System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting traffic information; means for collecting weather data; means for obtaining business hours of a delivery destination; means for collecting cost and environmental impact data of a transportation means; means for selecting an optimal delivery route and transportation means based on the collected data; means for notifying the selected delivery route and transportation means; and means for monitoring and dynamically re-optimizing the data in real time.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, delivery delays and reduced efficiency are frequent due to factors such as traffic congestion, bad weather, and changes in business hours at delivery destinations. Furthermore, when selecting transportation methods, it is difficult to consider costs and environmental impacts, resulting in inefficient operations. Furthermore, logistics networks change dynamically due to fluctuations in market demand and various events, making fixed routes and methods insufficient. The present invention aims to solve these problems and provide a system that dynamically optimizes logistics networks in real time. [Means for solving the problem]

[0005] The present invention includes a means for collecting traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact data. It also includes a means for selecting the optimal delivery route and transportation method based on the collected data. It also includes a means for notifying the user of the selected delivery route and transportation method, and a means for monitoring the data in real time and dynamically re-optimizing it. Specifically, it uses an external database or API to collect traffic information and weather data, analyzes the data using a machine learning model, and calculates the optimal route and transportation method. This makes it possible to always execute optimal delivery plans based on the latest information.

[0006] "Traffic information" refers to information about road traffic, such as road congestion, traffic accidents, and construction information.

[0007] "Weather data" refers to meteorological data such as the current weather in a certain area, the probability of precipitation, wind speed, and temperature.

[0008] "Business hours of delivery destination" is information indicating the business hours during which the delivery destination of the product can accept delivery.

[0009] "Cost of transportation means" is information on the costs incurred when using a specific transportation means.

[0010] "Environmental impact data" is data that indicates the environmental impact, such as carbon dioxide emissions, that occurs when a particular mode of transportation is used.

[0011] "Means of collection" refers to the mechanism for obtaining the necessary data using external databases and APIs.

[0012] "Means to select" is a process for determining the optimal delivery route and means of transportation based on collected data.

[0013] The "notification means" is a mechanism for informing users of information about optimized delivery routes and transportation methods.

[0014] "Means for monitoring and dynamic re-optimization" refers to a mechanism for monitoring data in real time and recalculating optimal delivery routes and transportation methods in response to fluctuations. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. The operation of the system will be explained below based on a specific example embodiment.

[0037] Data collection

[0038] server

[0039] 1. Collection of traffic information

[0040] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[0041] 2. Weather data collection

[0042] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[0043] 3. Obtaining delivery address business hours

[0044] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0045] 4. Collecting transportation cost and environmental impact data

[0046] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[0047] Data analysis and optimal route selection

[0048] server

[0049] 1. Data Preprocessing

[0050] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0051] 2. Input to the AI ​​model

[0052] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[0053] 3. Extracting optimization results

[0054] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as the optimization results.

[0055] User notification and execution management

[0056] server

[0057] 1. Generate a notification

[0058] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[0059] Terminal

[0060] 1. Receiving notifications

[0061] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[0062] User

[0063] 1. Check the notification content

[0064] The delivery manager (user) checks the notification from the server and approves the proposed optimized route and transportation means.

[0065] Real-time monitoring and dynamic re-optimization

[0066] server

[0067] 1. Real-time data monitoring

[0068] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0069] 2. Dynamic Reoptimization

[0070] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[0071] Terminal

[0072] 1. Reminder

[0073] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[0074] User

[0075] 1. Reconfirmation and adjustment of instructions

[0076] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[0077] In this way, each component of this system, including the server, terminals, and users, works together to create an optimal logistics network based on the latest information, which can effectively resolve issues facing the entire logistics industry, such as reducing delivery delays, improving cost efficiency, and being environmentally conscious.

[0078] The processing flow will be explained below.

[0079] Step 1: Collect data

[0080] server

[0081] The server uses the Google Maps API to collect current traffic conditions and forecasts for major roads.

[0082] The server uses the Weather API to obtain current weather information and forecasts along the delivery route.

[0083] The server obtains business hours information for each delivery destination from the delivery destination database.

[0084] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and rail companies.

[0085] Step 2: Data Preprocessing

[0086] server

[0087] The server formats the collected data and prepares it in a format that can be input into the AI ​​model.

[0088] Specifically, it normalizes data, fills in missing values, and converts data types as necessary.

[0089] Step 3: Input to the AI ​​model

[0090] server

[0091] The server inputs the preprocessed data into a machine learning model and performs analysis.

[0092] Calculate optimal routes and modes of transport, taking into account traffic, weather, opening hours, transport costs and environmental impacts.

[0093] Step 4: Extracting optimization results

[0094] server

[0095] The optimal route and transportation method are extracted from the output of the AI ​​model.

[0096] This provides a detailed dispatch plan for optimization.

[0097] Step 5: Generate notifications

[0098] server

[0099] The server generates a message to notify the user based on the optimization result.

[0100] Specifically, it creates detailed information including the best route, transportation method, and estimated delivery time.

[0101] Step 6: Receive notifications

[0102] Terminal

[0103] The user device (smartphone or PC) receives the notification sent from the server and displays it on the screen.

[0104] Allow delivery managers to check notifications in real time.

[0105] Step 7: Review and approve the notification

[0106] User

[0107] The delivery manager reviews the notification displayed on the terminal and approves the optimized route and transportation proposal.

[0108] Tweak your delivery plan if necessary.

[0109] Step 8: Instructions for the carrier

[0110] User

[0111] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation information.

[0112] Specifically, instructions are sent to the supplier via the delivery management system.

[0113] Step 9: Monitor real-time data

[0114] server

[0115] The server continues to monitor traffic and weather data in real time while the delivery is in progress.

[0116] The database is updated as new information becomes available.

[0117] Step 10: Dynamic Reoptimization

[0118] server

[0119] The server then uses the AI ​​model again based on real-time data to dynamically perform optimization.

[0120] Depending on the situation, new optimal routes and means of transportation are recalculated.

[0121] Step 11: Snooze

[0122] server

[0123] If necessary, the new optimization results are notified to the user terminal.

[0124] Provides optimization information that responds to real-time fluctuations.

[0125] Step 12: Review and adjust instructions

[0126] User

[0127] The user checks the re-notification and issues new instructions to the delivery company if necessary.

[0128] The logistics company will then continue delivery using the proposed new route.

[0129] In this way, the server, terminals, and users work together to maintain an optimal logistics network based on the latest information, which reduces delivery delays, cuts costs, and is environmentally friendly.

[0130] Example 1

[0131] 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."

[0132] In current logistics networks, it is difficult to select the optimal delivery route and transportation method in real time, taking into account traffic information, weather data, delivery destination business hours, and the cost and environmental impact of transportation methods. Furthermore, collected data is not pre-processed sufficiently, and there is no mechanism for dynamic re-optimization when conditions change. This results in increased risks of delivery delays, increased costs, and negative environmental impacts, hindering efficient logistics.

[0133] 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.

[0134] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, and a means for acquiring business hours of delivery destinations. It also includes a means for collecting data on the cost and environmental impact of transportation means, a means for preprocessing the collected data, a means for selecting an optimal delivery route and transportation means using a machine learning model, a means for notifying the selected delivery route and transportation means, and a means for monitoring the data in real time and dynamically re-optimizing the data. This enables comprehensive analysis of various data and the provision of an optimal logistics network based on the latest information.

[0135] "Traffic information" refers to general information relating to vehicle traffic, such as road congestion, accident information, and construction information.

[0136] "Weather data" refers to general information about the weather, such as the weather in a particular area, temperature, probability of precipitation, wind speed, etc.

[0137] "Delivery destination business hours" refers to general information about the dates and times when each delivery destination can receive packages.

[0138] "Transportation costs" are the economic costs incurred to transport a load over a specific distance or weight.

[0139] "Environmental impact data" is information about the adverse environmental impacts, such as carbon dioxide emissions, caused by a particular mode of transportation.

[0140] "Preprocessing" is the process of formatting collected data, filling in missing values, and normalizing it to make it suitable for analysis or model input.

[0141] A "machine learning model" is an algorithm or computational method that learns patterns and knowledge through data analysis and makes predictions and classifications based on new data.

[0142] "Optimal delivery route and transportation mode selection" is the process of determining the most efficient and cost-effective delivery route and transportation mode by taking into account various data.

[0143] "Notifying" refers to the act of communicating the determined information or results to the user.

[0144] "Real-time monitoring" means continuously obtaining the latest data at the current time and immediately grasping changes in the situation.

[0145] "Dynamic re-optimization" is the process of recalculating and, if necessary, changing the optimal route or mode of transportation based on new information that becomes available in real time.

[0146] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time.

[0147] Data collection

[0148] server

[0149] The server utilizes several external APIs and databases to collect the following data:

[0150] 1. Collection of traffic information

[0151] The server uses the API of a traffic information service (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads, such as road congestion levels, accident information, and construction information.

[0152] 2. Weather data collection

[0153] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route, including local weather, temperature, chance of precipitation, wind speed, etc.

[0154] 3. Obtaining delivery address business hours

[0155] The server queries the database of delivery destinations to obtain the acceptable opening hours for each delivery destination, e.g., opening and closing times for stores.

[0156] 4. Collecting transportation cost and environmental impact data

[0157] The server collects cost and CO2 emissions data for each mode of transport from the APIs or internal databases of truck rental and rail companies, including the cost of delivering a certain distance and the carbon footprint of that mode of transport.

[0158] Data preprocessing and input to AI models

[0159] server

[0160] The collected data is first preprocessed. The server formats the data, imputes missing values, and normalizes it to prepare it in a format suitable for machine learning models. The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow) to calculate the optimal delivery route and transportation method. For example, it suggests routes that avoid traffic jams or safe routes in bad weather.

[0161] Notification of optimization results and execution management

[0162] server

[0163] Once the optimization results are obtained, the server generates a message to notify the user based on the results, including details such as the optimal route, transportation method, and estimated delivery time.

[0164] Terminal

[0165] The delivery manager's terminal receives the notification sent from the server and displays this information to the user in real time through the notification system.

[0166] User

[0167] The delivery manager checks the notification from the server and approves the proposed optimal route and transportation means, thereby carrying out the delivery work.

[0168] Real-time monitoring and dynamic re-optimization

[0169] server

[0170] While the delivery is in progress, the server continues to monitor traffic and weather data in real time. When new traffic congestion information or weather changes are collected, the server restarts the AI ​​model and re-optimizes it. The server then notifies the user again based on the new optimization results, promptly informing them of any necessary changes.

[0171] Terminal

[0172] The terminal receives new notifications and displays the necessary information to the user in real time.

[0173] User

[0174] The user confirms the re-notification and issues new instructions to the logistics company, who then carries out delivery using the proposed new route.

[0175] Specific examples

[0176] As a specific example, the following case can be mentioned.

[0177] Example: Optimizing delivery routes from Tokyo to Osaka. Collect data using a traffic information API, weather API, delivery destination business hours database, and truck rental API, and use a machine learning model to calculate the optimal route taking traffic congestion and weather into account.

[0178] Example prompt for a generative AI model:

[0179] "Calculate the optimal delivery route from Tokyo to Osaka. Recommend the best route and transportation method, taking into account traffic information, weather data, destination opening hours, truck rental costs and environmental impact."

[0180] In this way, the system of the present invention integrates and analyzes various types of data, and by always providing an optimal logistics network based on the latest information, it is possible to reduce delivery delays, improve cost efficiency, and be environmentally friendly.

[0181] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0182] Step 1: Collect data

[0183] server

[0184] The server uses multiple external APIs and databases to gather traffic information, weather data, delivery location opening hours, transportation costs, and environmental impact data. Specifically, it sends a "GET" request to retrieve the following data:

[0185] Input: A request containing an API key and query parameters

[0186] Output: Traffic information, weather data, business hours data, and transportation data in JSON format

[0187] Examples:

[0188] Traffic information: congestion, accident information, construction information

[0189] Weather data: weather, temperature, chance of precipitation, wind speed

[0190] Business hours: Opening and closing times for each delivery location

[0191] Cost and environmental impact data: shipping costs, CO2 emissions

[0192] Step 2: Data Preprocessing

[0193] server

[0194] The collected data is preprocessed and formatted so that it can be fed into a machine learning model. Specifically, missing values ​​are imputed and the data is normalized.

