic conditions, including road congestion and delay information.

[0562] A "delivery route" is a route used to deliver goods or cargo, and aims to optimize the route from the departure point to the destination.

[0563] "Internet of Things technology" is a general term for technologies that allow various sensors and devices to send and receive data via the Internet, enabling real-time monitoring and data collection.

[0564] "Inventory levels" refer to the current amount of goods in a warehouse or stockroom, and are the basis for managing inventory according to demand.

[0565] "Demand forecasting" is the process of predicting future demand based on past data and current conditions, and is useful for determining inventory management and delivery plans.

[0566] An "eco-friendly transportation method" is a means of transportation that minimizes environmental impact, such as fuel efficiency and CO2 emissions, and is a method that aims for sustainable logistics.

[0567] "User's information terminal" is a general term for the terminal used by the user to receive information, including smartphones, tablets, and personal computers.

[0568] "API for traffic information services" refers to an application programming interface provided by a service that provides traffic data, and is used to obtain real-time traffic information.

[0569] An "IoT platform" is a system that serves as the foundation for realizing Internet of Things technology and is used to collect and manage data from sensors.

[0570] A "demand forecasting model" is a statistical or machine learning model for predicting future demand based on past sales data and market trends.

[0571] "Dijkstra's algorithm" is an algorithm that calculates the shortest path based on graph theory, and is used to calculate optimal routes on networks and maps.

[0572] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0573] The server first obtains real-time traffic data using the API of a traffic information service. Specifically, it uses a common API such as Google Maps API. This data is used to analyze traffic information and determine congestion and expected delay times.

[0574] The server then collects inventory information through the warehouse's IoT platform, using a widely used IoT platform such as AWS IoT Core. Stock levels are monitored in real time and stored in a database, enabling stockout prevention and efficient inventory management.

[0575] Generative AI uses past sales data to generate a demand forecasting model and predict future demand. This model uses machine learning frameworks such as PyTorch. Based on the results of the demand forecast, the server automatically generates an optimal delivery plan.

[0576] The server then generates the optimal delivery route using Dijkstra's algorithm, which is based on the collected traffic information and demand forecast data. After calculating the optimal route, the server evaluates the fuel efficiency and CO2 emissions of each route and suggests the most environmentally friendly transportation method.

[0577] The optimal delivery plan and eco-friendly shipping method are notified to the user's information terminal using services such as Firebase Cloud Messaging, allowing the user to check the optimal delivery plan in real time.

[0578] For example, in a logistics center using the "Smart Logistics Manager" application, logistics managers can simply open the app on their smartphones each morning to check the delivery plan for the day. The app constantly updates real-time traffic information, inventory levels, and demand forecasts, and suggests optimal delivery routes and eco-friendly transportation methods.

[0579] An example of a prompt sentence would be something like the following, which can be input into the generative AI model to provide the necessary data:

[0580] "Calculate the optimal delivery route based on current traffic conditions and inventory levels. Reference historical sales data, forecast demand, and suggest eco-friendly delivery methods."

[0581] This makes it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0582] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0583] Step 1:

[0584] The server obtains real-time traffic data using the API of a traffic information service. Specifically, it obtains current traffic information from sources such as Google Maps API, and analyzes that data to determine congestion and expected delay times. Input data includes congestion status and traffic event information for each road section. Analysis results are saved as output in JSON format or similar.

[0585] Step 2:

[0586] The server collects inventory information through the warehouse's IoT platform. Specifically, it uses a platform such as AWS IoT Core to obtain inventory level data from sensors installed in the warehouse and monitors it in real time. Input data includes product identification codes and current quantities. The output is the latest inventory level stored in a database.

[0587] Step 3:

[0588] The server uses past sales data to generate a demand forecasting model and predict future demand. Specifically, it uses a machine learning framework such as PyTorch to build the demand forecasting model and analyzes past sales data as input. Future demand forecast data is generated as output.

[0589] Step 4:

[0590] The server generates the optimal delivery route using Dijkstra's algorithm. Specifically, it calculates the optimal delivery route using the traffic information acquired in step 1 and the demand forecast data generated in step 3 as input. The algorithm calculates the shortest route based on graph theory. The optimal delivery route is generated as output, and the route information is saved in a database.

[0591] Step 5:

[0592] The server evaluates the fuel efficiency and CO2 emissions of each delivery route and proposes the most environmentally friendly transportation method. Specifically, it calculates environmental evaluation parameters using the delivery route information generated in step 4 as input. The output is the evaluation results of fuel efficiency and CO2 emissions, as well as information on the most eco-friendly route.

[0593] Step 6:

[0594] The device notifies the user of the optimal delivery plan and eco-friendly shipping method. Specifically, a push notification is sent to the user's smartphone or tablet using a notification service such as Firebase Cloud Messaging. The input data includes information on the optimal delivery route and eco-friendly shipping method. The output is that the user receives a notification and can view detailed information on their device.

[0595] The above processing steps make it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0596] 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.

[0597] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology, as well as a system that includes an emotion engine that recognizes user emotions. This system not only automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and suggests eco-friendly transportation methods that take environmental impact into consideration, but also recognizes the user's emotional state and dynamically adjusts delivery plans and suggestions accordingly.

[0598] 1. Data collection and real-time analysis

[0599] The server collects and analyzes the following data:

[0600] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[0601] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[0602] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[0603] 2. Data analysis and optimization

[0604] The server analyzes the data and generates an optimal delivery plan as follows:

[0605] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[0606] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0607] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[0608] 3. Optimal Route Generation and Evaluation

[0609] The server generates and evaluates optimal delivery routes using the following algorithm:

[0610] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic data and demand forecasts.

[0611] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[0612] 4. Recognizing and adjusting user emotions

[0613] The emotion engine works as follows:

[0614] The user's emotional state is analyzed in real time based on data collected from the user's device (e.g., voice, text, facial expressions, etc.).

[0615] Based on the analysis results, the user's emotional state (e.g., stress, elation, apathy, etc.) is determined and sent to the server.

[0616] 5. Adjust delivery plans

[0617] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state:

[0618] For users who are under stress, we prioritize quick and reliable delivery routes.

[0619] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0620] 6. User Notification and Action

[0621] The device will notify the user of the following:

[0622] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0623] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[0624] Adaptation based on user emotions: Providing delivery plans and recommendations that best fit the user's emotional state.

[0625] Specific examples

[0626] For example, an online retailer might use the system as follows:

[0627] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[0628] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time inventory monitoring.

[0629] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[0630] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[0631] 5. The emotion engine analyzes the user's emotional state based on data collected from the user's device and creates delivery suggestions that are optimally tailored to the user's characteristics.

[0632] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on this.

[0633] In this way, the present invention can realize efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[0634] The processing flow will be explained below.

[0635] Step 1: Data collection

[0636] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[0637] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[0638] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[0639] Step 2: Data analysis

[0640] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[0641] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[0642] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[0643] Step 3: Optimal route generation

[0644] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[0645] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[0646] Step 4: Environmental impact assessment

[0647] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[0648] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[0649] Step 5: Propose eco-friendly transportation methods

[0650] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[0651] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[0652] Step 6: Recognizing user emotions

[0653] The device collects the user's voice input, text messages, and facial recognition data.

[0654] An emotion engine analyzes the collected data to determine the user's emotional state in real time, which can include stress, joy, anxiety, etc.

[0655] Step 7: Adjust your shipping plan

[0656] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state.

[0657] For example, a user who is under stress may be given priority in suggesting a fast and reliable delivery route.

[0658] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0659] Step 8: Notification and execution of delivery plan

[0660] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[0661] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[0662] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[0663] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[0664] Example 2

[0665] 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."

[0666] Currently, delivery management systems monitor traffic information and inventory levels, forecast demand, and perform other tasks, but do not adjust delivery plans to take user emotions into account. This poses a challenge as they are unable to respond to users' stress levels and eco-consciousness. This could also lead to a decline in user satisfaction.

[0667] 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.

[0668] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using Internet of Things technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, means for analyzing the user's emotional state using position recognition technology and adjusting the delivery plan based on that emotional state, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient, environmentally friendly, and detailed delivery management that takes user emotions into consideration.

[0669] "Generative AI" is an AI system that automatically performs tasks such as data analysis, prediction, and optimization.

[0670] "Real-time traffic information" refers to instantaneous data such as current road conditions, traffic volume, and delay information.

[0671] The "delivery route" is the route along which the product is delivered.

[0672] "Internet of Things technology" is a technology that allows data to be sent and received between physical devices over the Internet.

[0673] "Stock level" refers to the quantity of goods in a warehouse or store.

[0674] "Demand forecasting" is the prediction of future demand.

[0675] A "delivery plan" is a plan that includes detailed schedules and route settings for delivering products.

[0676] "Environmental impact" refers to the impact that a particular activity or process has on the environment.

[0677] "Transportation Method" means the means or method used to deliver the goods.

[0678] "Emotional state" refers to the user's current psychological and emotional state.

[0679] "Position recognition technology" is a technology that analyzes the user's emotions and psychological state.

[0680] A "user terminal" is an electronic device used by a user, such as a computer or smartphone.

[0681] The present invention relates to a delivery management system that combines artificial intelligence, Internet of Things technology, and position recognition technology. Specifically, the following hardware and software configuration is used.

[0682] Data collection and analysis

[0683] The server collects and analyzes various data. The main hardware used is a server with an internet connection, and the following software is used:

[0684] Real-time traffic information: Real-time traffic data is obtained using the API of a traffic information service (e.g., Google Maps API), which collects congestion and delay information and analyzes it on the server.

[0685] Inventory information: Inventory data is acquired in real time using IoT sensors in the warehouse (e.g., sensors manufactured by Zebra Technologies) and sent to a server, where it is stored in a central database.

[0686] Demand forecast data: Based on past sales data, we update the demand forecasting model (e.g., using TensorFlow) and generate new demand forecast data.

[0687] Data optimization and evaluation

[0688] The server generates an optimal delivery plan and route based on the collected data:

[0689] Traffic data analysis: The acquired traffic information is analyzed and used to understand the congestion status of major routes, which is then used to calculate predicted travel times.

[0690] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0691] Demand forecast data analysis: Predict future demand and create optimal delivery plans based on that.

[0692] Optimal route generation

[0693] The server calculates the optimal delivery route using Dijkstra's algorithm or other optimization algorithms (e.g., A algorithm). It evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the transportation method with the least environmental impact.

[0694] User Emotion Recognition

[0695] The emotion engine analyzes the user's emotional state in real time using voice, text, and facial expression data collected from the user's device. The emotion analysis uses Microsoft Azure's Emotion API. The analysis results are sent to the server, and the delivery plan is adjusted based on the user's emotional state.

[0696] Notification and execution of delivery plans

[0697] The device notifies the user of the following information:

[0698] Delivery plan: A detailed plan including specific delivery routes, departure times, and estimated arrival times.

[0699] Eco-friendly shipping methods: Offer environmentally friendly options (e.g., using electric trucks or shared deliveries).

[0700] Emotional adjustment: Providing delivery plans and recommendations that best fit the user's emotional state.

[0701] Specific examples

[0702] For example, an online retailer might use the system as follows:

[0703] 1. The server obtains current traffic data from a traffic information service (Google Maps API) and analyzes busy times and routes.

[0704] 2. The terminal transmits inventory information obtained from IoT sensors (manufactured by Zebra Technologies) in the warehouse to the server, enabling real-time inventory monitoring.

[0705] 3. The server updates the demand forecasting model (using TensorFlow) based on past sales data, predicts future demand, and calculates which products are needed in which areas.

[0706] 4. The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the collected data and generate multiple route options.

[0707] 5. The emotion engine analyzes the voice and facial expression data collected from the user's device using Microsoft Azure's Emotion API to determine the user's emotional state in real time.

[0708] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on that information.

[0709] Prompt Sentence Examples

[0710] "Generate an algorithm that optimizes delivery plans, taking into account the following:"

[0711] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0712] Step 1: Data collection

[0713] A server collects real-time traffic information, inventory data, and historical sales data.

[0714] Input: Traffic information service API, IoT sensors in warehouses, past sales data

[0715] Specific operation:

[0716] The server uses the Google Maps API to obtain real-time traffic data.

[0717] The server collects inventory data from Zebra Technologies sensors and stores it in a central database.

[0718] The server retrieves past sales data from the database.

[0719] Output: Traffic data, inventory data, past sales data

[0720] Step 2: Real-time analysis

[0721] The server performs real-time analysis based on the data collected.