[0195] Input: JSON formatted collected data

[0196] Output: Preprocessed dataset

[0197] Examples:

[0198] Missing Value Imputation: Impute missing weather data with the mean value

[0199] Data normalization: Scaling numerical data such as traffic information or temperature to a range of 0 to 1

[0200] Step 3: Input to the AI ​​model

[0201] server

[0202] The preprocessed data is fed into a machine learning model to calculate the optimal delivery route and transportation method. A TensorFlow model is used.

[0203] Input: Preprocessed dataset

[0204] Output: Prediction results of the AI ​​model

[0205] Examples:

[0206] Suggesting routes to avoid traffic jams

[0207] Choosing a safe route in bad weather

[0208] Step 4: Extracting optimization results

[0209] server

[0210] The optimal route and mode of transport is extracted from the output of the AI ​​model and the results are shaped.

[0211] Input: AI model prediction results

[0212] Output: Optimal route and transportation details

[0213] Examples:

[0214] Optimal Route: Recommended route from origin to destination

[0215] Transportation: Preferred transportation method (truck or rail)

[0216] Step 5: Generate notifications

[0217] server

[0218] Based on the optimization results, a message is generated to notify the user.

[0219] Input: Best route and transportation details

[0220] Output: Information message

[0221] Examples:

[0222] Message content: Delivery schedule, route details, transportation method, estimated delivery time

[0223] Step 6: Receive and view notifications

[0224] Terminal

[0225] The delivery manager's terminal receives the notification sent from the server and displays it on the screen.

[0226] Input: Notification message sent by the server

[0227] Output: Notification displayed on the screen

[0228] Examples:

[0229] Use smartphone and PC notification systems to notify users in real time

[0230] Step 7: Review and approve the notification

[0231] User

[0232] The delivery manager checks the notification sent from the server and approves the proposed optimal route and transportation means.

[0233] Input: Notification message displayed on the screen

[0234] Output: Approval or correction instructions

[0235] Examples:

[0236] After checking on your smartphone or PC, press the approval button

[0237] Step 8: Monitor real-time data

[0238] server

[0239] Even while the delivery is in progress, traffic and weather data is monitored in real time to collect the latest information.

[0240] Input: Real-time data from API

[0241] Output: Updated traffic and weather data

[0242] Examples:

[0243] Timely acquisition of new traffic congestion information and weather change data

[0244] Step 9: Dynamic Reoptimization

[0245] server

[0246] The AI ​​model is reactivated based on real-time data and re-optimized according to changes in the situation.

[0247] Input: Updated traffic and weather data

[0248] Output: New optimal route and transportation details

[0249] Examples:

[0250] Proposing the best alternative route in the event of a sudden accident

[0251] Step 10: Generate and send a snooze notification

[0252] server

[0253] Based on the results of the re-optimization, a notification message is generated and sent to the user again.

[0254] Input: New best route and transportation details

[0255] Output: New notification message

[0256] Examples:

[0257] Clearly state the changes and notify users again

[0258] Step 11: Receive and view snooze notifications

[0259] Terminal

[0260] The delivery manager's terminal receives the new notification message and displays it on the screen.

[0261] Input: New notification message sent by the server

[0262] Output: The new notification displayed on the screen.

[0263] Examples:

[0264] Use smartphone or PC notification systems to notify users again in real time

[0265] Step 12: Review and adjust instructions

[0266] User

[0267] The delivery manager will review the new notification and issue new instructions to the logistics company if necessary.

[0268] Input: New notification displayed on screen

[0269] Output: Sending new instructions

[0270] Examples:

[0271] Instructing logistics companies to continue deliveries using new recommended routes

[0272] These steps ensure that the system always provides the most optimal logistics network based on up-to-date information, reducing delivery delays, improving cost efficiency, and being environmentally friendly.

[0273] (Application example 1)

[0274] 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."

[0275] In today's world, where efficiency and sustainability are required for logistics, it is necessary to select the optimal delivery route taking into account traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact. However, existing systems are unable to support dynamic optimization in real time, making it difficult to respond quickly to sudden traffic congestion or weather changes. In addition, there is a lack of concrete improvement measures to achieve efficient delivery at logistics centers.

[0276] 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.

[0277] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for calculating a delivery route in conjunction with the collected data and displaying the optimization result through an application installed on the transport robot. This makes it possible to select an optimal delivery route and transportation means in real time at a logistics center, thereby achieving efficient and sustainable delivery.

[0278] "Traffic information" refers to data related to traffic, such as road congestion, accidents, and construction work.

[0279] "Weather data" refers to various information related to weather, such as weather, temperature, precipitation, and wind speed.

[0280] "Business hours of delivery destination" refers to the opening and closing hours of the facility or store to which the logistics center delivers.

[0281] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[0282] "Environmental impact data" refers to data on the impact that a means of transportation has on the environment, specifically data on CO2 emissions, etc.

[0283] The "optimal delivery route" is the most efficient and economical delivery route calculated based on multiple conditions.

[0284] "Transportation" means the means (e.g., truck, rail, etc.) used to transport goods from a distribution center to a delivery destination.

[0285] A "notification" is a means by which a system communicates information to a user.

[0286] "Real-time data monitoring" means that the system continuously monitors data according to the current situation.

[0287] "Dynamic reoptimization" refers to the process by which the AI ​​model recalculates new optimal delivery routes and modes of transportation whenever conditions change.

[0288] An "application" is software designed to perform a specific task.

[0289] A "transport robot" is an automated mechanical device used in logistics centers to transport and organize cargo.

[0290] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system is realized through the cooperation of a server, terminals, and users.

[0291] Data collection

[0292] server:

[0293] 1. Traffic information collection:

[0294] The server uses external APIs to obtain traffic conditions and forecasts for major roads, specifically road congestion, accident information, and construction information.

[0295] 2. Weather data collection:

[0296] The server uses a weather information API to obtain weather information and forecasts for the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each region.

[0297] 3. Get delivery location business hours:

[0298] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0299] 4. Collecting transportation cost and environmental impact data:

[0300] The server collects data on the cost and CO2 emissions of each transportation mode from the APIs or internal databases of truck rental companies and rail companies.

[0301] Data analysis and optimal route selection

[0302] server:

[0303] 1. Data Preprocessing:

[0304] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0305] 2. Input to the AI ​​model:

[0306] The server uses machine learning models (such as TensorFlow) to calculate optimal delivery routes and transportation methods based on the preprocessed data, for example, proposing routes to avoid traffic jams or safe routes in bad weather.

[0307] 3. Extracting optimization results:

[0308] The server extracts the optimal route and transportation method from the output of the AI ​​model.

[0309] User notification and execution management

[0310] server:

[0311] 1. Generate notification:

[0312] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[0313] Device:

[0314] 1. Receiving notifications:

[0315] The delivery manager's device receives the notification sent from the server and displays it on the screen. For example, a notification system on a smartphone or PC can be used to notify the user in real time.

[0316] User:

[0317] 1. Check the notification:

[0318] The delivery manager checks the notification from the server and approves the proposal for the optimized route and transportation means.

[0319] Real-time monitoring and dynamic re-optimization

[0320] server:

[0321] 1. Real-time data monitoring:

[0322] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0323] 2. Dynamic reoptimization:

[0324] The server then reactivates the AI ​​model based on real-time data and dynamically recalculates the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, the server immediately suggests an optimal alternative route.

[0325] Device:

[0326] 1. Reminder:

[0327] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[0328] User:

[0329] 1. Review and adjust instructions:

[0330] The user checks the re-notification and issues new instructions to the distributor if new instructions are required.

[0331] In this way, optimization results can be displayed through an application installed on the delivery robots within the logistics center, enabling efficient delivery management in real time.

[0332] Specific processing examples

[0333] Road congestion and accident information obtained from the traffic information API is input into the AI ​​model to calculate the optimal route from the logistics center to a specific store.

[0334] In the event of a sudden change in weather or a new traffic accident, the information is reloaded in real time, and the AI ​​model is recalculated to present a new route.

[0335] Example prompt for a generative AI model:

[0336] "Can you calculate the optimal route from the logistics center to each delivery destination based on traffic, weather, and business information? Specifically, please suggest routes that avoid traffic jams and are safe in bad weather."

[0337] This will enable a significant improvement in delivery efficiency at logistics centers.

[0338] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0339] Step 1:

[0340] The server collects traffic information. Specifically, it uses an external API to obtain current and forecast traffic conditions for major roads. In this case, it sends an API request and receives data such as road congestion, accident information, and construction information. The input is the response data from the API, and the output is structured traffic information data.

[0341] Step 2:

[0342] The server collects weather data. It uses a weather information API to obtain weather information and forecasts for the delivery route. For example, it obtains data such as the weather, temperature, precipitation probability, and wind speed for each region via an API request and processes that information. The input is the response data from the API, and the output is structured weather information data.

[0343] Step 3:

[0344] The server retrieves the business hours of delivery destinations. It sends a query to the delivery destination database to retrieve the acceptable business hours for each delivery destination. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information from the database. The input is the response data from the database, and the output is structured business hours data.

[0345] Step 4:

[0346] The server collects data on the cost and environmental impact of transportation modes. It collects data such as the cost and CO2 emissions of each transportation mode from the APIs of truck rental companies and railway companies, or from an internal database. The input is the response data from the API or database, and the output is structured cost and environmental impact data.

[0347] Step 5:

[0348] The server preprocesses the collected data. Specifically, it normalizes the data, fills in missing values, and formats it so that it can be input into an AI model. The input is various collected data, and the output is a compiled dataset.

[0349] Step 6:

[0350] The server uses an AI model based on the preprocessed data to calculate the optimal delivery route and transportation method. Using machine learning libraries such as TensorFlow, the server inputs data into the model to make predictions. The input is the preprocessed dataset, and the output is a proposal for an optimized delivery route and transportation method.

[0351] Step 7:

[0352] The server generates a message to notify the user based on the optimization results. Specifically, it creates detailed information including the optimal route, transportation method, and expected delivery time, and prepares it to be sent to the user's device. The input is the output data of the AI ​​model, and the output is the notification message.

[0353] Step 8:

[0354] The device receives notifications sent from the server and displays them on the screen. For example, it notifies the user in real time using the notification system of a smartphone or PC. The input is the notification message from the server, and the output is the notification displayed on the device.

[0355] Step 9:

[0356] The user checks the notification from the server and approves the proposed optimized route and transportation means. The input is the notification content displayed on the terminal, and the output is the user's approval action.

[0357] Step 10:

[0358] The server monitors traffic and weather data in real time while the delivery is in progress. New traffic congestion information and weather change data are collected as they arrive and updated within the system. The input is real-time data, and the output is updated status data.

[0359] Step 11:

[0360] The server then runs the AI ​​model again based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, it will immediately suggest an optimal alternative route. The input is updated real-time data, and the output is the recalculated optimal route.

[0361] Step 12:

[0362] The server re-notifies the user terminal of the new optimization results and promptly notifies them of any necessary changes. The input is the recalculated optimal route, and the output is the re-notification message.

[0363] Step 13:

[0364] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The input is the re-notification message and the output is the user's new instructions.

[0365] Through the above steps, efficient and sustainable delivery management can be achieved using applications installed on delivery robots within logistics centers.

[0366] 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.

[0367] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, delivery destination business hours, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on those emotions. The operation of this system will be explained below based on a specific example of the system.

[0368] Data collection

[0369] server

[0370] 1. Collection of traffic information

[0371] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[0372] 2. Weather data collection

[0373] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[0374] 3. Obtaining delivery address business hours

[0375] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0376] 4. Collecting transportation cost and environmental impact data

[0377] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[0378] Data analysis and optimal route selection

[0379] server

[0380] 1. Data Preprocessing

[0381] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0382] 2. Input to the AI ​​model

[0383] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[0384] 3. Extracting optimization results

[0385] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as optimization results.