[0722] Input: Collected traffic data, inventory data, historical sales data

[0723] Specific operation:

[0724] The server analyzes traffic data to identify congestion and delays.

[0725] The server analyzes the inventory data and determines the current inventory levels.

[0726] The server uses past sales data to update the demand forecasting model (TensorFlow).

[0727] Output: Analyzed traffic data, inventory levels, and up-to-date demand forecast data

[0728] Step 3: Data analysis and supply and demand forecasting

[0729] The server analyzes demand forecasts and supply availability to generate optimal delivery plans.

[0730] Inputs: Parsed traffic data, inventory levels, and the latest demand forecast data

[0731] Specific operation:

[0732] The server calculates the congestion status and travel time for each route based on the latest traffic data.

[0733] The server analyzes the inventory level for each item and determines whether the item is in stock.

[0734] The server uses the demand forecasting model to predict future demand.

[0735] Output: supply and demand balance, recommended inventory levels, predictive delivery plans

[0736] Step 4: Optimal route generation and evaluation

[0737] The server generates the optimal delivery route and evaluates the environmental impact.

[0738] Input: Data analysis results, predicted delivery plan

[0739] Specific operation:

[0740] The server uses Dijkstra's algorithm to calculate the optimal route.

[0741] The server calculates the fuel efficiency and CO2 emissions of each route and evaluates the environmental impact.

[0742] Output: Optimal delivery route, environmental impact assessment results

[0743] Step 5: Recognizing user emotions

[0744] An emotion engine analyzes the user's emotional state.

[0745] Input: User's voice data, text data, facial expression data

[0746] Specific operation:

[0747] The emotion engine uses Microsoft Azure's Emotion API to analyze the user's emotional state in real time.

[0748] The analysis results are sent to the server.

[0749] Output: User sentiment analysis results

[0750] Step 6: Adjust your shipping plan

[0751] The server dynamically adjusts the delivery plan based on the user's emotional state.

[0752] Input: User sentiment analysis results, optimal delivery route, environmental impact assessment results

[0753] Specific operation:

[0754] For users in a stressed state, the server generates a delivery plan that prioritizes the route that can be reached in the shortest time.

[0755] For eco-conscious users, the server adjusts the delivery plan by selecting a transportation method that minimizes the environmental load.

[0756] Output: Adjusted delivery plan

[0757] Step 7: Notify users and take action

[0758] The terminal notifies the user of the adjusted delivery plan and executes it.

[0759] Input: Adjusted delivery plan

[0760] Specific operation:

[0761] The device will send a push notification to the user and display a detailed delivery plan.

[0762] The terminal suggests eco-friendly transportation methods.

[0763] Output: User notification, executed dispatch plan

[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] In food delivery services, the challenge is to flexibly adjust delivery plans and transportation methods based on the user's emotional state, thereby increasing user satisfaction and reducing environmental impact. Current delivery systems calculate optimal delivery routes taking into account real-time traffic and inventory information, but it is difficult to dynamically adjust routes to reflect the user's emotional state. As a result, they are unable to provide detailed support for users who are in a hurry or environmentally conscious.

[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: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates an optimal delivery route; a means that monitors inventory levels in real time using Internet of Things technology and collects data; a generating AI that performs demand forecasting and automatically generates an optimal delivery plan based on the forecast data; a generating AI that evaluates the environmental impact of each delivery route and suggests the most environmentally friendly transportation method; a means that recognizes the user's emotional state and dynamically adjusts the delivery plan and transportation method based on the emotional state; and a means that notifies the user's terminal of the optimal delivery plan and eco-friendly transportation method. This enables flexible delivery plans that reflect the user's emotional state, thereby improving user satisfaction and reducing environmental impact.

[0768] "Generative AI" refers to AI that makes predictions and analyses based on data and automatically generates optimal plans.

[0769] "Real-time traffic information" refers to data that instantly acquires current traffic conditions and shows congestion and road conditions.

[0770] The "optimal delivery route" is a route selected to minimize delivery time and costs based on collected traffic information, inventory information, and demand forecasts.

[0771] "Internet of Things technology" refers to technology that allows physical devices and sensors to exchange information over the Internet.

[0772] "Inventory level" refers to data that indicates the current amount of goods or materials stored in a warehouse or the like.

[0773] "Demand forecasting" is the process of predicting future demand based on past sales data and market trends.

[0774] A "delivery plan" is a plan that shows the specific schedule, routes, and resource allocation for product delivery.

[0775] "Environmental impact" refers to the impact that activities such as transportation and delivery have on the environment, particularly CO2 emissions and energy consumption.

[0776] "User's emotional state" refers to information that indicates the emotions and mental state that the user is currently feeling.

[0777] "Dynamic adjustment" refers to the flexible modification of plans and methods in response to changing situations and conditions in real time.

[0778] "User terminal" refers to a device through which a user receives information, such as a smartphone or tablet.

[0779] "Eco-friendly transportation" refers to the use of transportation methods that have a lower impact on the environment, such as electric vehicles and bicycles.

[0780] This invention is a system that dynamically adjusts delivery plans and proposes environmentally friendly transportation methods, primarily for food delivery services, taking into account the user's emotional state. Specifically, the system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecast data, and provides flexible delivery plans that reflect the user's emotional state.

[0781] 1. Data collection and real-time analysis

[0782] The server collects and analyzes data using the following means:

[0783] Real-time traffic information: Collected using the API of a traffic information service. For example, an API key from an external traffic information service (e.g., TomTom Traffic) is used to obtain current congestion and delay information.

[0784] Inventory Information: Using Internet of Things technology, real-time inventory data is collected from sensors in the warehouse. Specifically, IoT sensors are used to monitor the stock levels of each product and store them in a central database.

[0785] Demand forecast data: A generative AI model is used to generate a demand forecast model from past sales data and calculate new demand forecast data. For example, a demand forecasting algorithm using TensorFlow is used.

[0786] 2. Data analysis and optimization

[0787] The server analyzes the data and generates an optimal delivery plan using the following methods:

[0788] Traffic data analysis: Analyzes real-time traffic information and predicts congestion and travel times on major routes based on the acquired data.

[0789] Inventory Data Analysis: Analyze collected inventory data to identify where needed items are in stock.

[0790] Demand forecasting data analysis: Uses generative AI models to predict future demand and use the results to create optimal delivery plans.

[0791] 3. Optimal Route Generation and Evaluation

[0792] The server uses Dijkstra's algorithm and other optimization algorithms to calculate optimal delivery routes based on collected traffic data and demand forecast data. It also evaluates the fuel efficiency and CO2 emissions of the selected routes and proposes the transportation method with the least environmental impact.

[0793] 4. Recognizing and adjusting user emotions

[0794] The user's device (e.g., smartphone) recognizes the user's emotional state using the following means:

[0795] Emotional data collection: Analyze the user's emotional state in real time based on data such as voice, text, and facial expressions.

[0796] Emotional state determination: Based on the analysis results, the user's emotional state (e.g., stress, elation, indifference, etc.) is determined and sent to the server.

[0797] 5. Dynamic adjustment of delivery plans

[0798] The server dynamically adjusts its delivery plan and transportation suggestions based on the user's emotional state using the following means:

[0799] For users under stress, we prioritize quick and reliable delivery routes.

[0800] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[0801] 6. User Notification and Action

[0802] The terminal will notify the user:

[0803] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0804] Eco-friendly transport methods: Environmentally friendly options such as using electric vehicles and offering shared deliveries.

[0805] Adjustments based on user emotions: Delivery plans and suggestions are optimized to the user's emotional state.

[0806] As a specific example, if a user is judged to be "tired," they will be notified, "Please relax and wait, we will deliver the item as quickly as possible by car," and if a user requests an "eco-friendly delivery method," they will be notified, "We will deliver the item by electric motorcycle."

[0807] Example prompts to input to the generative AI model

[0808] "If the user is fatigued, provide them with the best delivery route and associated plan to respond quickly."

[0809] "For users who wish to use EcoMute, please provide a delivery method that minimizes the environmental impact."

[0810] As a result, the present invention realizes efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[0811] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0812] Step 1:

[0813] The server collects real-time traffic information. Specifically, it uses the API of the traffic information service to obtain traffic data (e.g., congestion status and delay information). The input is real-time traffic data from the API, and the output is the congestion status and predicted travel time as an analysis result. Data processing involves analyzing the congestion level after collecting traffic information and calculating predicted travel times for each major route.

[0814] Step 2:

[0815] The server uses Internet of Things technology to monitor inventory levels in real time and collect data. Specifically, it obtains inventory data from IoT sensors in the warehouse and stores it in a central database. The input is inventory data from the sensors, and the output is real-time inventory levels. Data processing involves collecting data from the sensors to create and update the current inventory status of products.

[0816] Step 3:

[0817] The server uses a generative AI model to perform demand forecasting. The input is past sales data, and the output is future demand forecast data. Specifically, an AI model (e.g., TensorFlow) is used to analyze past sales data and generate a demand forecasting model. Data calculation involves training the model based on past sales trends and calculating a new demand forecast.

[0818] Step 4:

[0819] The server automatically generates optimal delivery routes based on collected traffic data and demand forecast data. The input is real-time traffic data and demand forecast data, and the output is the optimal delivery route proposal. Specifically, it uses Dijkstra's algorithm and other optimization algorithms to calculate the optimal route taking fuel efficiency and travel time into consideration. Data calculations combine the congestion status of each route with demand forecasts to generate effective routes.

[0820] Step 5:

[0821] The device recognizes the user's emotional state. Specifically, it collects data such as voice, text, and facial expressions, and analyzes the emotional state in real time based on this. The input is voice, text, and facial expression data from the device, and the output is the user's emotional state as an analysis result. Data processing involves analyzing the data using an emotion recognition engine (e.g., Affectiva) to determine the current emotional state.

[0822] Step 6:

[0823] The server dynamically adjusts the delivery plan based on the user's emotional state. The input is the user's emotional state data, and the output is an adjusted delivery plan according to the emotion. Specifically, the delivery route and transportation method are changed according to the user's emotional state. For example, a fast delivery route is proposed for a stressed user, and a route with a low environmental impact is proposed for an eco-conscious user. Data calculation involves analyzing the user's emotional data and dynamically updating the delivery plan based on that data.

[0824] Step 7:

[0825] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the adjusted delivery plan, and the output is the notification to the user. Specifically, notifications are sent to smartphones, tablets, etc., providing the user with detailed delivery information (departure time, estimated arrival time, transportation method, etc.). In operation, the system improves user satisfaction by notifying the user of delivery information tailored to the user in real time.

[0826] 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.

[0827] 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.

[0828] 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.

[0829] [Third embodiment]

[0830] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0831] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0832] 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).

[0833] 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.

[0834] 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.

[0835] 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).

[0836] 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.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] 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.

[0841] 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."

[0842] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0843] 1. Data collection and real-time analysis

[0844] The server collects and analyzes the following data:

[0845] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[0846] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[0847] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[0848] 2. Data analysis and optimization

[0849] The server analyzes the data and generates an optimal delivery plan as follows:

[0850] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[0851] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[0852] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[0853] 3. Optimal Route Generation and Evaluation

[0854] The server generates and evaluates optimal delivery routes using the following algorithm:

[0855] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic information and demand forecasts.

[0856] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[0857] 4. Notice to Users

[0858] The device will notify the user of the following:

[0859] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[0860] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[0861] Specific examples

[0862] For example, an online retailer might use the system as follows:

[0863] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[0864] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time monitoring of inventory.

[0865] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[0866] 4. The server calculates the optimal delivery route based on the collected data using Dijkstra's algorithm and generates multiple route options.

[0867] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0868] 6. The device will inform the user of the optimal delivery plan and eco-friendly shipping method.

[0869] In this way, the present invention can realize efficient and environmentally friendly logistics management.

[0870] The processing flow will be explained below.

[0871] Step 1: Data collection

[0872] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[0873] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[0874] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[0875] Step 2: Data analysis

[0876] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[0877] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[0878] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[0879] Step 3: Optimal route generation

[0880] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[0881] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[0882] Step 4: Environmental impact assessment

[0883] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[0884] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[0885] Step 5: Propose eco-friendly transportation methods

[0886] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[0887] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[0888] Step 6: Notification and execution of delivery plan

[0889] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[0890] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[0891] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[0892] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[0893] Example 1

[0894] 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."

[0895] Conventional delivery management systems cannot efficiently utilize real-time traffic information or accurately monitor inventory levels, resulting in delays and errors in demand forecasts. Furthermore, they lack the functionality to automatically suggest transportation methods that take environmental impact into consideration, resulting in insufficient ecological response. To solve these problems, an efficient and environmentally friendly delivery management method is needed.

[0896] 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.

[0897] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using sensor technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient and environmentally friendly delivery management.

[0898] "Generative AI" is an AI that uses past data and algorithms to perform advanced processing such as data analysis, demand forecasting, and calculation of optimal routes.

[0899] "Real-time traffic information" refers to data that provides current traffic conditions, congestion levels, delay information, and other information in real time.

[0900] An "optimal delivery route" is a delivery route calculated based on collected traffic information and demand forecast data to minimize travel time, distance, and environmental impact.

[0901] "Sensor technology" is a general term for hardware and software technologies that monitor the physical environment and interpret it as digital data.

[0902] "Inventory level" is data that indicates the quantity and condition of products currently held in a warehouse, store, etc.

[0903] "Demand forecasting" is the process of predicting future demand based on past sales data and other relevant information.

[0904] A "delivery plan" is a detailed plan for the delivery of goods, including specific routes, departure times, estimated arrival times, and the like.

[0905] "Environmental load" is a general term for the impact on the environment, such as energy consumption and CO2 emissions associated with delivery activities.

[0906] "Eco-friendly transportation methods" refer to transportation means and methods that are environmentally friendly, such as being fuel-efficient and reducing CO2 emissions.

[0907] "User's device" refers to an electronic device used by a user to receive delivery plans and notifications, including a smartphone, tablet, or PC.

[0908] This invention is a system that combines generative artificial intelligence and sensor technology to automatically generate optimal delivery routes based on traffic information, inventory levels, and demand forecasts, and proposes delivery methods that take environmental impact into consideration. This system is implemented using the following hardware and software.

[0909] Major hardware and software

[0910] 1. Server

[0911] Traffic information service API: Used to collect real-time traffic information. Examples include "Google Maps API" and "HERE API."

[0912] Database: Uses the database technology required to store and manage inventory information and sales data. Examples include "MySQL" and "PostgreSQL."

[0913] Generative AI models: Used to perform demand forecasting. Machine learning libraries such as TensorFlow and PyTorch.

[0914] Optimization algorithms: Used to calculate delivery routes. Examples include "Dijkstra's algorithm" and "A algorithm."

[0915] Environmental impact assessment tools: Evaluate fuel efficiency and CO2 emissions. An example is the "Emission Calculation Toolkit."

[0916] 2. Terminal

[0917] Smartphone app: Application software that informs users about delivery plans and eco-friendly shipping methods.

[0918] IoT sensors: Devices placed in warehouses to collect inventory data and send it to a server. Examples include sensors from Zebra Technologies and Bosch Rexroth.

[0919] Specific explanation of the processing content

[0920] The server collects and analyzes real-time traffic information, inventory information, and demand forecast data. The traffic information is analyzed to predict congestion and delays on major routes. The server also receives inventory data sent from IoT sensors in the warehouse and stores it in a central database. This data is used to monitor inventory levels in real time.

[0921] Furthermore, the server uses a generative AI model to forecast future demand based on past sales data, thereby predicting where demand for a particular product will increase.

[0922] Based on the collected and analyzed data, the server calculates the optimal delivery route using Dijkstra's algorithm, and also evaluates the environmental impact of the generated route, proposing the most fuel-efficient and least CO2-emitting transportation method.

[0923] The optimal delivery plan and eco-friendly shipping method will be communicated to the user via the device. For example, a smartphone app could be used to inform the user of the specific delivery route, departure time, and estimated arrival time. Eco-friendly shipping options will also be presented via in-app and email notifications.

[0924] Specific examples

[0925] For example, if an online retailer were to use the system, it would work as follows:

[0926] 1. The server obtains real-time traffic data from a traffic information service API (e.g., Google Maps API) and analyzes busy times and routes.

[0927] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse (e.g., Bosch Rexroth) to the server, enabling real-time inventory monitoring.

[0928] 3. The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand and calculate which products are in demand in which areas.

[0929] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[0930] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[0931] 6. The device will notify the user of optimal delivery plans and eco-friendly shipping methods.

[0932] Prompt Sentence Examples

[0933] Below are some example prompts to input to a generative AI model:

[0934] "Based on past sales data, predict future demand and calculate the optimal delivery route using Dijkstra's algorithm."

[0935] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0936] Step 1: Obtaining real-time traffic information

[0937] The server sends a request to a traffic information service API (e.g., Google Maps API) to obtain real-time traffic information. The input is the API request, and the output is traffic data in JSON format. The server uses this data to calculate congestion and delay predictions. Specifically, the server sends an HTTP request, analyzes the data received as a response, and generates a traffic situation map.

[0938] Step 2: Collect inventory data

[0939] The terminals transmit inventory information obtained from IoT sensors in the warehouse (e.g., "Bosch Rexroth") to a server. The input is inventory data from the IoT sensors, and the output is inventory level information stored in a central database on the server. Specifically, the sensors transmit inventory information using the MQTT protocol, which the server receives and stores in the database. The server monitors the acquired inventory data in real time.

[0940] Step 3: Generate demand forecast data

[0941] The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand. The input is past sales data, and the output is future demand forecast data. The server queries past sales data from a database and inputs it into a machine learning model to calculate the predicted value. Specifically, the server collects sales data and applies it to the predictive model to generate a list of products that will be in high demand.

[0942] Step 4: Analyze traffic data

[0943] The server analyzes real-time traffic information collected and identifies the congestion status of major routes. The input is real-time traffic information, and the output is route information that is predicted to be congested. Specifically, the server uses traffic data to predict travel times and identify congested routes.

[0944] Step 5: Analyze inventory data

[0945] The server analyzes inventory data and identifies where the required items are in stock. The input is inventory data, and the output is inventory location information for each product category. Specifically, the server calculates how much inventory is in which warehouse based on the quantity and location of the inventory items.

[0946] Step 6: Analyze the demand forecast data

[0947] The server analyzes the results of the demand forecasting model and predicts future demand. The input is the demand forecast data, and the output is a list of regions and products where demand will increase. The server aggregates the predicted demand data for each region and identifies which regions will see increased demand in the future.

[0948] Step 7: Generate delivery routes

[0949] The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the traffic information and demand forecast data collected. The input is traffic information and demand forecast data, and the output is the optimal delivery route. Specifically, the server calculates the travel time and distance for each candidate route and generates multiple route options.

[0950] Step 8: Assess the environmental impact

[0951] The server evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the most eco-friendly transportation method. The input is candidate route data, and the output is the route with the least environmental impact. The server uses the "Emission Calculation Toolkit" to calculate the fuel consumption and CO2 emissions for each route.

[0952] Step 9: Delivery plan and eco-friendly shipping notification

[0953] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the optimal delivery plan and eco-friendly transportation method, and the output is the notified information. Specifically, the content is notified to the user via a smartphone app or web portal.

[0954] (Application example 1)

[0955] 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."

[0956] Conventional delivery management systems do not integrate real-time traffic information collection, inventory management, demand forecasting, and environmental impact reduction functions, and are operated by multiple independent systems. This makes it difficult to calculate optimal delivery routes or propose eco-friendly transportation methods, resulting in inefficient management. Furthermore, there is a lack of means to notify users, which can lead to logistics delays and wasteful energy consumption.

[0957] 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.

[0958] In this invention, the server includes: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates optimal delivery routes; a real-time monitoring and data collection system that uses Internet of Things (IoT) technology to monitor inventory levels; a generating AI that performs demand forecasting and automatically generates optimal delivery plans based on the forecasted data; a generating AI that evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method; a notifying system that notifies a user of the optimal delivery plan and the eco-friendly transportation method via a traffic information service API; a collecting and monitoring system that collects and monitors inventory information via an IoT platform within a warehouse; a demand forecasting model that analyzes future demand; and a generating system that generates optimal delivery routes based on Dijkstra's algorithm, thereby enabling the generation of efficient, real-time delivery plans and the proposal of eco-friendly transportation methods.

[0959] "Generative AI" is an artificial intelligence technology that analyzes and predicts collected data to make optimal decisions in real time.

[0960] "Real-time traffic information" refers to data that allows for instantaneous understanding of current traffic conditions, including road congestion and delay information.

[0961] A "delivery route" is a route used to deliver goods or cargo, and aims to optimize the route from the departure point to the destination.

[0962] "Internet of Things technology" is a general term for technologies that allow various sensors and devices to send and receive data via the Internet, enabling real-time monitoring and data collection.

[0963] "Inventory levels" refer to the current amount of goods in a warehouse or stockroom, and are the basis for managing inventory according to demand.

[0964] "Demand forecasting" is the process of predicting future demand based on past data and current conditions, and is useful for determining inventory management and delivery plans.

[0965] An "eco-friendly transportation method" is a means of transportation that minimizes environmental impact, such as fuel efficiency and CO2 emissions, and is a method that aims for sustainable logistics.

[0966] "User's information terminal" is a general term for the terminal used by the user to receive information, including smartphones, tablets, and personal computers.

[0967] "API for traffic information services" refers to an application programming interface provided by a service that provides traffic data, and is used to obtain real-time traffic information.

[0968] An "IoT platform" is a system that serves as the foundation for realizing Internet of Things technology and is used to collect and manage data from sensors.

[0969] A "demand forecasting model" is a statistical or machine learning model for predicting future demand based on past sales data and market trends.

[0970] "Dijkstra's algorithm" is an algorithm that calculates the shortest path based on graph theory, and is used to calculate optimal routes on networks and maps.

[0971] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[0972] The server first obtains real-time traffic data using the API of a traffic information service. Specifically, it uses a common API such as Google Maps API. This data is used to analyze traffic information and determine congestion and expected delay times.

[0973] The server then collects inventory information through the warehouse's IoT platform, using a widely used IoT platform such as AWS IoT Core. Stock levels are monitored in real time and stored in a database, enabling stockout prevention and efficient inventory management.

[0974] Generative AI uses past sales data to generate a demand forecasting model and predict future demand. This model uses machine learning frameworks such as PyTorch. Based on the results of the demand forecast, the server automatically generates an optimal delivery plan.

[0975] The server then generates the optimal delivery route using Dijkstra's algorithm, which is based on the collected traffic information and demand forecast data. After calculating the optimal route, the server evaluates the fuel efficiency and CO2 emissions of each route and suggests the most environmentally friendly transportation method.

[0976] The optimal delivery plan and eco-friendly shipping method are notified to the user's information terminal using services such as Firebase Cloud Messaging, allowing the user to check the optimal delivery plan in real time.

[0977] For example, in a logistics center using the "Smart Logistics Manager" application, logistics managers can simply open the app on their smartphones each morning to check the delivery plan for the day. The app constantly updates real-time traffic information, inventory levels, and demand forecasts, and suggests optimal delivery routes and eco-friendly transportation methods.

[0978] An example of a prompt sentence would be something like the following, which can be input into the generative AI model to provide the necessary data:

[0979] "Calculate the optimal delivery route based on current traffic conditions and inventory levels. Reference historical sales data, forecast demand, and suggest eco-friendly delivery methods."

[0980] This makes it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0981] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0982] Step 1:

[0983] The server obtains real-time traffic data using the API of a traffic information service. Specifically, it obtains current traffic information from sources such as Google Maps API, and analyzes that data to determine congestion and expected delay times. Input data includes congestion status and traffic event information for each road section. Analysis results are saved as output in JSON format or similar.

[0984] Step 2:

[0985] The server collects inventory information through the warehouse's IoT platform. Specifically, it uses a platform such as AWS IoT Core to obtain inventory level data from sensors installed in the warehouse and monitors it in real time. Input data includes product identification codes and current quantities. The output is the latest inventory level stored in a database.

[0986] Step 3:

[0987] The server uses past sales data to generate a demand forecasting model and predict future demand. Specifically, it uses a machine learning framework such as PyTorch to build the demand forecasting model and analyzes past sales data as input. Future demand forecast data is generated as output.

[0988] Step 4:

[0989] The server generates the optimal delivery route using Dijkstra's algorithm. Specifically, it calculates the optimal delivery route using the traffic information acquired in step 1 and the demand forecast data generated in step 3 as input. The algorithm calculates the shortest route based on graph theory. The optimal delivery route is generated as output, and the route information is saved in a database.