[0386] User emotion recognition and response

[0387] server

[0388] 1. Emotional Engine Activation

[0389] The emotion engine installed on the server collects emotion data through user voice input and facial recognition. For example, a user sets up a scene where facial recognition is performed using a smartphone camera.

[0390] Terminal

[0391] 1. Emotion analysis via voice input or facial recognition

[0392] The user device uses voice input and a camera to analyze the user's emotions in real time, for example, detecting when the user expresses dissatisfaction with a delivery delay.

[0393] server

[0394] 1. Emotional Data Analysis

[0395] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, for example, re-proposing a different delivery route if the user expresses dissatisfaction.

[0396] User notification and execution management

[0397] server

[0398] 1. Generate a notification

[0399] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[0400] Terminal

[0401] 1. Receiving notifications

[0402] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[0403] User

[0404] 1. Check the notification content

[0405] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[0406] Real-time monitoring and dynamic re-optimization

[0407] server

[0408] 1. Real-time data monitoring

[0409] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0410] 2. Dynamic Reoptimization

[0411] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[0412] Terminal

[0413] 1. Reminder

[0414] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[0415] User

[0416] 1. Reconfirmation and adjustment of instructions

[0417] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[0418] In this way, the server, terminals, users, and emotion engine work together to create a logistics network that is always the most efficient and satisfies users, thereby reducing delivery delays, cutting costs, being environmentally friendly, and improving customer satisfaction.

[0419] The processing flow will be explained below.

[0420] Step 1: Collect data

[0421] server

[0422] The server uses the Google Maps API to collect current and forecast traffic conditions on major roads, specifically traffic flow, congestion information, and accident information.

[0423] The server uses the Weather API to collect current weather information along the delivery route, specifically the weather, temperature, precipitation probability, wind speed, etc. for each area.

[0424] The server retrieves the acceptable business hours of each delivery destination from the delivery destination database, for example, the business hours and holiday information of each store.

[0425] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and railroad companies, specifically, the costs and environmental impact data of each transportation method.

[0426] Step 2: Data Preprocessing

[0427] server

[0428] The server prepares the collected data in a format suitable for analysis, for example by filling in missing data and standardizing the data format.

[0429] Normalize and scale the data to prepare it for input into the AI ​​model.

[0430] Step 3: Input to the AI ​​model

[0431] server

[0432] The server inputs the pre-processed data into an AI model for real-time analysis, using machine learning algorithms to calculate the optimal delivery route and transportation method.

[0433] Step 4: Extracting optimization results

[0434] server

[0435] The server extracts the optimization results obtained from the AI ​​model, such as the optimal route and means of transportation.

[0436] The optimization results are compiled as a delivery plan.

[0437] Step 5: Collecting emotion data

[0438] Terminal

[0439] The user device collects the user's emotions using voice input or a camera, for example, by the user speaking into a smartphone or pointing their face at the device's camera.

[0440] Step 6: Analyze the sentiment data

[0441] server

[0442] The emotion engine installed on the server analyzes the collected emotion data, for example, analyzing voice data to determine whether the user is angry or happy.

[0443] Step 7: Emotional Adjustment

[0444] server

[0445] The server adjusts the optimization results based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will re-propose a different delivery route.

[0446] Step 8: Generate notifications

[0447] server

[0448] The server generates a message based on the optimization and sentiment analysis results, creating a notification that includes detailed information such as the delivery route, transportation method, and estimated delivery time.

[0449] Step 9: Receive notifications

[0450] Terminal

[0451] The user device receives the notification sent from the server and displays it on the screen. For example, the notification system of a smartphone or PC is used to notify the user in real time.

[0452] Step 10: Review and approve the notification

[0453] User

[0454] The delivery manager (user) checks the notification displayed on the terminal, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[0455] Step 11: Instructions for the carrier

[0456] User

[0457] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation method information. Specifically, the instructions are notified to the company through the delivery management system.

[0458] Step 12: Monitor real-time data

[0459] server

[0460] The server monitors traffic and weather information in real time while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0461] Step 13: Dynamic Reoptimization

[0462] server

[0463] The server then uses the AI ​​model to dynamically optimize the route and transportation method based on real-time data, and if conditions change, it recalculates the optimal route and transportation method.

[0464] Step 14: Snooze

[0465] server

[0466] The server notifies the user terminal of the new optimization results, providing a new delivery plan that responds to real-time fluctuations.

[0467] Step 15: Review and adjust instructions

[0468] User

[0469] The user can then review the re-notification and issue new instructions to the delivery company if necessary, and the delivery company will then continue delivery using the proposed new route.

[0470] In this way, the server, terminals, users, and emotion engine work together to create the most efficient logistics network possible, which always provides the highest level of user satisfaction. This reduces delivery delays, cuts costs, contributes to environmental friendliness, and improves customer satisfaction.

[0471] Example 2

[0472] 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."

[0473] Conventional logistics network systems face the problem of difficult integrated control of multiple data sources, as they individually manage and analyze traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact data. Dynamic real-time re-optimization and adjustment of optimization content based on user emotion recognition are also difficult, resulting in reduced customer satisfaction and efficiency. Furthermore, data preprocessing and the use of machine learning models are difficult to implement, increasing the system's complexity and making implementation difficult.

[0474] 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.

[0475] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, a means for acquiring business hours of delivery destinations, and a means for collecting data on transportation costs and environmental impacts. This allows for a means for selecting an optimal delivery route and transportation means based on the collected data, which in turn includes a means for analyzing data using a machine learning model, a means for notifying the user of the selected delivery route and transportation means, a means for monitoring the data in real time and dynamically re-optimizing the data, and a means for collecting and analyzing user emotion data and adjusting the optimization content based on the data. This allows for integrated control of various data sources, dynamic optimization in real time, and flexible optimization based on user emotion, thereby improving the efficiency of the logistics network and customer satisfaction.

[0476] "Traffic information" refers to data on the current state and forecast of road traffic, such as road congestion, accident information, and construction information.

[0477] "Weather data" refers to data relating to weather conditions, such as the weather, temperature, probability of precipitation, and wind speed, for a particular area.

[0478] "Delivery destination business hours" is information about the hours during which a specific delivery destination can accept packages.

[0479] "Cost of transportation" refers to data on the fees and expenses incurred when using a particular transportation method.

[0480] "Environmental impact data" refers to data on the environmental impact, such as CO2 emissions, that occurs when a particular means of transportation is used.

[0481] A "machine learning model" is an algorithm or framework for analyzing data and making predictions or classifications based on that data.

[0482] "Preprocessing means" refers to the process of standardizing and normalizing collected data, filling in missing values, and otherwise preparing the data in an analyzable format.

[0483] "Dynamic reoptimization" is the process of recalculating and updating optimal delivery routes and modes of transportation in response to changes in data monitored in real time.

[0484] "User emotion data" refers to data relating to the user's psychological state and emotions collected through voice input and facial recognition.

[0485] "Adjusting optimization content based on emotional data" is the process of analyzing collected user emotional data and changing the optimization content of delivery routes and transportation methods based on the results.

[0486] The logistics network optimization system according to the present invention selects and dynamically reoptimizes optimal delivery routes and transportation means by implementing the following multiple processes.

[0487] Data collection and analysis

[0488] Collection of traffic information

[0489] The server uses an external API (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads. The server calls the API every five minutes to collect new data such as road congestion, accident information, and construction information, and stores it in the database.

[0490] Weather data collection

[0491] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route. The server obtains weather information every hour and collects and stores data such as the weather, temperature, precipitation probability, and wind speed for each area.

[0492] Get delivery address business hours

[0493] The server references a database of destinations to obtain the acceptable business hours for each destination. The server queries the database once a day at night to update the business hours for each destination.

[0494] Collecting transportation cost and environmental impact data

[0495] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railway companies, or from an internal database. Once a month, the server calls the APIs of each service provider to obtain the latest pricing and environmental impact data.

[0496] Data preprocessing and using machine learning models

[0497] Data Preprocessing

[0498] The server runs the process of standardizing and normalizing the collected data and imputing missing values ​​using SQL scripts and ETL (Extract, Transform, Load) processes written in Python, for example, using the mean or median to impute missing values.

[0499] Input to the machine learning model

[0500] The server uses the preprocessed data to input into a machine learning model (for example, a TensorFlow or PyTorch model). The formatted data is passed to the AI ​​model in batches for inference. The machine learning model calculates the optimal delivery route and transportation method based on the given data.

[0501] User emotion recognition and analysis

[0502] Emotional Engine Activation

[0503] The server uses an emotion engine to collect emotion data through user voice input and facial recognition, and schedules a task to analyze the user's input data at regular intervals.

[0504] Sentiment analysis via voice input or facial recognition

[0505] The device uses a microphone and camera to analyze the user's emotions in real time. This includes analyzing the user's facial expressions and tone of voice using deep learning techniques. For example, if the user expresses dissatisfaction, emotional data will be collected.

[0506] Emotional Data Analysis

[0507] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, enabling flexible optimization that takes user emotions into account.

[0508] User notification and execution management

[0509] Generating and Receiving Notifications

[0510] The server generates messages to notify users based on the optimization results and the emotion engine's analysis results. Specifically, it generates and executes HTML emails and push notifications. The distribution manager's device receives the notifications sent from the server and displays them on the screen. Information is conveyed to users in real time using the smartphone's notification system or PC's desktop notification function.

[0511] Checking notification content

[0512] The user can then review the notification from the server and approve the optimized route and transportation suggestions. Specifically, the user can review the notification in depth and make fine adjustments as needed, for example, based on new requirements or conditions.

[0513] Real-time monitoring and dynamic re-optimization

[0514] Real-time data monitoring

[0515] The server continues to monitor real-time traffic and weather data during delivery, retrieving new data from the API every 10 minutes and updating the situation.

[0516] Performing dynamic reoptimization

[0517] The server then re-executes the AI ​​model based on real-time data and recalculates the optimization results according to changes in the situation. For example, if information about a sudden accident is received, a new route will be calculated immediately and the user will be notified of the new optimization results.

[0518] Re-notification and instruction adjustment

[0519] The server notifies the user terminal of the new optimization results and promptly notifies the user of the changes. The user can then check the re-notification and, if necessary, issue new instructions to the logistics company.

[0520] Prompt Sentence Examples

[0521] Traffic: "There's been an accident on a major road, causing congestion. It's also raining along my route. My delivery destination is open from 9 AM to 6 PM. Please suggest the most cost-effective route and transportation method."

[0522] In this way, the system of the present invention performs dynamic optimization taking into account various data and user emotions, thereby improving the efficiency of the logistics network and increasing user satisfaction.

[0523] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0524] Step 1: Collect data

[0525] The server uses external APIs to collect traffic information, weather data, delivery destination business hours, and transportation cost and environmental impact data. Specifically, the server obtains traffic information every five minutes from the Google Maps API and weather data every hour from the OpenWeatherMap API. Delivery destination business hours are obtained from the database once a day at night, and transportation cost and environmental impact data are collected once a month through the API. This collected data is stored in the database and used in the next step.

[0526] Input: Raw data obtained from API

[0527] Output: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[0528] Step 2: Data Preprocessing

[0529] The server formats the collected data and converts it into a format that can be input to the machine learning model. Specifically, it uses Python scripts to normalize the data (e.g., scaling the value range to 0-1) and impute missing values ​​(e.g., imputing missing values ​​with the mean). The preprocessed data is then prepared as input for the AI ​​model.

[0530] Input: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[0531] Output: Preprocessed data (normalized and imputed data)

[0532] Step 3: Input to the machine learning model

[0533] The server inputs the preprocessed data into a machine learning model. Specifically, the data is passed in batches to an AI model built using TensorFlow or PyTorch, which performs inference. The AI ​​model then calculates the optimal delivery route and transportation method.