[0990] Step 5:

[0991] The server evaluates the fuel efficiency and CO2 emissions of each delivery route and proposes the most environmentally friendly transportation method. Specifically, it calculates environmental evaluation parameters using the delivery route information generated in step 4 as input. The output is the evaluation results of fuel efficiency and CO2 emissions, as well as information on the most eco-friendly route.

[0992] Step 6:

[0993] The device notifies the user of the optimal delivery plan and eco-friendly shipping method. Specifically, a push notification is sent to the user's smartphone or tablet using a notification service such as Firebase Cloud Messaging. The input data includes information on the optimal delivery route and eco-friendly shipping method. The output is that the user receives a notification and can view detailed information on their device.

[0994] The above processing steps make it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[0995] 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.

[0996] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology, as well as a system that includes an emotion engine that recognizes user emotions. This system not only automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and suggests eco-friendly transportation methods that take environmental impact into consideration, but also recognizes the user's emotional state and dynamically adjusts delivery plans and suggestions accordingly.

[0997] 1. Data collection and real-time analysis

[0998] The server collects and analyzes the following data:

[0999] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[1000] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[1001] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[1002] 2. Data analysis and optimization

[1003] The server analyzes the data and generates an optimal delivery plan as follows:

[1004] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[1005] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[1006] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[1007] 3. Optimal Route Generation and Evaluation

[1008] The server generates and evaluates optimal delivery routes using the following algorithm:

[1009] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic data and demand forecasts.

[1010] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[1011] 4. Recognizing and adjusting user emotions

[1012] The emotion engine works as follows:

[1013] The user's emotional state is analyzed in real time based on data collected from the user's device (e.g., voice, text, facial expressions, etc.).

[1014] Based on the analysis results, the user's emotional state (e.g., stress, elation, apathy, etc.) is determined and sent to the server.

[1015] 5. Adjust delivery plans

[1016] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state:

[1017] For users who are under stress, we prioritize quick and reliable delivery routes.

[1018] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1019] 6. User Notification and Action

[1020] The device will notify the user of the following:

[1021] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[1022] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[1023] Adaptation based on user emotions: Providing delivery plans and recommendations that best fit the user's emotional state.

[1024] Specific examples

[1025] For example, an online retailer might use the system as follows:

[1026] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[1027] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time inventory monitoring.

[1028] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[1029] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[1030] 5. The emotion engine analyzes the user's emotional state based on data collected from the user's device and creates delivery suggestions that are optimally tailored to the user's characteristics.

[1031] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on this.

[1032] In this way, the present invention can realize efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[1033] The processing flow will be explained below.

[1034] Step 1: Data collection

[1035] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[1036] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[1037] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[1038] Step 2: Data analysis

[1039] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[1040] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[1041] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[1042] Step 3: Optimal route generation

[1043] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[1044] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[1045] Step 4: Environmental impact assessment

[1046] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[1047] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[1048] Step 5: Propose eco-friendly transportation methods

[1049] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[1050] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[1051] Step 6: Recognizing user emotions

[1052] The device collects the user's voice input, text messages, and facial recognition data.

[1053] An emotion engine analyzes the collected data to determine the user's emotional state in real time, which can include stress, joy, anxiety, etc.

[1054] Step 7: Adjust your shipping plan

[1055] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state.

[1056] For example, a user who is under stress may be given priority in suggesting a fast and reliable delivery route.

[1057] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1058] Step 8: Notification and execution of delivery plan

[1059] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[1060] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[1061] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[1062] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[1063] Example 2

[1064] 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."

[1065] Currently, delivery management systems monitor traffic information and inventory levels, forecast demand, and perform other tasks, but do not adjust delivery plans to take user emotions into account. This poses a challenge as they are unable to respond to users' stress levels and eco-consciousness. This could also lead to a decline in user satisfaction.

[1066] 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.

[1067] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using Internet of Things technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, means for analyzing the user's emotional state using position recognition technology and adjusting the delivery plan based on that emotional state, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient, environmentally friendly, and detailed delivery management that takes user emotions into consideration.

[1068] "Generative AI" is an AI system that automatically performs tasks such as data analysis, prediction, and optimization.

[1069] "Real-time traffic information" refers to instantaneous data such as current road conditions, traffic volume, and delay information.

[1070] The "delivery route" is the route along which the product is delivered.

[1071] "Internet of Things technology" is a technology that allows data to be sent and received between physical devices over the Internet.

[1072] "Stock level" refers to the quantity of goods in a warehouse or store.

[1073] "Demand forecasting" is the prediction of future demand.

[1074] A "delivery plan" is a plan that includes detailed schedules and route settings for delivering products.

[1075] "Environmental impact" refers to the impact that a particular activity or process has on the environment.

[1076] "Transportation Method" means the means or method used to deliver the goods.

[1077] "Emotional state" refers to the user's current psychological and emotional state.

[1078] "Position recognition technology" is a technology that analyzes the user's emotions and psychological state.

[1079] A "user terminal" is an electronic device used by a user, such as a computer or smartphone.

[1080] The present invention relates to a delivery management system that combines artificial intelligence, Internet of Things technology, and position recognition technology. Specifically, the following hardware and software configuration is used.

[1081] Data collection and analysis

[1082] The server collects and analyzes various data. The main hardware used is a server with an internet connection, and the following software is used:

[1083] Real-time traffic information: Real-time traffic data is obtained using the API of a traffic information service (e.g., Google Maps API), which collects congestion and delay information and analyzes it on the server.

[1084] Inventory information: Inventory data is acquired in real time using IoT sensors in the warehouse (e.g., sensors manufactured by Zebra Technologies) and sent to a server, where it is stored in a central database.

[1085] Demand forecast data: Based on past sales data, we update the demand forecasting model (e.g., using TensorFlow) and generate new demand forecast data.

[1086] Data optimization and evaluation

[1087] The server generates an optimal delivery plan and route based on the collected data:

[1088] Traffic data analysis: The acquired traffic information is analyzed and used to understand the congestion status of major routes, which is then used to calculate predicted travel times.

[1089] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[1090] Demand forecast data analysis: Predict future demand and create optimal delivery plans based on that.

[1091] Optimal route generation

[1092] The server calculates the optimal delivery route using Dijkstra's algorithm or other optimization algorithms (e.g., A algorithm). It evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the transportation method with the least environmental impact.

[1093] User Emotion Recognition

[1094] The emotion engine analyzes the user's emotional state in real time using voice, text, and facial expression data collected from the user's device. The emotion analysis uses Microsoft Azure's Emotion API. The analysis results are sent to the server, and the delivery plan is adjusted based on the user's emotional state.

[1095] Notification and execution of delivery plans

[1096] The device notifies the user of the following information:

[1097] Delivery plan: A detailed plan including specific delivery routes, departure times, and estimated arrival times.

[1098] Eco-friendly shipping methods: Offer environmentally friendly options (e.g., using electric trucks or shared deliveries).

[1099] Emotional adjustment: Providing delivery plans and recommendations that best fit the user's emotional state.

[1100] Specific examples

[1101] For example, an online retailer might use the system as follows:

[1102] 1. The server obtains current traffic data from a traffic information service (Google Maps API) and analyzes busy times and routes.

[1103] 2. The terminal transmits inventory information obtained from IoT sensors (manufactured by Zebra Technologies) in the warehouse to the server, enabling real-time inventory monitoring.

[1104] 3. The server updates the demand forecasting model (using TensorFlow) based on past sales data, predicts future demand, and calculates which products are needed in which areas.

[1105] 4. The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the collected data and generate multiple route options.

[1106] 5. The emotion engine analyzes the voice and facial expression data collected from the user's device using Microsoft Azure's Emotion API to determine the user's emotional state in real time.

[1107] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on that information.

[1108] Prompt Sentence Examples

[1109] "Generate an algorithm that optimizes delivery plans, taking into account the following:"

[1110] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1111] Step 1: Data collection

[1112] A server collects real-time traffic information, inventory data, and historical sales data.

[1113] Input: Traffic information service API, IoT sensors in warehouses, past sales data

[1114] Specific operation:

[1115] The server uses the Google Maps API to obtain real-time traffic data.

[1116] The server collects inventory data from Zebra Technologies sensors and stores it in a central database.

[1117] The server retrieves past sales data from the database.

[1118] Output: Traffic data, inventory data, past sales data

[1119] Step 2: Real-time analysis

[1120] The server performs real-time analysis based on the data collected.

[1121] Input: Collected traffic data, inventory data, historical sales data

[1122] Specific operation:

[1123] The server analyzes traffic data to identify congestion and delays.

[1124] The server analyzes the inventory data and determines the current inventory levels.

[1125] The server uses past sales data to update the demand forecasting model (TensorFlow).

[1126] Output: Analyzed traffic data, inventory levels, and up-to-date demand forecast data

[1127] Step 3: Data analysis and supply and demand forecasting

[1128] The server analyzes demand forecasts and supply availability to generate optimal delivery plans.

[1129] Inputs: Parsed traffic data, inventory levels, and the latest demand forecast data

[1130] Specific operation:

[1131] The server calculates the congestion status and travel time for each route based on the latest traffic data.

[1132] The server analyzes the inventory level for each item and determines whether the item is in stock.

[1133] The server uses the demand forecasting model to predict future demand.

[1134] Output: supply and demand balance, recommended inventory levels, predictive delivery plans

[1135] Step 4: Optimal route generation and evaluation

[1136] The server generates the optimal delivery route and evaluates the environmental impact.

[1137] Input: Data analysis results, predicted delivery plan

[1138] Specific operation:

[1139] The server uses Dijkstra's algorithm to calculate the optimal route.

[1140] The server calculates the fuel efficiency and CO2 emissions of each route and evaluates the environmental impact.

[1141] Output: Optimal delivery route, environmental impact assessment results

[1142] Step 5: Recognizing user emotions

[1143] An emotion engine analyzes the user's emotional state.

[1144] Input: User's voice data, text data, facial expression data

[1145] Specific operation:

[1146] The emotion engine uses Microsoft Azure's Emotion API to analyze the user's emotional state in real time.

[1147] The analysis results are sent to the server.

[1148] Output: User sentiment analysis results

[1149] Step 6: Adjust your shipping plan

[1150] The server dynamically adjusts the delivery plan based on the user's emotional state.

[1151] Input: User sentiment analysis results, optimal delivery route, environmental impact assessment results

[1152] Specific operation:

[1153] For users in a stressed state, the server generates a delivery plan that prioritizes the route that can be reached in the shortest time.

[1154] For eco-conscious users, the server adjusts the delivery plan by selecting a transportation method that minimizes the environmental load.

[1155] Output: Adjusted delivery plan

[1156] Step 7: Notify users and take action

[1157] The terminal notifies the user of the adjusted delivery plan and executes it.

[1158] Input: Adjusted delivery plan

[1159] Specific operation:

[1160] The device will send a push notification to the user and display a detailed delivery plan.

[1161] The terminal suggests eco-friendly transportation methods.

[1162] Output: User notification, executed dispatch plan

[1163] (Application example 2)

[1164] 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."

[1165] In food delivery services, the challenge is to flexibly adjust delivery plans and transportation methods based on the user's emotional state, thereby increasing user satisfaction and reducing environmental impact. Current delivery systems calculate optimal delivery routes taking into account real-time traffic and inventory information, but it is difficult to dynamically adjust routes to reflect the user's emotional state. As a result, they are unable to provide detailed support for users who are in a hurry or environmentally conscious.

[1166] 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: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates an optimal delivery route; a means that monitors inventory levels in real time using Internet of Things technology and collects data; a generating AI that performs demand forecasting and automatically generates an optimal delivery plan based on the forecast data; a generating AI that evaluates the environmental impact of each delivery route and suggests the most environmentally friendly transportation method; a means that recognizes the user's emotional state and dynamically adjusts the delivery plan and transportation method based on the emotional state; and a means that notifies the user's terminal of the optimal delivery plan and eco-friendly transportation method. This enables flexible delivery plans that reflect the user's emotional state, thereby improving user satisfaction and reducing environmental impact.

[1167] "Generative AI" refers to AI that makes predictions and analyses based on data and automatically generates optimal plans.

[1168] "Real-time traffic information" refers to data that instantly acquires current traffic conditions and shows congestion and road conditions.

[1169] The "optimal delivery route" is a route selected to minimize delivery time and costs based on collected traffic information, inventory information, and demand forecasts.

[1170] "Internet of Things technology" refers to technology that allows physical devices and sensors to exchange information over the Internet.