[0534] Input: Preprocessed data

[0535] Output: Optimal delivery route and transportation means

[0536] Step 4: Collect and analyze emotion data

[0537] The device collects user emotional data using a camera and microphone. For example, it uses a deep learning model to analyze the user's facial expressions and voice tone captured by the camera in real time and extract emotional data. The extracted emotional data is then sent to a server.

[0538] Input: User's face image and voice input

[0539] Output: Emotion data (e.g., dissatisfied, satisfied, surprised)

[0540] Step 5: Adjust optimization based on sentiment data

[0541] The server analyzes the received emotional data and adjusts the optimization results based on the results. For example, if the user expresses dissatisfaction, it will run the AI ​​model again to calculate a different delivery route and transportation method, and generate a new optimization result.

[0542] Input: Sentiment data, initial results of optimal delivery routes and transportation methods

[0543] Output: Coordinated optimal delivery routes and modes

[0544] Step 6: Generate and send notifications

[0545] The server generates a notification message based on the optimization results and the emotion engine analysis results. Specifically, it generates an HTML email or push notification and sends it to the user's device.

[0546] Input: Optimization results, sentiment analysis results

[0547] Output: Notification messages (e.g., delivery route, transportation method, expected delivery time)

[0548] Step 7: Receive and confirm notifications

[0549] The device receives notification messages sent from the server and displays them on the screen. The user can then review the notification content and fine-tune their delivery plan as needed. For example, they can view optimized route and transportation suggestions in real time via push notifications on their smartphone or desktop notifications on their PC.

[0550] Input: Notification message

[0551] Output: User confirmation and approval

[0552] Step 8: Real-time monitoring and dynamic re-optimization

[0553] The server continues to monitor traffic and weather information in real time even during deliveries. When new data is acquired, the AI ​​model is reactivated as needed to recalculate the optimization results according to the situation. For example, if information about a sudden accident is received, a recalculated delivery route will be immediately proposed.

[0554] Input: Real-time data (traffic information, weather data)

[0555] Output: Recalculated optimal delivery route and means

[0556] Step 9: Re-notification and instruction adjustment

[0557] The server notifies the user terminal of the new optimization results and promptly notifies the user if new instructions are required. The user checks the re-notification and, if new instructions are required, issues new instructions to the logistics company.

[0558] Input: Recalculated optimization results

[0559] Output: Reminder message, user instruction adjustment

[0560] In this way, this system collects, analyzes, and optimizes data through each processing step, realizing flexible logistics management that also takes user emotions into consideration.

[0561] (Application example 2)

[0562] 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."

[0563] Conventional logistics network optimization systems have been able to optimize delivery routes based on traffic information, weather data, and transportation methods, but no systems have been able to flexibly respond by taking user emotions into account. As a result, they have been unable to adequately address the stress and dissatisfaction felt by users due to unforeseen circumstances. The present invention aims to provide a system that further improves user satisfaction by recognizing user emotions and dynamically re-optimizing delivery routes and transportation methods based on those emotions.

[0564] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0565] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the user of the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for recognizing user emotions and re-optimizing the delivery route and transportation means based on the emotion data. This enables more flexible and satisfying responses that take user emotions into consideration when optimizing a logistics network.

[0566] "Traffic information" refers to data about the current and predicted state of road traffic, such as road congestion, accident information, and construction information.

[0567] "Weather data" refers to meteorological information such as the current weather, temperature, probability of precipitation, and wind speed in areas along the delivery route.

[0568] "Delivery destination business hours" refers to the hours during which each delivery destination can receive packages.

[0569] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[0570] "Environmental Impact Data" means data showing the environmental impact, such as carbon dioxide emissions, associated with the use of a means of transportation.

[0571] The "optimal delivery route" refers to the most efficient route, taking into account factors such as traffic conditions, weather, opening hours at the delivery destination, transportation costs, and environmental impact.

[0572] "Means of transport" refers to the method of transporting goods, such as truck or rail.

[0573] "Recognizing user emotions" refers to detecting the user's emotional state through voice input or facial recognition.

[0574] "Emotion data" refers to data obtained as a result of emotion recognition of a user, and includes, for example, emotional states such as joy or stress.

[0575] "Dynamic re-optimization" refers to constantly recalculating the optimal route and transportation method based on real-time changes in traffic information, weather data, user sentiment, and other factors.

[0576] "Notifying" refers to conveying information about the selected delivery route and transportation means to the user and other relevant parties.

[0577] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on them.

[0578] Data collection

[0579] server

[0580] First, the server collects traffic information using an external API. This data includes road congestion, accident information, and construction information. Similarly, weather data is collected using a weather information API. This data includes information on the current weather along the delivery route, temperature, precipitation probability, wind speed, and other information. The server also obtains the business hours of delivery destinations through a database and API, confirming the times when each destination can accept packages. Furthermore, data on the cost and environmental impact of transportation methods is collected from the APIs of truck rental companies and railway companies.

[0581] Data analysis and optimal route selection

[0582] server

[0583] The server preprocesses this collected data and formats it so that it can be input into the AI ​​model. Specifically, it normalizes the data and fills in missing values. Using the formatted data, a machine learning model is used to calculate the optimal delivery route and means of transportation. For example, it can suggest routes that avoid traffic jams or safe routes in bad weather. The optimal route and means of transportation are extracted from the calculation results and compiled as the optimization results.

[0584] User emotion recognition and response

[0585] server

[0586] To recognize the user's emotions, an emotion engine installed on the server runs. This emotion engine collects emotion data through the user's voice input and facial recognition. For example, the user can use the camera on their smartphone to perform facial recognition.

[0587] Terminal

[0588] The user device, such as a smartphone or smart glasses, analyzes the user's emotions in real time using voice input and a camera, detecting when the user expresses dissatisfaction with a delivery delay.

[0589] server

[0590] The emotion engine analyzes the collected emotional data and adjusts the optimization results based on the results, re-proposing an alternative delivery route if the user expresses dissatisfaction.

[0591] User notification and execution management

[0592] server

[0593] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[0594] Terminal

[0595] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system of the smartphone or PC is used to notify the user in real time.

[0596] User

[0597] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[0598] Real-time monitoring and dynamic re-optimization

[0599] server

[0600] While the delivery is in progress, the server continues to monitor real-time traffic and weather data. For example, it collects new traffic congestion information and weather changes as they occur. It then re-runs the AI ​​model based on the real-time data, dynamically recalculating the optimization results if the situation changes.

[0601] Terminal

[0602] The new optimization results are notified to the user terminal again, and any necessary changes are quickly notified.

[0603] User

[0604] The re-notification is checked, and if new instructions are required, new instructions are issued to the logistics company, who then carries out delivery using the proposed route.

[0605] As a specific example, while a logistics manager is patrolling a site wearing smart glasses, if a delivery route is predicted to be delayed due to traffic congestion, the camera built into the glasses detects the manager's anxious facial expression and collects emotional data using an emotion recognition API. Based on this data, the AI ​​model re-proposes a safe and quick alternative route and immediately notifies the smart glasses. An example of a prompt is, "When a logistics manager is wearing smart glasses and the delivery route is likely to be delayed due to traffic congestion, the camera detects an anxious facial expression. Please process this data using the emotion API, have the AI ​​model recalculate an alternative route, and generate code to notify the new route."

[0606] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0607] Step 1:

[0608] The server uses an external API to collect traffic information. The data obtained from this external API includes road congestion status, accident information, and construction information. The API endpoint is called as input, and the latest traffic information data is obtained as output. Specifically, the server sends an HTTP request and receives JSON format data as a response.

[0609] Step 2:

[0610] The server collects weather data using a weather information API. The data obtained from this API includes weather, temperature, precipitation probability, and wind speed. The API request parameters are set as input, and weather forecast data is obtained as output. Specifically, the server makes an API request with the set parameters and receives a response.

[0611] Step 3:

[0612] The server retrieves business hours information for each destination from the destination database. This includes the times when each destination can receive packages. The server queries the destination ID or address as input and retrieves the business hours data as output. Specifically, the server executes the database query and extracts the required information.

[0613] Step 4:

[0614] The server collects cost and environmental impact data (e.g., CO2 emissions) for transportation modes through the APIs of truck rental companies and railway companies. It specifies the API key and query parameters as input, and obtains the cost and environmental data for each transportation mode as output. Specific operations include sending an API request and analyzing the response data.

[0615] Step 5:

[0616] The server consolidates all collected data and performs preprocessing. This involves normalizing the data, filling in missing values, and formatting it for input into the AI ​​model. It uses all the raw data it acquires as input and creates a formatted dataset as output. Specifically, it uses a data frame processing library (e.g., Pandas) to format the data.

[0617] Step 6:

[0618] The server inputs the formatted data into a machine learning model to calculate the optimal delivery route and transportation method. It uses the preprocessed data as input and gets the optimal route proposal as output. Specifically, it inputs the data into a pre-trained AI model (e.g., a Scikit-learn or TensorFlow model) and gets the prediction results.

[0619] Step 7:

[0620] The server generates a notification message based on the optimization results. It uses the AI ​​model's prediction results and the user's emotional data as input, and creates a notification message to send to the user as output. Specifically, it uses a text generation algorithm to construct a message containing the necessary information.

[0621] Step 8:

[0622] The device receives notifications sent from the server and displays them to the user. It receives notification data from the server as input and displays a message on the user's screen as output. Specific operations involve using the notification function of the mobile app or web app.

[0623] Step 9:

[0624] The user checks the notification from the server and approves or modifies the optimized route and transportation proposal. The user checks the notification content displayed on the terminal as input and gives instructions for approval or modification as output. Specific actions include tapping a button on the user interface.

[0625] Step 10:

[0626] While the delivery is in progress, the server continuously monitors real-time traffic and weather data. It receives the latest API data as input and generates re-optimized results as output, making periodic API requests to collect and analyze new data.

[0627] Step 11:

[0628] The server then re-sends notifications to the user, if necessary, based on the results of the re-optimization. It uses the newly calculated optimal route as input and generates a re-notification message as output. Specifically, it re-executes the notification generation process described above.

[0629] Step 12:

[0630] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The user checks the content of the re-notification as input and issues instructions to the logistics company as output. The specific operation is to perform a new operation according to the use case.

[0631] 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.

[0632] 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.

[0633] 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.

[0634] [Second embodiment]

[0635] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0636] 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.

[0637] 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).

[0638] 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.

[0639] 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.

[0640] 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).

[0641] 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.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] 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.

[0646] 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."

[0647] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. The operation of the system will be explained below based on a specific example embodiment.

[0648] Data collection

[0649] server

[0650] 1. Collection of traffic information

[0651] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[0652] 2. Weather data collection

[0653] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[0654] 3. Obtaining delivery address business hours

[0655] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0656] 4. Collecting transportation cost and environmental impact data

[0657] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[0658] Data analysis and optimal route selection

[0659] server

[0660] 1. Data Preprocessing

[0661] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0662] 2. Input to the AI ​​model

[0663] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[0664] 3. Extracting optimization results

[0665] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as the optimization results.

[0666] User notification and execution management

[0667] server

[0668] 1. Generate a notification

[0669] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[0670] Terminal

[0671] 1. Receiving notifications

[0672] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[0673] User

[0674] 1. Check the notification content

[0675] The delivery manager (user) checks the notification from the server and approves the proposed optimized route and transportation means.

[0676] Real-time monitoring and dynamic re-optimization

[0677] server

[0678] 1. Real-time data monitoring

[0679] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0680] 2. Dynamic Reoptimization

[0681] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[0682] Terminal

[0683] 1. Reminder

[0684] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[0685] User

[0686] 1. Reconfirmation and adjustment of instructions

[0687] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[0688] In this way, each component of this system, including the server, terminals, and users, works together to create an optimal logistics network based on the latest information, which can effectively resolve issues facing the entire logistics industry, such as reducing delivery delays, improving cost efficiency, and being environmentally conscious.

[0689] The processing flow will be explained below.

[0690] Step 1: Collect data

[0691] server

[0692] The server uses the Google Maps API to collect current traffic conditions and forecasts for major roads.

[0693] The server uses the Weather API to obtain current weather information and forecasts along the delivery route.

[0694] The server obtains business hours information for each delivery destination from the delivery destination database.

[0695] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and rail companies.

[0696] Step 2: Data Preprocessing

[0697] server

[0698] The server formats the collected data and prepares it in a format that can be input into the AI ​​model.

[0699] Specifically, it normalizes data, fills in missing values, and converts data types as necessary.

[0700] Step 3: Input to the AI ​​model

[0701] server

[0702] The server inputs the preprocessed data into a machine learning model and performs analysis.

[0703] Calculate optimal routes and modes of transport, taking into account traffic, weather, opening hours, transport costs and environmental impacts.

[0704] Step 4: Extracting optimization results

[0705] server

[0706] The optimal route and transportation method are extracted from the output of the AI ​​model.

[0707] This provides a detailed dispatch plan for optimization.

[0708] Step 5: Generate notifications

[0709] server

[0710] The server generates a message to notify the user based on the optimization result.

[0711] Specifically, it creates detailed information including the best route, transportation method, and estimated delivery time.

[0712] Step 6: Receive notifications

[0713] Terminal

[0714] The user device (smartphone or PC) receives the notification sent from the server and displays it on the screen.

[0715] Allow delivery managers to check notifications in real time.

[0716] Step 7: Review and approve the notification

[0717] User

[0718] The delivery manager reviews the notification displayed on the terminal and approves the optimized route and transportation proposal.

[0719] Tweak your delivery plan if necessary.

[0720] Step 8: Instructions for the carrier

[0721] User

[0722] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation information.

[0723] Specifically, instructions are sent to the supplier via the delivery management system.

[0724] Step 9: Monitor real-time data

[0725] server

[0726] The server continues to monitor traffic and weather data in real time while the delivery is in progress.

[0727] The database is updated as new information becomes available.

[0728] Step 10: Dynamic Reoptimization

[0729] server

[0730] The server then uses the AI ​​model again based on real-time data to dynamically perform optimization.

[0731] Depending on the situation, new optimal routes and means of transportation are recalculated.

[0732] Step 11: Snooze

[0733] server

[0734] If necessary, the new optimization results are notified to the user terminal.

[0735] Provides optimization information that responds to real-time fluctuations.

[0736] Step 12: Review and adjust instructions

[0737] User

[0738] The user checks the re-notification and issues new instructions to the delivery company if necessary.

[0739] The logistics company will then continue delivery using the proposed new route.

[0740] In this way, the server, terminals, and users work together to maintain an optimal logistics network based on the latest information, which reduces delivery delays, cuts costs, and is environmentally friendly.

[0741] Example 1

[0742] 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."

[0743] In current logistics networks, it is difficult to select the optimal delivery route and transportation method in real time, taking into account traffic information, weather data, delivery destination business hours, and the cost and environmental impact of transportation methods. Furthermore, collected data is not pre-processed sufficiently, and there is no mechanism for dynamic re-optimization when conditions change. This results in increased risks of delivery delays, increased costs, and negative environmental impacts, hindering efficient logistics.

[0744] 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.

[0745] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, and a means for acquiring business hours of delivery destinations. It also includes a means for collecting data on the cost and environmental impact of transportation means, a means for preprocessing the collected data, a means for selecting an optimal delivery route and transportation means using a machine learning model, a means for notifying the selected delivery route and transportation means, and a means for monitoring the data in real time and dynamically re-optimizing the data. This enables comprehensive analysis of various data and the provision of an optimal logistics network based on the latest information.

[0746] "Traffic information" refers to general information relating to vehicle traffic, such as road congestion, accident information, and construction information.

[0747] "Weather data" refers to general information about the weather, such as the weather in a particular area, temperature, probability of precipitation, wind speed, etc.

[0748] "Delivery destination business hours" refers to general information about the dates and times when each delivery destination can receive packages.

[0749] "Transportation costs" are the economic costs incurred to transport a load over a specific distance or weight.

[0750] "Environmental impact data" is information about the adverse environmental impacts, such as carbon dioxide emissions, caused by a particular mode of transportation.

[0751] "Preprocessing" is the process of formatting collected data, filling in missing values, and normalizing it to make it suitable for analysis or model input.

[0752] A "machine learning model" is an algorithm or computational method that learns patterns and knowledge through data analysis and makes predictions and classifications based on new data.

[0753] "Optimal delivery route and transportation mode selection" is the process of determining the most efficient and cost-effective delivery route and transportation mode by taking into account various data.

[0754] "Notifying" refers to the act of communicating the determined information or results to the user.

[0755] "Real-time monitoring" means continuously obtaining the latest data at the current time and immediately grasping changes in the situation.

[0756] "Dynamic re-optimization" is the process of recalculating and, if necessary, changing the optimal route or mode of transportation based on new information that becomes available in real time.

[0757] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time.

[0758] Data collection

[0759] server

[0760] The server utilizes several external APIs and databases to collect the following data:

[0761] 1. Collection of traffic information

[0762] The server uses the API of a traffic information service (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads, such as road congestion levels, accident information, and construction information.

[0763] 2. Weather data collection

[0764] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route, including local weather, temperature, chance of precipitation, wind speed, etc.

[0765] 3. Obtaining delivery address business hours

[0766] The server queries the database of delivery destinations to obtain the acceptable opening hours for each delivery destination, e.g., opening and closing times for stores.

[0767] 4. Collecting transportation cost and environmental impact data

[0768] The server collects cost and CO2 emissions data for each mode of transport from the APIs or internal databases of truck rental and rail companies, including the cost of delivering a certain distance and the carbon footprint of that mode of transport.

[0769] Data preprocessing and input to AI models

[0770] server

[0771] The collected data is first preprocessed. The server formats the data, imputes missing values, and normalizes it to prepare it in a format suitable for machine learning models. The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow) to calculate the optimal delivery route and transportation method. For example, it suggests routes that avoid traffic jams or safe routes in bad weather.

[0772] Notification of optimization results and execution management

[0773] server

[0774] Once the optimization results are obtained, the server generates a message to notify the user based on the results, including details such as the optimal route, transportation method, and estimated delivery time.

[0775] Terminal

[0776] The delivery manager's terminal receives the notification sent from the server and displays this information to the user in real time through the notification system.

[0777] User

[0778] The delivery manager checks the notification from the server and approves the proposed optimal route and transportation means, thereby carrying out the delivery work.

[0779] Real-time monitoring and dynamic re-optimization

[0780] server

[0781] While the delivery is in progress, the server continues to monitor traffic and weather data in real time. When new traffic congestion information or weather changes are collected, the server restarts the AI ​​model and re-optimizes it. The server then notifies the user again based on the new optimization results, promptly informing them of any necessary changes.

[0782] Terminal

[0783] The terminal receives new notifications and displays the necessary information to the user in real time.

[0784] User

[0785] The user confirms the re-notification and issues new instructions to the logistics company, who then carries out delivery using the proposed new route.

[0786] Specific examples

[0787] As a specific example, the following case can be mentioned.

[0788] Example: Optimizing delivery routes from Tokyo to Osaka. Collect data using a traffic information API, weather API, delivery destination business hours database, and truck rental API, and use a machine learning model to calculate the optimal route taking traffic congestion and weather into account.

[0789] Example prompt for a generative AI model:

[0790] "Calculate the optimal delivery route from Tokyo to Osaka. Recommend the best route and transportation method, taking into account traffic information, weather data, destination opening hours, truck rental costs and environmental impact."

[0791] In this way, the system of the present invention integrates and analyzes various types of data, and by always providing an optimal logistics network based on the latest information, it is possible to reduce delivery delays, improve cost efficiency, and be environmentally friendly.

[0792] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0793] Step 1: Collect data

[0794] server

[0795] The server uses multiple external APIs and databases to gather traffic information, weather data, delivery location opening hours, transportation costs, and environmental impact data. Specifically, it sends a "GET" request to retrieve the following data:

[0796] Input: A request containing an API key and query parameters

[0797] Output: Traffic information, weather data, business hours data, and transportation data in JSON format

[0798] Examples:

[0799] Traffic information: congestion, accident information, construction information

[0800] Weather data: weather, temperature, chance of precipitation, wind speed

[0801] Business hours: Opening and closing times for each delivery location

[0802] Cost and environmental impact data: shipping costs, CO2 emissions

[0803] Step 2: Data Preprocessing

[0804] server

[0805] The collected data is preprocessed and formatted so that it can be fed into a machine learning model. Specifically, missing values ​​are imputed and the data is normalized.

[0806] Input: JSON formatted collected data

[0807] Output: Preprocessed dataset

[0808] Examples:

[0809] Missing Value Imputation: Impute missing weather data with the mean value

[0810] Data normalization: Scaling numerical data such as traffic information or temperature to a range of 0 to 1

[0811] Step 3: Input to the AI ​​model

[0812] server

[0813] The preprocessed data is fed into a machine learning model to calculate the optimal delivery route and transportation method. A TensorFlow model is used.

[0814] Input: Preprocessed dataset

[0815] Output: Prediction results of the AI ​​model

[0816] Examples:

[0817] Suggesting routes to avoid traffic jams

[0818] Choosing a safe route in bad weather

[0819] Step 4: Extracting optimization results

[0820] server

[0821] The optimal route and mode of transport is extracted from the output of the AI ​​model and the results are shaped.

[0822] Input: AI model prediction results

[0823] Output: Optimal route and transportation details

[0824] Examples:

[0825] Optimal Route: Recommended route from origin to destination

[0826] Transportation: Preferred transportation method (truck or rail)

[0827] Step 5: Generate notifications

[0828] server

[0829] Based on the optimization results, a message is generated to notify the user.

[0830] Input: Best route and transportation details

[0831] Output: Information message

[0832] Examples:

[0833] Message content: Delivery schedule, route details, transportation method, estimated delivery time

[0834] Step 6: Receive and view notifications

[0835] Terminal

[0836] The delivery manager's terminal receives the notification sent from the server and displays it on the screen.

[0837] Input: Notification message sent by the server

[0838] Output: Notification displayed on the screen

[0839] Examples:

[0840] Use smartphone and PC notification systems to notify users in real time

[0841] Step 7: Review and approve the notification

[0842] User

[0843] The delivery manager checks the notification sent from the server and approves the proposed optimal route and transportation means.

[0844] Input: Notification message displayed on the screen

[0845] Output: Approval or correction instructions

[0846] Examples:

[0847] After checking on your smartphone or PC, press the approval button

[0848] Step 8: Monitor real-time data

[0849] server

[0850] Even while the delivery is in progress, traffic and weather data is monitored in real time to collect the latest information.

[0851] Input: Real-time data from API

[0852] Output: Updated traffic and weather data

[0853] Examples:

[0854] Timely acquisition of new traffic congestion information and weather change data

[0855] Step 9: Dynamic Reoptimization

[0856] server

[0857] The AI ​​model is reactivated based on real-time data and re-optimized according to changes in the situation.

[0858] Input: Updated traffic and weather data

[0859] Output: New optimal route and transportation details

[0860] Examples:

[0861] Proposing the best alternative route in the event of a sudden accident

[0862] Step 10: Generate and send a snooze notification

[0863] server

[0864] Based on the results of the re-optimization, a notification message is generated and sent to the user again.

[0865] Input: New best route and transportation details

[0866] Output: New notification message

[0867] Examples:

[0868] Clearly state the changes and notify users again

[0869] Step 11: Receive and view snooze notifications

[0870] Terminal

[0871] The delivery manager's terminal receives the new notification message and displays it on the screen.

[0872] Input: New notification message sent by the server

[0873] Output: The new notification displayed on the screen.

[0874] Examples:

[0875] Use smartphone or PC notification systems to notify users again in real time

[0876] Step 12: Review and adjust instructions

[0877] User

[0878] The delivery manager will review the new notification and issue new instructions to the logistics company if necessary.