[1171] "Inventory level" refers to data that indicates the current amount of goods or materials stored in a warehouse or the like.

[1172] "Demand forecasting" is the process of predicting future demand based on past sales data and market trends.

[1173] A "delivery plan" is a plan that shows the specific schedule, routes, and resource allocation for product delivery.

[1174] "Environmental impact" refers to the impact that activities such as transportation and delivery have on the environment, particularly CO2 emissions and energy consumption.

[1175] "User's emotional state" refers to information that indicates the emotions and mental state that the user is currently feeling.

[1176] "Dynamic adjustment" refers to the flexible modification of plans and methods in response to changing situations and conditions in real time.

[1177] "User terminal" refers to a device through which a user receives information, such as a smartphone or tablet.

[1178] "Eco-friendly transportation" refers to the use of transportation methods that have a lower impact on the environment, such as electric vehicles and bicycles.

[1179] This invention is a system that dynamically adjusts delivery plans and proposes environmentally friendly transportation methods, primarily for food delivery services, taking into account the user's emotional state. Specifically, the system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecast data, and provides flexible delivery plans that reflect the user's emotional state.

[1180] 1. Data collection and real-time analysis

[1181] The server collects and analyzes data using the following means:

[1182] Real-time traffic information: Collected using the API of a traffic information service. For example, an API key from an external traffic information service (e.g., TomTom Traffic) is used to obtain current congestion and delay information.

[1183] Inventory Information: Using Internet of Things technology, real-time inventory data is collected from sensors in the warehouse. Specifically, IoT sensors are used to monitor the stock levels of each product and store them in a central database.

[1184] Demand forecast data: A generative AI model is used to generate a demand forecast model from past sales data and calculate new demand forecast data. For example, a demand forecasting algorithm using TensorFlow is used.

[1185] 2. Data analysis and optimization

[1186] The server analyzes the data and generates an optimal delivery plan using the following methods:

[1187] Traffic data analysis: Analyzes real-time traffic information and predicts congestion and travel times on major routes based on the acquired data.

[1188] Inventory Data Analysis: Analyze collected inventory data to identify where needed items are in stock.

[1189] Demand forecasting data analysis: Uses generative AI models to predict future demand and use the results to create optimal delivery plans.

[1190] 3. Optimal Route Generation and Evaluation

[1191] The server uses Dijkstra's algorithm and other optimization algorithms to calculate optimal delivery routes based on collected traffic data and demand forecast data. It also evaluates the fuel efficiency and CO2 emissions of the selected routes and proposes the transportation method with the least environmental impact.

[1192] 4. Recognizing and adjusting user emotions

[1193] The user's device (e.g., smartphone) recognizes the user's emotional state using the following means:

[1194] Emotional data collection: Analyze the user's emotional state in real time based on data such as voice, text, and facial expressions.

[1195] Emotional state determination: Based on the analysis results, the user's emotional state (e.g., stress, elation, indifference, etc.) is determined and sent to the server.

[1196] 5. Dynamic adjustment of delivery plans

[1197] The server dynamically adjusts its delivery plan and transportation suggestions based on the user's emotional state using the following means:

[1198] For users under stress, we prioritize quick and reliable delivery routes.

[1199] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1200] 6. User Notification and Action

[1201] The terminal will notify the user:

[1202] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[1203] Eco-friendly transport methods: Environmentally friendly options such as using electric vehicles and offering shared deliveries.

[1204] Adjustments based on user emotions: Delivery plans and suggestions are optimized to the user's emotional state.

[1205] As a specific example, if a user is judged to be "tired," they will be notified, "Please relax and wait, we will deliver the item as quickly as possible by car," and if a user requests an "eco-friendly delivery method," they will be notified, "We will deliver the item by electric motorcycle."

[1206] Example prompts to input to the generative AI model

[1207] "If the user is fatigued, provide them with the best delivery route and associated plan to respond quickly."

[1208] "For users who wish to use EcoMute, please provide a delivery method that minimizes the environmental impact."

[1209] As a result, the present invention realizes efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[1210] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1211] Step 1:

[1212] The server collects real-time traffic information. Specifically, it uses the API of the traffic information service to obtain traffic data (e.g., congestion status and delay information). The input is real-time traffic data from the API, and the output is the congestion status and predicted travel time as an analysis result. Data processing involves analyzing the congestion level after collecting traffic information and calculating predicted travel times for each major route.

[1213] Step 2:

[1214] The server uses Internet of Things technology to monitor inventory levels in real time and collect data. Specifically, it obtains inventory data from IoT sensors in the warehouse and stores it in a central database. The input is inventory data from the sensors, and the output is real-time inventory levels. Data processing involves collecting data from the sensors to create and update the current inventory status of products.

[1215] Step 3:

[1216] The server uses a generative AI model to perform demand forecasting. The input is past sales data, and the output is future demand forecast data. Specifically, an AI model (e.g., TensorFlow) is used to analyze past sales data and generate a demand forecasting model. Data calculation involves training the model based on past sales trends and calculating a new demand forecast.

[1217] Step 4:

[1218] The server automatically generates optimal delivery routes based on collected traffic data and demand forecast data. The input is real-time traffic data and demand forecast data, and the output is the optimal delivery route proposal. Specifically, it uses Dijkstra's algorithm and other optimization algorithms to calculate the optimal route taking fuel efficiency and travel time into consideration. Data calculations combine the congestion status of each route with demand forecasts to generate effective routes.

[1219] Step 5:

[1220] The device recognizes the user's emotional state. Specifically, it collects data such as voice, text, and facial expressions, and analyzes the emotional state in real time based on this. The input is voice, text, and facial expression data from the device, and the output is the user's emotional state as an analysis result. Data processing involves analyzing the data using an emotion recognition engine (e.g., Affectiva) to determine the current emotional state.

[1221] Step 6:

[1222] The server dynamically adjusts the delivery plan based on the user's emotional state. The input is the user's emotional state data, and the output is an adjusted delivery plan according to the emotion. Specifically, the delivery route and transportation method are changed according to the user's emotional state. For example, a fast delivery route is proposed for a stressed user, and a route with a low environmental impact is proposed for an eco-conscious user. Data calculation involves analyzing the user's emotional data and dynamically updating the delivery plan based on that data.

[1223] Step 7:

[1224] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the adjusted delivery plan, and the output is the notification to the user. Specifically, notifications are sent to smartphones, tablets, etc., providing the user with detailed delivery information (departure time, estimated arrival time, transportation method, etc.). In operation, the system improves user satisfaction by notifying the user of delivery information tailored to the user in real time.

[1225] 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.

[1226] 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.

[1227] 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.

[1228] [Fourth embodiment]

[1229] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1230] 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.

[1231] 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).

[1232] 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.

[1233] 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.

[1234] 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).

[1235] 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.

[1236] 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.

[1237] 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.

[1238] 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.

[1239] 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.

[1240] 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.

[1241] 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."

[1242] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[1243] 1. Data collection and real-time analysis

[1244] The server collects and analyzes the following data:

[1245] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[1246] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[1247] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[1248] 2. Data analysis and optimization

[1249] The server analyzes the data and generates an optimal delivery plan as follows:

[1250] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[1251] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[1252] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[1253] 3. Optimal Route Generation and Evaluation

[1254] The server generates and evaluates optimal delivery routes using the following algorithm:

[1255] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic information and demand forecasts.

[1256] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[1257] 4. Notice to Users

[1258] The device will notify the user of the following:

[1259] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[1260] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[1261] Specific examples

[1262] For example, an online retailer might use the system as follows:

[1263] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[1264] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time monitoring of inventory.

[1265] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[1266] 4. The server calculates the optimal delivery route based on the collected data using Dijkstra's algorithm and generates multiple route options.

[1267] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[1268] 6. The device will inform the user of the optimal delivery plan and eco-friendly shipping method.

[1269] In this way, the present invention can realize efficient and environmentally friendly logistics management.

[1270] The processing flow will be explained below.

[1271] Step 1: Data collection

[1272] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[1273] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[1274] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[1275] Step 2: Data analysis

[1276] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[1277] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[1278] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[1279] Step 3: Optimal route generation

[1280] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[1281] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[1282] Step 4: Environmental impact assessment

[1283] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[1284] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[1285] Step 5: Propose eco-friendly transportation methods

[1286] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[1287] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[1288] Step 6: Notification and execution of delivery plan

[1289] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[1290] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[1291] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[1292] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[1293] Example 1

[1294] 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."

[1295] Conventional delivery management systems cannot efficiently utilize real-time traffic information or accurately monitor inventory levels, resulting in delays and errors in demand forecasts. Furthermore, they lack the functionality to automatically suggest transportation methods that take environmental impact into consideration, resulting in insufficient ecological response. To solve these problems, an efficient and environmentally friendly delivery management method is needed.

[1296] 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.

[1297] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using sensor technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient and environmentally friendly delivery management.

[1298] "Generative AI" is an AI that uses past data and algorithms to perform advanced processing such as data analysis, demand forecasting, and calculation of optimal routes.

[1299] "Real-time traffic information" refers to data that provides current traffic conditions, congestion levels, delay information, and other information in real time.

[1300] An "optimal delivery route" is a delivery route calculated based on collected traffic information and demand forecast data to minimize travel time, distance, and environmental impact.

[1301] "Sensor technology" is a general term for hardware and software technologies that monitor the physical environment and interpret it as digital data.

[1302] "Inventory level" is data that indicates the quantity and condition of products currently held in a warehouse, store, etc.

[1303] "Demand forecasting" is the process of predicting future demand based on past sales data and other relevant information.

[1304] A "delivery plan" is a detailed plan for the delivery of goods, including specific routes, departure times, estimated arrival times, and the like.

[1305] "Environmental load" is a general term for the impact on the environment, such as energy consumption and CO2 emissions associated with delivery activities.

[1306] "Eco-friendly transportation methods" refer to transportation means and methods that are environmentally friendly, such as being fuel-efficient and reducing CO2 emissions.

[1307] "User's device" refers to an electronic device used by a user to receive delivery plans and notifications, including a smartphone, tablet, or PC.

[1308] This invention is a system that combines generative artificial intelligence and sensor technology to automatically generate optimal delivery routes based on traffic information, inventory levels, and demand forecasts, and proposes delivery methods that take environmental impact into consideration. This system is implemented using the following hardware and software.

[1309] Major hardware and software

[1310] 1. Server

[1311] Traffic information service API: Used to collect real-time traffic information. Examples include "Google Maps API" and "HERE API."

[1312] Database: Uses the database technology required to store and manage inventory information and sales data. Examples include "MySQL" and "PostgreSQL."

[1313] Generative AI models: Used to perform demand forecasting. Machine learning libraries such as TensorFlow and PyTorch.

[1314] Optimization algorithms: Used to calculate delivery routes. Examples include "Dijkstra's algorithm" and "A algorithm."

[1315] Environmental impact assessment tools: Evaluate fuel efficiency and CO2 emissions. An example is the "Emission Calculation Toolkit."

[1316] 2. Terminal

[1317] Smartphone app: Application software that informs users about delivery plans and eco-friendly shipping methods.

[1318] IoT sensors: Devices placed in warehouses to collect inventory data and send it to a server. Examples include sensors from Zebra Technologies and Bosch Rexroth.

[1319] Specific explanation of the processing content

[1320] The server collects and analyzes real-time traffic information, inventory information, and demand forecast data. The traffic information is analyzed to predict congestion and delays on major routes. The server also receives inventory data sent from IoT sensors in the warehouse and stores it in a central database. This data is used to monitor inventory levels in real time.

[1321] Furthermore, the server uses a generative AI model to forecast future demand based on past sales data, thereby predicting where demand for a particular product will increase.

[1322] Based on the collected and analyzed data, the server calculates the optimal delivery route using Dijkstra's algorithm, and also evaluates the environmental impact of the generated route, proposing the most fuel-efficient and least CO2-emitting transportation method.

[1323] The optimal delivery plan and eco-friendly shipping method will be communicated to the user via the device. For example, a smartphone app could be used to inform the user of the specific delivery route, departure time, and estimated arrival time. Eco-friendly shipping options will also be presented via in-app and email notifications.

[1324] Specific examples

[1325] For example, if an online retailer were to use the system, it would work as follows:

[1326] 1. The server obtains real-time traffic data from a traffic information service API (e.g., Google Maps API) and analyzes busy times and routes.

[1327] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse (e.g., Bosch Rexroth) to the server, enabling real-time inventory monitoring.

[1328] 3. The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand and calculate which products are in demand in which areas.