[0879] Input: New notification displayed on screen

[0880] Output: Sending new instructions

[0881] Examples:

[0882] Instructing logistics companies to continue deliveries using new recommended routes

[0883] These steps ensure that the system always provides the most optimal logistics network based on up-to-date information, reducing delivery delays, improving cost efficiency, and being environmentally friendly.

[0884] (Application example 1)

[0885] 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."

[0886] In today's world, where efficiency and sustainability are required for logistics, it is necessary to select the optimal delivery route taking into account traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact. However, existing systems are unable to support dynamic optimization in real time, making it difficult to respond quickly to sudden traffic congestion or weather changes. In addition, there is a lack of concrete improvement measures to achieve efficient delivery at logistics centers.

[0887] 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.

[0888] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for calculating a delivery route in conjunction with the collected data and displaying the optimization result through an application installed on the transport robot. This makes it possible to select an optimal delivery route and transportation means in real time at a logistics center, thereby achieving efficient and sustainable delivery.

[0889] "Traffic information" refers to data related to traffic, such as road congestion, accidents, and construction work.

[0890] "Weather data" refers to various information related to weather, such as weather, temperature, precipitation, and wind speed.

[0891] "Business hours of delivery destination" refers to the opening and closing hours of the facility or store to which the logistics center delivers.

[0892] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[0893] "Environmental impact data" refers to data on the impact that a means of transportation has on the environment, specifically data on CO2 emissions, etc.

[0894] The "optimal delivery route" is the most efficient and economical delivery route calculated based on multiple conditions.

[0895] "Transportation" means the means (e.g., truck, rail, etc.) used to transport goods from a distribution center to a delivery destination.

[0896] A "notification" is a means by which a system communicates information to a user.

[0897] "Real-time data monitoring" means that the system continuously monitors data according to the current situation.

[0898] "Dynamic reoptimization" refers to the process by which the AI ​​model recalculates new optimal delivery routes and modes of transportation whenever conditions change.

[0899] An "application" is software designed to perform a specific task.

[0900] A "transport robot" is an automated mechanical device used in logistics centers to transport and organize cargo.

[0901] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system is realized through the cooperation of a server, terminals, and users.

[0902] Data collection

[0903] server:

[0904] 1. Traffic information collection:

[0905] The server uses external APIs to obtain traffic conditions and forecasts for major roads, specifically road congestion, accident information, and construction information.

[0906] 2. Weather data collection:

[0907] The server uses a weather information API to obtain weather information and forecasts for the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each region.

[0908] 3. Get delivery location business hours:

[0909] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0910] 4. Collecting transportation cost and environmental impact data:

[0911] The server collects data on the cost and CO2 emissions of each transportation mode from the APIs or internal databases of truck rental companies and rail companies.

[0912] Data analysis and optimal route selection

[0913] server:

[0914] 1. Data Preprocessing:

[0915] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0916] 2. Input to the AI ​​model:

[0917] The server uses machine learning models (such as TensorFlow) to calculate optimal delivery routes and transportation methods based on the preprocessed data, for example, proposing routes to avoid traffic jams or safe routes in bad weather.

[0918] 3. Extracting optimization results:

[0919] The server extracts the optimal route and transportation method from the output of the AI ​​model.

[0920] User notification and execution management

[0921] server:

[0922] 1. Generate notification:

[0923] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[0924] Device:

[0925] 1. Receiving notifications:

[0926] The delivery manager's device receives the notification sent from the server and displays it on the screen. For example, a notification system on a smartphone or PC can be used to notify the user in real time.

[0927] User:

[0928] 1. Check the notification:

[0929] The delivery manager checks the notification from the server and approves the proposal for the optimized route and transportation means.

[0930] Real-time monitoring and dynamic re-optimization

[0931] server:

[0932] 1. Real-time data monitoring:

[0933] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[0934] 2. Dynamic reoptimization:

[0935] The server then reactivates the AI ​​model based on real-time data and dynamically recalculates the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, the server immediately suggests an optimal alternative route.

[0936] Device:

[0937] 1. Reminder:

[0938] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[0939] User:

[0940] 1. Review and adjust instructions:

[0941] The user checks the re-notification and issues new instructions to the distributor if new instructions are required.

[0942] In this way, optimization results can be displayed through an application installed on the delivery robots within the logistics center, enabling efficient delivery management in real time.

[0943] Specific processing examples

[0944] Road congestion and accident information obtained from the traffic information API is input into the AI ​​model to calculate the optimal route from the logistics center to a specific store.

[0945] In the event of a sudden change in weather or a new traffic accident, the information is reloaded in real time, and the AI ​​model is recalculated to present a new route.

[0946] Example prompt for a generative AI model:

[0947] "Can you calculate the optimal route from the logistics center to each delivery destination based on traffic, weather, and business information? Specifically, please suggest routes that avoid traffic jams and are safe in bad weather."

[0948] This will enable a significant improvement in delivery efficiency at logistics centers.

[0949] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0950] Step 1:

[0951] The server collects traffic information. Specifically, it uses an external API to obtain current and forecast traffic conditions for major roads. In this case, it sends an API request and receives data such as road congestion, accident information, and construction information. The input is the response data from the API, and the output is structured traffic information data.

[0952] Step 2:

[0953] The server collects weather data. It uses a weather information API to obtain weather information and forecasts for the delivery route. For example, it obtains data such as the weather, temperature, precipitation probability, and wind speed for each region via an API request and processes that information. The input is the response data from the API, and the output is structured weather information data.

[0954] Step 3:

[0955] The server retrieves the business hours of delivery destinations. It sends a query to the delivery destination database to retrieve the acceptable business hours for each delivery destination. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information from the database. The input is the response data from the database, and the output is structured business hours data.

[0956] Step 4:

[0957] The server collects data on the cost and environmental impact of transportation modes. It collects data such as the cost and CO2 emissions of each transportation mode from the APIs of truck rental companies and railway companies, or from an internal database. The input is the response data from the API or database, and the output is structured cost and environmental impact data.

[0958] Step 5:

[0959] The server preprocesses the collected data. Specifically, it normalizes the data, fills in missing values, and formats it so that it can be input into an AI model. The input is various collected data, and the output is a compiled dataset.

[0960] Step 6:

[0961] The server uses an AI model based on the preprocessed data to calculate the optimal delivery route and transportation method. Using machine learning libraries such as TensorFlow, the server inputs data into the model to make predictions. The input is the preprocessed dataset, and the output is a proposal for an optimized delivery route and transportation method.

[0962] Step 7:

[0963] The server generates a message to notify the user based on the optimization results. Specifically, it creates detailed information including the optimal route, transportation method, and expected delivery time, and prepares it to be sent to the user's device. The input is the output data of the AI ​​model, and the output is the notification message.

[0964] Step 8:

[0965] The device receives notifications sent from the server and displays them on the screen. For example, it notifies the user in real time using the notification system of a smartphone or PC. The input is the notification message from the server, and the output is the notification displayed on the device.

[0966] Step 9:

[0967] The user checks the notification from the server and approves the proposed optimized route and transportation means. The input is the notification content displayed on the terminal, and the output is the user's approval action.

[0968] Step 10:

[0969] The server monitors traffic and weather data in real time while the delivery is in progress. New traffic congestion information and weather change data are collected as they arrive and updated within the system. The input is real-time data, and the output is updated status data.

[0970] Step 11:

[0971] The server then runs the AI ​​model again based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, it will immediately suggest an optimal alternative route. The input is updated real-time data, and the output is the recalculated optimal route.

[0972] Step 12:

[0973] The server re-notifies the user terminal of the new optimization results and promptly notifies them of any necessary changes. The input is the recalculated optimal route, and the output is the re-notification message.

[0974] Step 13:

[0975] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The input is the re-notification message and the output is the user's new instructions.

[0976] Through the above steps, efficient and sustainable delivery management can be achieved using applications installed on delivery robots within logistics centers.

[0977] 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.

[0978] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, delivery destination business hours, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on those emotions. The operation of this system will be explained below based on a specific example of the system.

[0979] Data collection

[0980] server

[0981] 1. Collection of traffic information

[0982] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[0983] 2. Weather data collection

[0984] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[0985] 3. Obtaining delivery address business hours

[0986] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[0987] 4. Collecting transportation cost and environmental impact data

[0988] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[0989] Data analysis and optimal route selection

[0990] server

[0991] 1. Data Preprocessing

[0992] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[0993] 2. Input to the AI ​​model

[0994] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[0995] 3. Extracting optimization results

[0996] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as optimization results.

[0997] User emotion recognition and response

[0998] server

[0999] 1. Emotional Engine Activation

[1000] The emotion engine installed on the server collects emotion data through user voice input and facial recognition. For example, a user sets up a scene where facial recognition is performed using a smartphone camera.

[1001] Terminal

[1002] 1. Emotion analysis via voice input or facial recognition

[1003] The user device uses voice input and a camera to analyze the user's emotions in real time, for example, detecting when the user expresses dissatisfaction with a delivery delay.

[1004] server

[1005] 1. Emotional Data Analysis

[1006] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, for example, re-proposing a different delivery route if the user expresses dissatisfaction.

[1007] User notification and execution management

[1008] server

[1009] 1. Generate a notification

[1010] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[1011] Terminal

[1012] 1. Receiving notifications

[1013] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[1014] User

[1015] 1. Check the notification content

[1016] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1017] Real-time monitoring and dynamic re-optimization

[1018] server

[1019] 1. Real-time data monitoring

[1020] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1021] 2. Dynamic Reoptimization

[1022] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[1023] Terminal

[1024] 1. Reminder

[1025] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[1026] User

[1027] 1. Reconfirmation and adjustment of instructions

[1028] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[1029] In this way, the server, terminals, users, and emotion engine work together to create a logistics network that is always the most efficient and satisfies users, thereby reducing delivery delays, cutting costs, being environmentally friendly, and improving customer satisfaction.

[1030] The processing flow will be explained below.

[1031] Step 1: Collect data

[1032] server

[1033] The server uses the Google Maps API to collect current and forecast traffic conditions on major roads, specifically traffic flow, congestion information, and accident information.

[1034] The server uses the Weather API to collect current weather information along the delivery route, specifically the weather, temperature, precipitation probability, wind speed, etc. for each area.

[1035] The server retrieves the acceptable business hours of each delivery destination from the delivery destination database, for example, the business hours and holiday information of each store.

[1036] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and railroad companies, specifically, the costs and environmental impact data of each transportation method.

[1037] Step 2: Data Preprocessing

[1038] server

[1039] The server prepares the collected data in a format suitable for analysis, for example by filling in missing data and standardizing the data format.

[1040] Normalize and scale the data to prepare it for input into the AI ​​model.

[1041] Step 3: Input to the AI ​​model

[1042] server

[1043] The server inputs the pre-processed data into an AI model for real-time analysis, using machine learning algorithms to calculate the optimal delivery route and transportation method.

[1044] Step 4: Extracting optimization results

[1045] server

[1046] The server extracts the optimization results obtained from the AI ​​model, such as the optimal route and means of transportation.

[1047] The optimization results are compiled as a delivery plan.

[1048] Step 5: Collecting emotion data

[1049] Terminal

[1050] The user device collects the user's emotions using voice input or a camera, for example, by the user speaking into a smartphone or pointing their face at the device's camera.

[1051] Step 6: Analyze the sentiment data

[1052] server

[1053] The emotion engine installed on the server analyzes the collected emotion data, for example, analyzing voice data to determine whether the user is angry or happy.

[1054] Step 7: Emotional Adjustment

[1055] server

[1056] The server adjusts the optimization results based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will re-propose a different delivery route.

[1057] Step 8: Generate notifications

[1058] server

[1059] The server generates a message based on the optimization and sentiment analysis results, creating a notification that includes detailed information such as the delivery route, transportation method, and estimated delivery time.

[1060] Step 9: Receive notifications

[1061] Terminal

[1062] The user device receives the notification sent from the server and displays it on the screen. For example, the notification system of a smartphone or PC is used to notify the user in real time.

[1063] Step 10: Review and approve the notification

[1064] User

[1065] The delivery manager (user) checks the notification displayed on the terminal, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1066] Step 11: Instructions for the carrier

[1067] User

[1068] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation method information. Specifically, the instructions are notified to the company through the delivery management system.

[1069] Step 12: Monitor real-time data

[1070] server

[1071] The server monitors traffic and weather information in real time while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1072] Step 13: Dynamic Reoptimization

[1073] server

[1074] The server then uses the AI ​​model to dynamically optimize the route and transportation method based on real-time data, and if conditions change, it recalculates the optimal route and transportation method.

[1075] Step 14: Snooze

[1076] server

[1077] The server notifies the user terminal of the new optimization results, providing a new delivery plan that responds to real-time fluctuations.

[1078] Step 15: Review and adjust instructions

[1079] User

[1080] The user can then review the re-notification and issue new instructions to the delivery company if necessary, and the delivery company will then continue delivery using the proposed new route.

[1081] In this way, the server, terminals, users, and emotion engine work together to create the most efficient logistics network possible, which always provides the highest level of user satisfaction. This reduces delivery delays, cuts costs, contributes to environmental friendliness, and improves customer satisfaction.

[1082] Example 2

[1083] 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."

[1084] Conventional logistics network systems face the problem of difficult integrated control of multiple data sources, as they individually manage and analyze traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact data. Dynamic real-time re-optimization and adjustment of optimization content based on user emotion recognition are also difficult, resulting in reduced customer satisfaction and efficiency. Furthermore, data preprocessing and the use of machine learning models are difficult to implement, increasing the system's complexity and making implementation difficult.

[1085] 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.

[1086] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, a means for acquiring business hours of delivery destinations, and a means for collecting data on transportation costs and environmental impacts. This allows for a means for selecting an optimal delivery route and transportation means based on the collected data, which in turn includes a means for analyzing data using a machine learning model, a means for notifying the user of the selected delivery route and transportation means, a means for monitoring the data in real time and dynamically re-optimizing the data, and a means for collecting and analyzing user emotion data and adjusting the optimization content based on the data. This allows for integrated control of various data sources, dynamic optimization in real time, and flexible optimization based on user emotion, thereby improving the efficiency of the logistics network and customer satisfaction.

[1087] "Traffic information" refers to data on the current state and forecast of road traffic, such as road congestion, accident information, and construction information.

[1088] "Weather data" refers to data relating to weather conditions, such as the weather, temperature, probability of precipitation, and wind speed, for a particular area.

[1089] "Delivery destination business hours" is information about the hours during which a specific delivery destination can accept packages.

[1090] "Cost of transportation" refers to data on the fees and expenses incurred when using a particular transportation method.

[1091] "Environmental impact data" refers to data on the environmental impact, such as CO2 emissions, that occurs when a particular means of transportation is used.

[1092] A "machine learning model" is an algorithm or framework for analyzing data and making predictions or classifications based on that data.

[1093] "Preprocessing means" refers to the process of standardizing and normalizing collected data, filling in missing values, and otherwise preparing the data in an analyzable format.

[1094] "Dynamic reoptimization" is the process of recalculating and updating optimal delivery routes and modes of transportation in response to changes in data monitored in real time.

[1095] "User emotion data" refers to data relating to the user's psychological state and emotions collected through voice input and facial recognition.

[1096] "Adjusting optimization content based on emotional data" is the process of analyzing collected user emotional data and changing the optimization content of delivery routes and transportation methods based on the results.

[1097] The logistics network optimization system according to the present invention selects and dynamically reoptimizes optimal delivery routes and transportation means by implementing the following multiple processes.

[1098] Data collection and analysis

[1099] Collection of traffic information

[1100] The server uses an external API (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads. The server calls the API every five minutes to collect new data such as road congestion, accident information, and construction information, and stores it in the database.

[1101] Weather data collection

[1102] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route. The server obtains weather information every hour and collects and stores data such as the weather, temperature, precipitation probability, and wind speed for each area.

[1103] Get delivery address business hours

[1104] The server references a database of destinations to obtain the acceptable business hours for each destination. The server queries the database once a day at night to update the business hours for each destination.

[1105] Collecting transportation cost and environmental impact data

[1106] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railway companies, or from an internal database. Once a month, the server calls the APIs of each service provider to obtain the latest pricing and environmental impact data.

[1107] Data preprocessing and using machine learning models

[1108] Data Preprocessing

[1109] The server runs the process of standardizing and normalizing the collected data and imputing missing values ​​using SQL scripts and ETL (Extract, Transform, Load) processes written in Python, for example, using the mean or median to impute missing values.

[1110] Input to the machine learning model

[1111] The server uses the preprocessed data to input into a machine learning model (for example, a TensorFlow or PyTorch model). The formatted data is passed to the AI ​​model in batches for inference. The machine learning model calculates the optimal delivery route and transportation method based on the given data.

[1112] User emotion recognition and analysis

[1113] Emotional Engine Activation

[1114] The server uses an emotion engine to collect emotion data through user voice input and facial recognition, and schedules a task to analyze the user's input data at regular intervals.

[1115] Sentiment analysis via voice input or facial recognition

[1116] The device uses a microphone and camera to analyze the user's emotions in real time. This includes analyzing the user's facial expressions and tone of voice using deep learning techniques. For example, if the user expresses dissatisfaction, emotional data will be collected.

[1117] Emotional Data Analysis

[1118] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, enabling flexible optimization that takes user emotions into account.

[1119] User notification and execution management

[1120] Generating and Receiving Notifications

[1121] The server generates messages to notify users based on the optimization results and the emotion engine's analysis results. Specifically, it generates and executes HTML emails and push notifications. The distribution manager's device receives the notifications sent from the server and displays them on the screen. Information is conveyed to users in real time using the smartphone's notification system or PC's desktop notification function.

[1122] Checking notification content

[1123] The user can then review the notification from the server and approve the optimized route and transportation suggestions. Specifically, the user can review the notification in depth and make fine adjustments as needed, for example, based on new requirements or conditions.

[1124] Real-time monitoring and dynamic re-optimization

[1125] Real-time data monitoring

[1126] The server continues to monitor real-time traffic and weather data during delivery, retrieving new data from the API every 10 minutes and updating the situation.

[1127] Performing dynamic reoptimization

[1128] The server then re-executes the AI ​​model based on real-time data and recalculates the optimization results according to changes in the situation. For example, if information about a sudden accident is received, a new route will be calculated immediately and the user will be notified of the new optimization results.

[1129] Re-notification and instruction adjustment

[1130] The server notifies the user terminal of the new optimization results and promptly notifies the user of the changes. The user can then check the re-notification and, if necessary, issue new instructions to the logistics company.

[1131] Prompt Sentence Examples

[1132] Traffic: "There's been an accident on a major road, causing congestion. It's also raining along my route. My delivery destination is open from 9 AM to 6 PM. Please suggest the most cost-effective route and transportation method."

[1133] In this way, the system of the present invention performs dynamic optimization taking into account various data and user emotions, thereby improving the efficiency of the logistics network and increasing user satisfaction.

[1134] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1135] Step 1: Collect data

[1136] The server uses external APIs to collect traffic information, weather data, delivery destination business hours, and transportation cost and environmental impact data. Specifically, the server obtains traffic information every five minutes from the Google Maps API and weather data every hour from the OpenWeatherMap API. Delivery destination business hours are obtained from the database once a day at night, and transportation cost and environmental impact data are collected once a month through the API. This collected data is stored in the database and used in the next step.

[1137] Input: Raw data obtained from API

[1138] Output: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[1139] Step 2: Data Preprocessing

[1140] The server formats the collected data and converts it into a format that can be input to the machine learning model. Specifically, it uses Python scripts to normalize the data (e.g., scaling the value range to 0-1) and impute missing values ​​(e.g., imputing missing values ​​with the mean). The preprocessed data is then prepared as input for the AI ​​model.

[1141] Input: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[1142] Output: Preprocessed data (normalized and imputed data)

[1143] Step 3: Input to the machine learning model

[1144] The server inputs the preprocessed data into a machine learning model. Specifically, the data is passed in batches to an AI model built using TensorFlow or PyTorch, which performs inference. The AI ​​model then calculates the optimal delivery route and transportation method.

[1145] Input: Preprocessed data

[1146] Output: Optimal delivery route and transportation means

[1147] Step 4: Collect and analyze emotion data

[1148] The device collects user emotional data using a camera and microphone. For example, it uses a deep learning model to analyze the user's facial expressions and voice tone captured by the camera in real time and extract emotional data. The extracted emotional data is then sent to a server.

[1149] Input: User's face image and voice input

[1150] Output: Emotion data (e.g., dissatisfied, satisfied, surprised)

[1151] Step 5: Adjust optimization based on sentiment data

[1152] The server analyzes the received emotional data and adjusts the optimization results based on the results. For example, if the user expresses dissatisfaction, it will run the AI ​​model again to calculate a different delivery route and transportation method, and generate a new optimization result.

[1153] Input: Sentiment data, initial results of optimal delivery routes and transportation methods

[1154] Output: Coordinated optimal delivery routes and modes

[1155] Step 6: Generate and send notifications

[1156] The server generates a notification message based on the optimization results and the emotion engine analysis results. Specifically, it generates an HTML email or push notification and sends it to the user's device.

[1157] Input: Optimization results, sentiment analysis results

[1158] Output: Notification messages (e.g., delivery route, transportation method, expected delivery time)

[1159] Step 7: Receive and confirm notifications

[1160] The device receives notification messages sent from the server and displays them on the screen. The user can then review the notification content and fine-tune their delivery plan as needed. For example, they can view optimized route and transportation suggestions in real time via push notifications on their smartphone or desktop notifications on their PC.

[1161] Input: Notification message

[1162] Output: User confirmation and approval

[1163] Step 8: Real-time monitoring and dynamic re-optimization

[1164] The server continues to monitor traffic and weather information in real time even during deliveries. When new data is acquired, the AI ​​model is reactivated as needed to recalculate the optimization results according to the situation. For example, if information about a sudden accident is received, a recalculated delivery route will be immediately proposed.

[1165] Input: Real-time data (traffic information, weather data)

[1166] Output: Recalculated optimal delivery route and means

[1167] Step 9: Re-notification and instruction adjustment

[1168] The server notifies the user terminal of the new optimization results and promptly notifies the user if new instructions are required. The user checks the re-notification and, if new instructions are required, issues new instructions to the logistics company.

[1169] Input: Recalculated optimization results

[1170] Output: Reminder message, user instruction adjustment

[1171] In this way, this system collects, analyzes, and optimizes data through each processing step, realizing flexible logistics management that also takes user emotions into consideration.

[1172] (Application example 2)

[1173] 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."

[1174] Conventional logistics network optimization systems have been able to optimize delivery routes based on traffic information, weather data, and transportation methods, but no systems have been able to flexibly respond by taking user emotions into account. As a result, they have been unable to adequately address the stress and dissatisfaction felt by users due to unforeseen circumstances. The present invention aims to provide a system that further improves user satisfaction by recognizing user emotions and dynamically re-optimizing delivery routes and transportation methods based on those emotions.

[1175] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1176] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the user of the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for recognizing user emotions and re-optimizing the delivery route and transportation means based on the emotion data. This enables more flexible and satisfying responses that take user emotions into consideration when optimizing a logistics network.

[1177] "Traffic information" refers to data about the current and predicted state of road traffic, such as road congestion, accident information, and construction information.

[1178] "Weather data" refers to meteorological information such as the current weather, temperature, probability of precipitation, and wind speed in areas along the delivery route.

[1179] "Delivery destination business hours" refers to the hours during which each delivery destination can receive packages.

[1180] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[1181] "Environmental Impact Data" means data showing the environmental impact, such as carbon dioxide emissions, associated with the use of a means of transportation.

[1182] The "optimal delivery route" refers to the most efficient route, taking into account factors such as traffic conditions, weather, opening hours at the delivery destination, transportation costs, and environmental impact.