[1329] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[1330] 5. The server evaluates the fuel efficiency and CO2 emissions of each route option and suggests the most eco-friendly transportation method.

[1331] 6. The device will notify the user of optimal delivery plans and eco-friendly shipping methods.

[1332] Prompt Sentence Examples

[1333] Below are some example prompts to input to a generative AI model:

[1334] "Based on past sales data, predict future demand and calculate the optimal delivery route using Dijkstra's algorithm."

[1335] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1336] Step 1: Obtaining real-time traffic information

[1337] The server sends a request to a traffic information service API (e.g., Google Maps API) to obtain real-time traffic information. The input is the API request, and the output is traffic data in JSON format. The server uses this data to calculate congestion and delay predictions. Specifically, the server sends an HTTP request, analyzes the data received as a response, and generates a traffic situation map.

[1338] Step 2: Collect inventory data

[1339] The terminals transmit inventory information obtained from IoT sensors in the warehouse (e.g., "Bosch Rexroth") to a server. The input is inventory data from the IoT sensors, and the output is inventory level information stored in a central database on the server. Specifically, the sensors transmit inventory information using the MQTT protocol, which the server receives and stores in the database. The server monitors the acquired inventory data in real time.

[1340] Step 3: Generate demand forecast data

[1341] The server uses a generative AI model (e.g., TensorFlow) based on past sales data to predict future demand. The input is past sales data, and the output is future demand forecast data. The server queries past sales data from a database and inputs it into a machine learning model to calculate the predicted value. Specifically, the server collects sales data and applies it to the predictive model to generate a list of products that will be in high demand.

[1342] Step 4: Analyze traffic data

[1343] The server analyzes real-time traffic information collected and grasps the congestion status of major routes. The input is real-time traffic information, and the output is route information that is predicted to be congested. Specifically, the server uses traffic data to predict travel times and identify congested routes.

[1344] Step 5: Analyze inventory data

[1345] The server analyzes inventory data and identifies where the required items are in stock. The input is inventory data, and the output is inventory location information for each product category. Specifically, the server calculates how much inventory is in which warehouse based on the quantity and location of the inventory items.

[1346] Step 6: Analyze the demand forecast data

[1347] The server analyzes the results of the demand forecasting model and predicts future demand. The input is the demand forecast data, and the output is a list of regions and products where demand will increase. The server aggregates the predicted demand data for each region and identifies which regions will see increased demand in the future.

[1348] Step 7: Generate delivery routes

[1349] The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the traffic information and demand forecast data collected. The input is traffic information and demand forecast data, and the output is the optimal delivery route. Specifically, the server calculates the travel time and distance for each candidate route and generates multiple route options.

[1350] Step 8: Assess the environmental impact

[1351] The server evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the most eco-friendly transportation method. The input is candidate route data, and the output is the route with the least environmental impact. The server uses the "Emission Calculation Toolkit" to calculate the fuel consumption and CO2 emissions for each route.

[1352] Step 9: Delivery plan and eco-friendly shipping notification

[1353] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the optimal delivery plan and eco-friendly transportation method, and the output is the notified information. Specifically, the content is notified to the user via a smartphone app or web portal.

[1354] (Application example 1)

[1355] 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."

[1356] Conventional delivery management systems do not integrate real-time traffic information collection, inventory management, demand forecasting, and environmental impact reduction functions, and are operated by multiple independent systems. This makes it difficult to calculate optimal delivery routes or propose eco-friendly transportation methods, resulting in inefficient management. Furthermore, there is a lack of means to notify users, which can lead to logistics delays and wasteful energy consumption.

[1357] 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.

[1358] In this invention, the server includes: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates optimal delivery routes; a real-time monitoring and data collection system that uses Internet of Things (IoT) technology to monitor inventory levels; a generating AI that performs demand forecasting and automatically generates optimal delivery plans based on the forecasted data; a generating AI that evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method; a notifying system that notifies a user of the optimal delivery plan and the eco-friendly transportation method via a traffic information service API; a collecting and monitoring system that collects and monitors inventory information via an IoT platform within a warehouse; a demand forecasting model that analyzes future demand; and a generating system that generates optimal delivery routes based on Dijkstra's algorithm, thereby enabling the generation of efficient, real-time delivery plans and the proposal of eco-friendly transportation methods.

[1359] "Generative AI" is an artificial intelligence technology that analyzes and predicts collected data to make optimal decisions in real time.

[1360] "Real-time traffic information" refers to data that allows for instantaneous understanding of current traffic conditions, including road congestion and delay information.

[1361] A "delivery route" is a route used to deliver goods or cargo, and aims to optimize the route from the departure point to the destination.

[1362] "Internet of Things technology" is a general term for technologies that allow various sensors and devices to send and receive data via the Internet, enabling real-time monitoring and data collection.

[1363] "Inventory levels" refer to the current amount of goods in a warehouse or stockroom, and are the basis for managing inventory according to demand.

[1364] "Demand forecasting" is the process of predicting future demand based on past data and current conditions, and is useful for determining inventory management and delivery plans.

[1365] An "eco-friendly transportation method" is a means of transportation that minimizes environmental impact, such as fuel efficiency and CO2 emissions, and is a method that aims for sustainable logistics.

[1366] "User's information terminal" is a general term for the terminal used by the user to receive information, including smartphones, tablets, and personal computers.

[1367] "API for traffic information services" refers to an application programming interface provided by a service that provides traffic data, and is used to obtain real-time traffic information.

[1368] An "IoT platform" is a system that serves as the foundation for realizing Internet of Things technology and is used to collect and manage data from sensors.

[1369] A "demand forecasting model" is a statistical or machine learning model for predicting future demand based on past sales data and market trends.

[1370] "Dijkstra's algorithm" is an algorithm that calculates the shortest path based on graph theory, and is used to calculate optimal routes on networks and maps.

[1371] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology. This system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and proposes eco-friendly transportation methods that take environmental impact into consideration.

[1372] The server first obtains real-time traffic data using the API of a traffic information service. Specifically, it uses a common API such as Google Maps API. This data is used to analyze traffic information and determine congestion and expected delay times.

[1373] The server then collects inventory information through the warehouse's IoT platform, using a widely used IoT platform such as AWS IoT Core. Stock levels are monitored in real time and stored in a database, enabling stockout prevention and efficient inventory management.

[1374] Generative AI uses past sales data to generate a demand forecasting model and predict future demand. This model uses machine learning frameworks such as PyTorch. Based on the results of the demand forecast, the server automatically generates an optimal delivery plan.

[1375] The server then generates the optimal delivery route using Dijkstra's algorithm, which is based on the collected traffic information and demand forecast data. After calculating the optimal route, the server evaluates the fuel efficiency and CO2 emissions of each route and suggests the most environmentally friendly transportation method.

[1376] The optimal delivery plan and eco-friendly shipping method are notified to the user's information terminal using services such as Firebase Cloud Messaging, allowing the user to check the optimal delivery plan in real time.

[1377] For example, in a logistics center using the "Smart Logistics Manager" application, logistics managers can simply open the app on their smartphones each morning to check the delivery plan for the day. The app constantly updates real-time traffic information, inventory levels, and demand forecasts, and suggests optimal delivery routes and eco-friendly transportation methods.

[1378] An example of a prompt sentence would be something like the following, which can be input into the generative AI model to provide the necessary data:

[1379] "Calculate the optimal delivery route based on current traffic conditions and inventory levels. Reference historical sales data, forecast demand, and suggest eco-friendly delivery methods."

[1380] This makes it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[1381] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1382] Step 1:

[1383] The server obtains real-time traffic data using the API of a traffic information service. Specifically, it obtains current traffic information from sources such as Google Maps API, and analyzes that data to determine congestion and expected delay times. Input data includes congestion status and traffic event information for each road section. Analysis results are saved as output in JSON format or similar.

[1384] Step 2:

[1385] The server collects inventory information through the warehouse's IoT platform. Specifically, it uses a platform such as AWS IoT Core to obtain inventory level data from sensors installed in the warehouse and monitors it in real time. Input data includes product identification codes and current quantities. The output is the latest inventory level stored in a database.

[1386] Step 3:

[1387] The server uses past sales data to generate a demand forecasting model and predict future demand. Specifically, it uses a machine learning framework such as PyTorch to build the demand forecasting model and analyzes past sales data as input. Future demand forecast data is generated as output.

[1388] Step 4:

[1389] The server generates the optimal delivery route using Dijkstra's algorithm. Specifically, it calculates the optimal delivery route using the traffic information acquired in step 1 and the demand forecast data generated in step 3 as input. The algorithm calculates the shortest route based on graph theory. The optimal delivery route is generated as output, and the route information is saved in a database.

[1390] Step 5:

[1391] The server evaluates the fuel efficiency and CO2 emissions of each delivery route and proposes the most environmentally friendly transportation method. Specifically, it calculates environmental evaluation parameters using the delivery route information generated in step 4 as input. The output is the evaluation results of fuel efficiency and CO2 emissions, as well as information on the most eco-friendly route.

[1392] Step 6:

[1393] The device notifies the user of the optimal delivery plan and eco-friendly shipping method. Specifically, a push notification is sent to the user's smartphone or tablet using a notification service such as Firebase Cloud Messaging. The input data includes information on the optimal delivery route and eco-friendly shipping method. The output is that the user receives a notification and can view detailed information on their device.

[1394] The above processing steps make it possible to generate efficient, real-time delivery plans and propose eco-friendly transportation methods.

[1395] 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.

[1396] This invention relates to a delivery management system that combines generative artificial intelligence and Internet of Things technology, as well as a system that includes an emotion engine that recognizes user emotions. This system not only automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecasts, and suggests eco-friendly transportation methods that take environmental impact into consideration, but also recognizes the user's emotional state and dynamically adjusts delivery plans and suggestions accordingly.

[1397] 1. Data collection and real-time analysis

[1398] The server collects and analyzes the following data:

[1399] Real-time traffic information: Analyzes congestion and delays using data obtained from the API of a traffic information service.

[1400] Inventory information: Inventory data collected from IoT sensors in the warehouse is stored in a central database to monitor stock levels in real time.

[1401] Demand forecast data: Update the demand forecast model generated based on past sales data and calculate new demand forecast data.

[1402] 2. Data analysis and optimization

[1403] The server analyzes the data and generates an optimal delivery plan as follows:

[1404] Traffic data analysis: Analyzes acquired real-time traffic information to understand congestion on major routes and predict travel times.

[1405] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[1406] Demand forecasting data analysis: Uses a demand forecasting model to predict future demand and use the results to create optimal delivery plans.

[1407] 3. Optimal Route Generation and Evaluation

[1408] The server generates and evaluates optimal delivery routes using the following algorithm:

[1409] Dijkstra's algorithm and other optimization algorithms are used to calculate optimal delivery routes based on collected traffic data and demand forecasts.

[1410] The selected route will be evaluated for fuel efficiency and CO2 emissions, and the transportation method with the least environmental impact will be proposed.

[1411] 4. Recognizing and adjusting user emotions

[1412] The emotion engine works as follows:

[1413] The user's emotional state is analyzed in real time based on data collected from the user's device (e.g., voice, text, facial expressions, etc.).

[1414] Based on the analysis results, the user's emotional state (e.g., stress, elation, apathy, etc.) is determined and sent to the server.

[1415] 5. Adjust delivery plans

[1416] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state:

[1417] For users who are under stress, we prioritize quick and reliable delivery routes.

[1418] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1419] 6. User Notification and Action

[1420] The device will notify the user of the following:

[1421] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[1422] Eco-friendly shipping methods: Environmentally friendly options such as using electric trucks and offering shared deliveries.

[1423] Adaptation based on user emotions: Providing delivery plans and recommendations that best fit the user's emotional state.

[1424] Specific examples

[1425] For example, an online retailer might use the system as follows:

[1426] 1. The server obtains current traffic data from a traffic information service and analyzes busy times and routes.

[1427] 2. The terminal transmits inventory information obtained from IoT sensors in the warehouse to the server, enabling real-time inventory monitoring.

[1428] 3. The server uses past sales data to forecast future demand and calculates which products are needed in which areas.

[1429] 4. Based on the data collected by the server, the optimal delivery route is calculated using Dijkstra's algorithm and multiple route options are generated.

[1430] 5. The emotion engine analyzes the user's emotional state based on data collected from the user's device and creates delivery suggestions that are optimally tailored to the user's characteristics.

[1431] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on this.

[1432] In this way, the present invention can realize efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[1433] The processing flow will be explained below.

[1434] Step 1: Data collection

[1435] The server uses the API of the traffic information service to obtain real-time traffic data, specifically, data on major road congestion, accidents, construction work, etc.

[1436] The terminal collects inventory information in real time from IoT sensors in the warehouse and sends it to the server. The inventory information includes the quantity of each product, storage location, and inventory history.

[1437] The server references historical sales data and collects data to update the demand forecasting model, including sales quantities, dates, and consumer buying patterns for specific products.

[1438] Step 2: Data analysis

[1439] The server analyzes the collected traffic data and predicts congestion and delays on major routes. For example, it calculates the estimated travel time for congested sections and considers alternative routes.

[1440] The server consolidates the inventory information sent from each warehouse and analyzes the current inventory status, detecting excess or shortage of stock and suggesting the ordering or movement of specific products.

[1441] The server uses the updated demand forecasting model to predict future demand, specifically forecasting sales for the next month and peak demand for a specific period, and then creates inventory and delivery plans based on the forecast.

[1442] Step 3: Optimal route generation

[1443] The server calculates the optimal delivery route using Dijkstra's algorithm or other routing algorithms, and generates multiple route options based on the collected traffic data and demand forecast results.

[1444] The terminal visually displays to the user the generated route options, each including departure time, estimated arrival time, distance traveled, and predicted traffic conditions.

[1445] Step 4: Environmental impact assessment

[1446] The server evaluates the environmental impact of each route option, calculating fuel efficiency and CO2 emissions based on the distance and travel time of each route.

[1447] The device displays to the user the environmental impact assessment results for each route, including CO2 emissions, fuel efficiency, and eco-friendliness.

[1448] Step 5: Propose eco-friendly transportation methods

[1449] Based on each route option, the server will suggest the most eco-friendly transportation method, such as using electric trucks or suggesting shared deliveries that combine multiple destinations on a single route.

[1450] The device displays eco-friendly transportation suggestions to the user, including the environmental impact and benefits of the selected transportation method.

[1451] Step 6: Recognizing user emotions

[1452] The device collects the user's voice input, text messages, and facial recognition data.

[1453] An emotion engine analyzes the collected data to determine the user's emotional state in real time, which can include stress, joy, anxiety, etc.

[1454] Step 7: Adjust your shipping plan

[1455] The server dynamically adjusts delivery plans and transportation suggestions based on the user's emotional state.

[1456] For example, a user who is under stress may be given priority in suggesting a fast and reliable delivery route.

[1457] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1458] Step 8: Notification and execution of delivery plan

[1459] The server generates the final delivery plan and notifies each stakeholder. The delivery plan includes route details, estimated departure and arrival times, vehicles to be used, and transportation methods.

[1460] The terminal displays the confirmed delivery plan to the user and prompts the user to confirm its contents. After confirmation, delivery begins.

[1461] The user carries out the delivery based on the delivery plan displayed on the device. During the delivery, the device transmits real-time location information and delivery status to the server, which continuously monitors the delivery status.

[1462] The above is a specific processing flow of the delivery management system of the present invention. This system makes it possible to realize efficient delivery plans and reduce environmental impact.

[1463] Example 2

[1464] 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."

[1465] Currently, delivery management systems monitor traffic information and inventory levels, forecast demand, and perform other tasks, but do not adjust delivery plans to take user emotions into account. This poses a challenge as they are unable to respond to users' stress levels and eco-consciousness. This could also lead to a decline in user satisfaction.

[1466] 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.

[1467] In this invention, the server includes means for collecting and analyzing real-time traffic information and calculating the optimal delivery route, means for monitoring inventory levels in real time using Internet of Things technology and collecting data, means for a generating AI to forecast demand and automatically generate an optimal delivery plan based on the forecast data, means for the generating AI to evaluate the environmental impact of each delivery route and propose the most environmentally friendly transportation method, means for analyzing the user's emotional state using position recognition technology and adjusting the delivery plan based on that emotional state, and means for notifying the user's terminal of the optimal delivery plan and eco-friendly transportation method, thereby enabling efficient, environmentally friendly, and detailed delivery management that takes user emotions into consideration.

[1468] "Generative AI" is an AI system that automatically performs tasks such as data analysis, prediction, and optimization.

[1469] "Real-time traffic information" refers to instantaneous data such as current road conditions, traffic volume, and delay information.

[1470] The "delivery route" is the route along which the product is delivered.

[1471] "Internet of Things technology" is a technology that allows data to be sent and received between physical devices over the Internet.

[1472] "Stock level" refers to the quantity of goods in a warehouse or store.

[1473] "Demand forecasting" is the prediction of future demand.

[1474] A "delivery plan" is a plan that includes detailed schedules and route settings for delivering products.

[1475] "Environmental impact" refers to the impact that a particular activity or process has on the environment.

[1476] "Transportation Method" means the means or method used to deliver the goods.

[1477] "Emotional state" refers to the user's current psychological and emotional state.

[1478] "Position recognition technology" is a technology that analyzes the user's emotions and psychological state.

[1479] A "user terminal" is an electronic device used by a user, such as a computer or smartphone.

[1480] The present invention relates to a delivery management system that combines artificial intelligence, Internet of Things technology, and position recognition technology. Specifically, the following hardware and software configuration is used.

[1481] Data collection and analysis

[1482] The server collects and analyzes various data. The main hardware used is a server with an internet connection, and the following software is used:

[1483] Real-time traffic information: Real-time traffic data is obtained using the API of a traffic information service (e.g., Google Maps API), which collects congestion and delay information and analyzes it on the server.

[1484] Inventory information: Inventory data is acquired in real time using IoT sensors in the warehouse (e.g., sensors manufactured by Zebra Technologies) and sent to a server, where it is stored in a central database.

[1485] Demand forecast data: Based on past sales data, we update the demand forecasting model (e.g., using TensorFlow) and generate new demand forecast data.

[1486] Data optimization and evaluation

[1487] The server generates an optimal delivery plan and route based on the collected data:

[1488] Traffic data analysis: The acquired traffic information is analyzed and used to understand the congestion status of major routes, which is then used to calculate predicted travel times.

[1489] Inventory Data Analysis: Analyze inventory levels and identify where needed items are in stock.

[1490] Demand forecast data analysis: Predict future demand and create optimal delivery plans based on that.

[1491] Optimal route generation

[1492] The server calculates the optimal delivery route using Dijkstra's algorithm or other optimization algorithms (e.g., A algorithm). It evaluates the fuel efficiency and CO2 emissions of the selected route and proposes the transportation method with the least environmental impact.

[1493] User Emotion Recognition

[1494] The emotion engine analyzes the user's emotional state in real time using voice, text, and facial expression data collected from the user's device. The emotion analysis uses Microsoft Azure's Emotion API. The analysis results are sent to the server, and the delivery plan is adjusted based on the user's emotional state.

[1495] Notification and execution of delivery plans

[1496] The device notifies the user of the following information:

[1497] Delivery plan: A detailed plan including specific delivery routes, departure times, and estimated arrival times.

[1498] Eco-friendly shipping methods: Offer environmentally friendly options (e.g., using electric trucks or shared deliveries).

[1499] Emotional adjustment: Providing delivery plans and recommendations that best fit the user's emotional state.

[1500] Specific examples

[1501] For example, an online retailer might use the system as follows:

[1502] 1. The server obtains current traffic data from a traffic information service (Google Maps API) and analyzes busy times and routes.

[1503] 2. The terminal transmits inventory information obtained from IoT sensors (manufactured by Zebra Technologies) in the warehouse to the server, enabling real-time inventory monitoring.

[1504] 3. The server updates the demand forecasting model (using TensorFlow) based on past sales data, predicts future demand, and calculates which products are needed in which areas.

[1505] 4. The server uses Dijkstra's algorithm to calculate the optimal delivery route based on the collected data and generate multiple route options.

[1506] 5. The emotion engine analyzes the voice and facial expression data collected from the user's device using Microsoft Azure's Emotion API to determine the user's emotional state in real time.

[1507] 6. The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method, and the user carries out the delivery based on that information.

[1508] Prompt Sentence Examples

[1509] "Generate an algorithm that optimizes delivery plans, taking into account the following:"

[1510] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1511] Step 1: Data collection

[1512] A server collects real-time traffic information, inventory data, and historical sales data.

[1513] Input: Traffic information service API, IoT sensors in warehouses, past sales data

[1514] Specific operation:

[1515] The server uses the Google Maps API to obtain real-time traffic data.

[1516] The server collects inventory data from Zebra Technologies sensors and stores it in a central database.

[1517] The server retrieves past sales data from the database.

[1518] Output: Traffic data, inventory data, past sales data

[1519] Step 2: Real-time analysis

[1520] The server performs real-time analysis based on the data collected.

[1521] Input: Collected traffic data, inventory data, historical sales data

[1522] Specific operation:

[1523] The server analyzes traffic data to identify congestion and delays.

[1524] The server analyzes the inventory data and determines the current inventory levels.

[1525] The server uses past sales data to update the demand forecasting model (TensorFlow).

[1526] Output: Analyzed traffic data, inventory levels, and up-to-date demand forecast data

[1527] Step 3: Data analysis and supply and demand forecasting

[1528] The server analyzes demand forecasts and supply availability to generate optimal delivery plans.

[1529] Inputs: Parsed traffic data, inventory levels, and the latest demand forecast data

[1530] Specific operation:

[1531] The server calculates the congestion status and travel time for each route based on the latest traffic data.

[1532] The server analyzes the inventory level for each item and determines whether the item is in stock.

[1533] The server uses the demand forecasting model to predict future demand.

[1534] Output: supply and demand balance, recommended inventory levels, predictive delivery plans

[1535] Step 4: Optimal route generation and evaluation

[1536] The server generates the optimal delivery route and evaluates the environmental impact.

[1537] Input: Data analysis results, predicted delivery plan

[1538] Specific operation:

[1539] The server uses Dijkstra's algorithm to calculate the optimal route.

[1540] The server calculates the fuel efficiency and CO2 emissions of each route and evaluates the environmental impact.

[1541] Output: Optimal delivery route, environmental impact assessment results

[1542] Step 5: Recognizing user emotions

[1543] An emotion engine analyzes the user's emotional state.

[1544] Input: User's voice data, text data, facial expression data

[1545] Specific operation:

[1546] The emotion engine uses Microsoft Azure's Emotion API to analyze the user's emotional state in real time.

[1547] The analysis results are sent to the server.

[1548] Output: User sentiment analysis results

[1549] Step 6: Adjust your shipping plan

[1550] The server dynamically adjusts the delivery plan based on the user's emotional state.

[1551] Input: User sentiment analysis results, optimal delivery route, environmental impact assessment results

[1552] Specific operation:

[1553] For users in a stressed state, the server generates a delivery plan that prioritizes the route that can be reached in the shortest time.

[1554] For eco-conscious users, the server adjusts the delivery plan by selecting a transportation method that minimizes the environmental load.

[1555] Output: Adjusted delivery plan

[1556] Step 7: Notify users and take action

[1557] The terminal notifies the user of the adjusted delivery plan and executes it.

[1558] Input: Adjusted delivery plan

[1559] Specific operation:

[1560] The device will send a push notification to the user and display a detailed delivery plan.

[1561] The terminal suggests eco-friendly transportation methods.

[1562] Output: User notification, executed dispatch plan

[1563] (Application example 2)

[1564] 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."

[1565] In food delivery services, the challenge is to flexibly adjust delivery plans and transportation methods based on the user's emotional state, thereby increasing user satisfaction and reducing environmental impact. Current delivery systems calculate optimal delivery routes taking into account real-time traffic and inventory information, but it is difficult to dynamically adjust routes to reflect the user's emotional state. As a result, they are unable to provide detailed support for users who are in a hurry or environmentally conscious.

[1566] 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: a generating artificial intelligence (AI) that collects and analyzes real-time traffic information and calculates an optimal delivery route; a means that monitors inventory levels in real time using Internet of Things technology and collects data; a generating AI that performs demand forecasting and automatically generates an optimal delivery plan based on the forecast data; a generating AI that evaluates the environmental impact of each delivery route and suggests the most environmentally friendly transportation method; a means that recognizes the user's emotional state and dynamically adjusts the delivery plan and transportation method based on the emotional state; and a means that notifies the user's terminal of the optimal delivery plan and eco-friendly transportation method. This enables flexible delivery plans that reflect the user's emotional state, thereby improving user satisfaction and reducing environmental impact.

[1567] "Generative AI" refers to AI that makes predictions and analyses based on data and automatically generates optimal plans.

[1568] "Real-time traffic information" refers to data that instantly acquires current traffic conditions and shows congestion and road conditions.

[1569] The "optimal delivery route" is a route selected to minimize delivery time and costs based on collected traffic information, inventory information, and demand forecasts.

[1570] "Internet of Things technology" refers to technology that allows physical devices and sensors to exchange information over the Internet.

[1571] "Inventory level" refers to data that indicates the current amount of goods or materials stored in a warehouse or the like.

[1572] "Demand forecasting" is the process of predicting future demand based on past sales data and market trends.

[1573] A "delivery plan" is a plan that shows the specific schedule, routes, and resource allocation for product delivery.

[1574] "Environmental impact" refers to the impact that activities such as transportation and delivery have on the environment, particularly CO2 emissions and energy consumption.

[1575] "User's emotional state" refers to information that indicates the emotions and mental state that the user is currently feeling.

[1576] "Dynamic adjustment" refers to the flexible modification of plans and methods in response to changing situations and conditions in real time.

[1577] "User terminal" refers to a device through which a user receives information, such as a smartphone or tablet.

[1578] "Eco-friendly transportation" refers to the use of transportation methods that have a lower impact on the environment, such as electric vehicles and bicycles.

[1579] This invention is a system that dynamically adjusts delivery plans and proposes environmentally friendly transportation methods, primarily for food delivery services, taking into account the user's emotional state. Specifically, the system automatically generates optimal delivery routes based on real-time traffic information, inventory levels, and demand forecast data, and provides flexible delivery plans that reflect the user's emotional state.

[1580] 1. Data collection and real-time analysis

[1581] The server collects and analyzes data using the following means:

[1582] Real-time traffic information: Collected using the API of a traffic information service. For example, an API key from an external traffic information service (e.g., TomTom Traffic) is used to obtain current congestion and delay information.

[1583] Inventory Information: Using Internet of Things technology, real-time inventory data is collected from sensors in the warehouse. Specifically, IoT sensors are used to monitor the stock levels of each product and store them in a central database.

[1584] Demand forecast data: A generative AI model is used to generate a demand forecast model from past sales data and calculate new demand forecast data. For example, a demand forecasting algorithm using TensorFlow is used.

[1585] 2. Data analysis and optimization

[1586] The server analyzes the data and generates an optimal delivery plan using the following methods:

[1587] Traffic data analysis: Analyzes real-time traffic information and predicts congestion and travel times on major routes based on the acquired data.

[1588] Inventory Data Analysis: Analyze collected inventory data to identify where needed items are in stock.

[1589] Demand forecasting data analysis: Uses generative AI models to predict future demand and use the results to create optimal delivery plans.

[1590] 3. Optimal Route Generation and Evaluation

[1591] The server uses Dijkstra's algorithm and other optimization algorithms to calculate optimal delivery routes based on collected traffic data and demand forecast data. It also evaluates the fuel efficiency and CO2 emissions of the selected routes and proposes the transportation method with the least environmental impact.

[1592] 4. Recognizing and adjusting user emotions

[1593] The user's device (e.g., smartphone) recognizes the user's emotional state using the following means:

[1594] Emotional data collection: Analyze the user's emotional state in real time based on data such as voice, text, and facial expressions.

[1595] Emotional state determination: Based on the analysis results, the user's emotional state (e.g., stress, elation, indifference, etc.) is determined and sent to the server.

[1596] 5. Dynamic adjustment of delivery plans

[1597] The server dynamically adjusts its delivery plan and transportation suggestions based on the user's emotional state using the following means:

[1598] For users under stress, we prioritize quick and reliable delivery routes.

[1599] For eco-conscious users, we will focus on proposing transportation methods that minimize the environmental impact.

[1600] 6. User Notification and Action

[1601] The terminal will notify the user:

[1602] Optimal delivery planning: A detailed plan including specific delivery routes, departure times, estimated arrival times, and more.

[1603] Eco-friendly transport methods: Environmentally friendly options such as using electric vehicles and offering shared deliveries.

[1604] Adjustments based on user emotions: Delivery plans and suggestions are optimized to the user's emotional state.

[1605] As a specific example, if a user is judged to be "tired," they will be notified, "Please relax and wait, we will deliver the item as quickly as possible by car," and if a user requests an "eco-friendly delivery method," they will be notified, "We will deliver the item by electric motorcycle."

[1606] Example prompts to input to the generative AI model

[1607] "If the user is fatigued, provide them with the best delivery route and associated plan to respond quickly."

[1608] "For users who wish to use EcoMute, please provide a delivery method that minimizes the environmental impact."

[1609] As a result, the present invention realizes efficient, environmentally friendly, and detailed delivery management that takes into account the user's feelings.

[1610] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1611] Step 1:

[1612] The server collects real-time traffic information. Specifically, it uses the API of the traffic information service to obtain traffic data (e.g., congestion status and delay information). The input is real-time traffic data from the API, and the output is the congestion status and predicted travel time as an analysis result. Data processing involves analyzing the congestion level after collecting traffic information and calculating predicted travel times for each major route.

[1613] Step 2:

[1614] The server uses Internet of Things technology to monitor inventory levels in real time and collect data. Specifically, it obtains inventory data from IoT sensors in the warehouse and stores it in a central database. The input is inventory data from the sensors, and the output is real-time inventory levels. Data processing involves collecting data from the sensors to create and update the current inventory status of products.

[1615] Step 3:

[1616] The server uses a generative AI model to perform demand forecasting. The input is past sales data, and the output is future demand forecast data. Specifically, an AI model (e.g., TensorFlow) is used to analyze past sales data and generate a demand forecasting model. Data calculation involves training the model based on past sales trends and calculating a new demand forecast.

[1617] Step 4:

[1618] The server automatically generates optimal delivery routes based on collected traffic data and demand forecast data. The input is real-time traffic data and demand forecast data, and the output is the optimal delivery route proposal. Specifically, it uses Dijkstra's algorithm and other optimization algorithms to calculate the optimal route taking fuel efficiency and travel time into consideration. Data calculations combine the congestion status of each route with demand forecasts to generate effective routes.

[1619] Step 5:

[1620] The device recognizes the user's emotional state. Specifically, it collects data such as voice, text, and facial expressions, and analyzes the emotional state in real time based on this. The input is voice, text, and facial expression data from the device, and the output is the user's emotional state as an analysis result. Data processing involves analyzing the data using an emotion recognition engine (e.g., Affectiva) to determine the current emotional state.

[1621] Step 6:

[1622] The server dynamically adjusts the delivery plan based on the user's emotional state. The input is the user's emotional state data, and the output is an adjusted delivery plan according to the emotion. Specifically, the delivery route and transportation method are changed according to the user's emotional state. For example, a fast delivery route is proposed for a stressed user, and a route with a low environmental impact is proposed for an eco-conscious user. Data calculation involves analyzing the user's emotional data and dynamically updating the delivery plan based on that data.

[1623] Step 7:

[1624] The terminal notifies the user of the optimal delivery plan and eco-friendly transportation method. The input is the adjusted delivery plan, and the output is the notification to the user. Specifically, notifications are sent to smartphones, tablets, etc., providing the user with detailed delivery information (departure time, estimated arrival time, transportation method, etc.). In operation, the system improves user satisfaction by notifying the user of delivery information tailored to the user in real time.

[1625] 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.

[1626] 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.

[1627] 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 robot 414.

[1628] 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.

[1629] 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.

[1630] 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.

[1631] 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).

[1632] 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.

[1633] 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."

[1634] 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.

[1635] 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).

[1636] 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.

[1637] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1638] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1639] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1640] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1641] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1642] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1643] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1644] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1645] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1646] The following is further disclosed regarding the above embodiment.

[1647] (Claim 1)

[1648] Generative AI collects and analyzes real-time traffic information and calculates the optimal delivery route.

[1649] a means of monitoring inventory levels and collecting data in real time using Internet of Things technology;

[1650] A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data;

[1651] A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method.

[1652] means for notifying a user's terminal of the optimal delivery plan and the eco-friendly transportation method;

[1653] A system including:

[1654] (Claim 2)

[1655] 2. The system of claim 1, wherein the generative artificial intelligence generates a demand forecasting model using historical sales data.

[1656] (Claim 3)

[1657] 10. The system of claim 1, wherein the Internet of Things technology communicates with sensors in a warehouse to collect inventory data.

[1658] "Example 1"

[1659] (Claim 1)

[1660] Generative AI collects and analyzes real-time traffic information and calculates the optimal delivery route.

[1661] A means of monitoring inventory levels and collecting data in real time using sensor technology;

[1662] A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data;

[1663] A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method.

[1664] means for notifying a user's terminal of the optimal delivery plan and the eco-friendly transportation method;

[1665] A system including:

[1666] (Claim 2)

[1667] 2. The system of claim 1, wherein the generative artificial intelligence generates a demand forecasting model using historical sales data.

[1668] (Claim 3)

[1669] 10. The system of claim 1, wherein the sensor technology communicates with sensors in a warehouse to collect inventory data.

[1670] "Application Example 1"

[1671] (Claim 1)

[1672] Generative AI collects and analyzes real-time traffic information and calculates the optimal delivery route.

[1673] a means of monitoring inventory levels and collecting data in real time using Internet of Things technology;

[1674] A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data;

[1675] A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method.

[1676] means for notifying the user's information terminal of the optimum delivery plan and eco-friendly transportation method;

[1677] A means of obtaining real-time traffic data using the API of a traffic information service;

[1678] A means of collecting and monitoring inventory information through an IoT platform in the warehouse,

[1679] a means for analyzing future demand using a demand forecasting model;

[1680] A means for generating an optimal delivery route based on Dijkstra's algorithm;

[1681] A system including:

[1682] (Claim 2)

[1683] The system of claim 1, wherein the generative artificial intelligence generates a demand forecasting model using past sales data and suggests eco-friendly transportation methods.

[1684] (Claim 3)

[1685] 10. The system of claim 1, wherein the Internet of Things technology communicates with sensors in the warehouse to collect and monitor inventory data.

[1686] "Example 2: Combining Emotion Engines"

[1687] (Claim 1)

[1688] Generative AI collects and analyzes real-time traffic information and calculates the optimal delivery route.

[1689] a means of monitoring inventory levels and collecting data in real time using Internet of Things technology;

[1690] A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data;

[1691] A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method.

[1692] means for analyzing a user's emotional state using position recognition technology and adjusting a delivery plan based on the emotional state;

[1693] means for notifying a user's terminal of the optimal delivery plan and the eco-friendly transportation method;

[1694] A system including:

[1695] (Claim 2)

[1696] 2. The system of claim 1, wherein the generative artificial intelligence generates a demand forecasting model using historical sales data.

[1697] (Claim 3)

[1698] 10. The system of claim 1, wherein the Internet of Things technology communicates with sensors in a warehouse to collect inventory data.

[1699] "Application example 2 when combining emotion engines"

[1700] (Claim 1)

[1701] Generative AI collects and analyzes real-time traffic information and calculates the optimal delivery route.

[1702] a means of monitoring inventory levels and collecting data in real time using Internet of Things technology;

[1703] A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data;

[1704] A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method.

[1705] means for recognizing a user's emotional state and dynamically adjusting a delivery plan or method based on the emotional state;

[1706] means for notifying a user's terminal of the optimal delivery plan and the eco-friendly transportation method;

[1707] A system including:

[1708] (Claim 2)

[1709] 2. The system of claim 1, wherein the generative artificial intelligence generates a demand forecasting model using historical sales data.

[1710] (Claim 3)

[1711] 10. The system of claim 1, wherein the Internet of Things technology communicates with sensors in a warehouse to collect inventory data. [Explanation of symbols]

[1712] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. Generative AI collects and analyzes real-time traffic information and calculates optimal delivery routes. a means of monitoring inventory levels and collecting data in real time using Internet of Things technology; A means for the artificial intelligence to predict demand and automatically generate optimal delivery plans based on the predicted data; A generative AI system evaluates the environmental impact of each delivery route and proposes the most environmentally friendly transportation method. means for notifying a user's terminal of the optimal delivery plan and the eco-friendly transportation method; A system including:

2. The system of claim 1 , wherein the generative artificial intelligence generates a demand forecasting model using historical sales data.

3. The system of claim 1 , wherein the Internet of Things technology communicates with sensors in a warehouse to collect inventory data.

Images