[1183] "Means of transport" refers to the method of transporting goods, such as truck or rail.

[1184] "Recognizing user emotions" refers to detecting the user's emotional state through voice input or facial recognition.

[1185] "Emotion data" refers to data obtained as a result of emotion recognition of a user, and includes, for example, emotional states such as joy or stress.

[1186] "Dynamic re-optimization" refers to constantly recalculating the optimal route and transportation method based on real-time changes in traffic information, weather data, user sentiment, and other factors.

[1187] "Notifying" refers to conveying information about the selected delivery route and transportation means to the user and other relevant parties.

[1188] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on them.

[1189] Data collection

[1190] server

[1191] First, the server collects traffic information using an external API. This data includes road congestion, accident information, and construction information. Similarly, weather data is collected using a weather information API. This data includes information on the current weather along the delivery route, temperature, precipitation probability, wind speed, and other information. The server also obtains the business hours of delivery destinations through a database and API, confirming the times when each destination can accept packages. Furthermore, data on the cost and environmental impact of transportation methods is collected from the APIs of truck rental companies and railway companies.

[1192] Data analysis and optimal route selection

[1193] server

[1194] The server preprocesses this collected data and formats it so that it can be input into the AI ​​model. Specifically, it normalizes the data and fills in missing values. Using the formatted data, a machine learning model is used to calculate the optimal delivery route and means of transportation. For example, it can suggest routes that avoid traffic jams or safe routes in bad weather. The optimal route and means of transportation are extracted from the calculation results and compiled as the optimization results.

[1195] User emotion recognition and response

[1196] server

[1197] To recognize the user's emotions, an emotion engine installed on the server runs. This emotion engine collects emotion data through the user's voice input and facial recognition. For example, the user can use the camera on their smartphone to perform facial recognition.

[1198] Terminal

[1199] The user device, such as a smartphone or smart glasses, analyzes the user's emotions in real time using voice input and a camera, detecting when the user expresses dissatisfaction with a delivery delay.

[1200] server

[1201] The emotion engine analyzes the collected emotional data and adjusts the optimization results based on the results, re-proposing an alternative delivery route if the user expresses dissatisfaction.

[1202] User notification and execution management

[1203] server

[1204] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[1205] Terminal

[1206] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system of the smartphone or PC is used to notify the user in real time.

[1207] User

[1208] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1209] Real-time monitoring and dynamic re-optimization

[1210] server

[1211] While the delivery is in progress, the server continues to monitor real-time traffic and weather data. For example, it collects new traffic congestion information and weather changes as they occur. It then re-runs the AI ​​model based on the real-time data, dynamically recalculating the optimization results if the situation changes.

[1212] Terminal

[1213] The new optimization results are notified to the user terminal again, and any necessary changes are quickly notified.

[1214] User

[1215] The re-notification is checked, and if new instructions are required, new instructions are issued to the logistics company, who then carries out delivery using the proposed route.

[1216] As a specific example, while a logistics manager is patrolling a site wearing smart glasses, if a delivery route is predicted to be delayed due to traffic congestion, the camera built into the glasses detects the manager's anxious facial expression and collects emotional data using an emotion recognition API. Based on this data, the AI ​​model re-proposes a safe and quick alternative route and immediately notifies the smart glasses. An example of a prompt is, "When a logistics manager is wearing smart glasses and the delivery route is likely to be delayed due to traffic congestion, the camera detects an anxious facial expression. Please process this data using the emotion API, have the AI ​​model recalculate an alternative route, and generate code to notify the new route."

[1217] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1218] Step 1:

[1219] The server uses an external API to collect traffic information. The data obtained from this external API includes road congestion status, accident information, and construction information. The API endpoint is called as input, and the latest traffic information data is obtained as output. Specifically, the server sends an HTTP request and receives JSON format data as a response.

[1220] Step 2:

[1221] The server collects weather data using a weather information API. The data obtained from this API includes weather, temperature, precipitation probability, and wind speed. The API request parameters are set as input, and weather forecast data is obtained as output. Specifically, the server makes an API request with the set parameters and receives a response.

[1222] Step 3:

[1223] The server retrieves business hours information for each destination from the destination database. This includes the times when each destination can receive packages. The server queries the destination ID or address as input and retrieves the business hours data as output. Specifically, the server executes the database query and extracts the required information.

[1224] Step 4:

[1225] The server collects cost and environmental impact data (e.g., CO2 emissions) for transportation modes through the APIs of truck rental companies and railway companies. It specifies the API key and query parameters as input, and obtains the cost and environmental data for each transportation mode as output. Specific operations include sending an API request and analyzing the response data.

[1226] Step 5:

[1227] The server consolidates all collected data and performs preprocessing. This involves normalizing the data, filling in missing values, and formatting it for input into the AI ​​model. It uses all the raw data it acquires as input and creates a formatted dataset as output. Specifically, it uses a data frame processing library (e.g., Pandas) to format the data.

[1228] Step 6:

[1229] The server inputs the formatted data into a machine learning model to calculate the optimal delivery route and transportation method. It uses the preprocessed data as input and gets the optimal route proposal as output. Specifically, it inputs the data into a pre-trained AI model (e.g., a Scikit-learn or TensorFlow model) and gets the prediction results.

[1230] Step 7:

[1231] The server generates a notification message based on the optimization results. It uses the AI ​​model's prediction results and the user's emotional data as input, and creates a notification message to send to the user as output. Specifically, it uses a text generation algorithm to construct a message containing the necessary information.

[1232] Step 8:

[1233] The device receives notifications sent from the server and displays them to the user. It receives notification data from the server as input and displays a message on the user's screen as output. Specific operations involve using the notification function of the mobile app or web app.

[1234] Step 9:

[1235] The user checks the notification from the server and approves or modifies the optimized route and transportation proposal. The user checks the notification content displayed on the terminal as input and gives instructions for approval or modification as output. Specific actions include tapping a button on the user interface.

[1236] Step 10:

[1237] While the delivery is in progress, the server continuously monitors real-time traffic and weather data. It receives the latest API data as input and generates re-optimized results as output, making periodic API requests to collect and analyze new data.

[1238] Step 11:

[1239] The server then re-sends notifications to the user, if necessary, based on the results of the re-optimization. It uses the newly calculated optimal route as input and generates a re-notification message as output. Specifically, it re-executes the notification generation process described above.

[1240] Step 12:

[1241] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The user checks the content of the re-notification as input and issues instructions to the logistics company as output. The specific operation is to perform a new operation according to the use case.

[1242] 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.

[1243] 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.

[1244] 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.

[1245] [Third embodiment]

[1246] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1247] 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.

[1248] 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).

[1249] 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.

[1250] 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.

[1251] 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).

[1252] 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.

[1253] 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.

[1254] 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.

[1255] 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.

[1256] 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.

[1257] 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."

[1258] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. The operation of the system will be explained below based on a specific example embodiment.

[1259] Data collection

[1260] server

[1261] 1. Collection of traffic information

[1262] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[1263] 2. Weather data collection

[1264] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[1265] 3. Obtaining delivery address business hours

[1266] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[1267] 4. Collecting transportation cost and environmental impact data

[1268] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[1269] Data analysis and optimal route selection

[1270] server

[1271] 1. Data Preprocessing

[1272] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[1273] 2. Input to the AI ​​model

[1274] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[1275] 3. Extracting optimization results

[1276] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as the optimization results.

[1277] User notification and execution management

[1278] server

[1279] 1. Generate a notification

[1280] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[1281] Terminal

[1282] 1. Receiving notifications

[1283] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[1284] User

[1285] 1. Check the notification content

[1286] The delivery manager (user) checks the notification from the server and approves the proposed optimized route and transportation means.

[1287] Real-time monitoring and dynamic re-optimization

[1288] server

[1289] 1. Real-time data monitoring

[1290] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1291] 2. Dynamic Reoptimization

[1292] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[1293] Terminal

[1294] 1. Reminder

[1295] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[1296] User

[1297] 1. Reconfirmation and adjustment of instructions

[1298] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[1299] In this way, each component of this system, including the server, terminals, and users, works together to create an optimal logistics network based on the latest information, which can effectively resolve issues facing the entire logistics industry, such as reducing delivery delays, improving cost efficiency, and being environmentally conscious.

[1300] The processing flow will be explained below.

[1301] Step 1: Collect data

[1302] server

[1303] The server uses the Google Maps API to collect current traffic conditions and forecasts for major roads.

[1304] The server uses the Weather API to obtain current weather information and forecasts along the delivery route.

[1305] The server obtains business hours information for each delivery destination from the delivery destination database.

[1306] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and rail companies.

[1307] Step 2: Data Preprocessing

[1308] server

[1309] The server formats the collected data and prepares it in a format that can be input into the AI ​​model.

[1310] Specifically, it normalizes data, fills in missing values, and converts data types as necessary.

[1311] Step 3: Input to the AI ​​model

[1312] server

[1313] The server inputs the preprocessed data into a machine learning model and performs analysis.

[1314] Calculate optimal routes and modes of transport, taking into account traffic, weather, opening hours, transport costs and environmental impacts.

[1315] Step 4: Extracting optimization results

[1316] server

[1317] The optimal route and transportation method are extracted from the output of the AI ​​model.

[1318] This provides a detailed dispatch plan for optimization.

[1319] Step 5: Generate notifications

[1320] server

[1321] The server generates a message to notify the user based on the optimization result.

[1322] Specifically, it creates detailed information including the best route, transportation method, and estimated delivery time.

[1323] Step 6: Receive notifications

[1324] Terminal

[1325] The user device (smartphone or PC) receives the notification sent from the server and displays it on the screen.

[1326] Allow delivery managers to check notifications in real time.

[1327] Step 7: Review and approve the notification

[1328] User

[1329] The delivery manager reviews the notification displayed on the terminal and approves the optimized route and transportation proposal.

[1330] Tweak your delivery plan if necessary.

[1331] Step 8: Instructions for the carrier

[1332] User

[1333] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation information.

[1334] Specifically, instructions are sent to the supplier via the delivery management system.

[1335] Step 9: Monitor real-time data

[1336] server

[1337] The server continues to monitor traffic and weather data in real time while the delivery is in progress.

[1338] The database is updated as new information becomes available.

[1339] Step 10: Dynamic Reoptimization

[1340] server

[1341] The server then uses the AI ​​model again based on real-time data to dynamically perform optimization.

[1342] Depending on the situation, new optimal routes and means of transportation are recalculated.

[1343] Step 11: Snooze

[1344] server

[1345] If necessary, the new optimization results are notified to the user terminal.

[1346] Provides optimization information that responds to real-time fluctuations.

[1347] Step 12: Review and adjust instructions

[1348] User

[1349] The user checks the re-notification and issues new instructions to the delivery company if necessary.

[1350] The logistics company will then continue delivery using the proposed new route.

[1351] In this way, the server, terminals, and users work together to maintain an optimal logistics network based on the latest information, which reduces delivery delays, cuts costs, and is environmentally friendly.

[1352] Example 1

[1353] 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."

[1354] In current logistics networks, it is difficult to select the optimal delivery route and transportation method in real time, taking into account traffic information, weather data, delivery destination business hours, and the cost and environmental impact of transportation methods. Furthermore, collected data is not pre-processed sufficiently, and there is no mechanism for dynamic re-optimization when conditions change. This results in increased risks of delivery delays, increased costs, and negative environmental impacts, hindering efficient logistics.

[1355] 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.

[1356] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, and a means for acquiring business hours of delivery destinations. It also includes a means for collecting data on the cost and environmental impact of transportation means, a means for preprocessing the collected data, a means for selecting an optimal delivery route and transportation means using a machine learning model, a means for notifying the selected delivery route and transportation means, and a means for monitoring the data in real time and dynamically re-optimizing the data. This enables comprehensive analysis of various data and the provision of an optimal logistics network based on the latest information.

[1357] "Traffic information" refers to general information relating to vehicle traffic, such as road congestion, accident information, and construction information.

[1358] "Weather data" refers to general information about the weather, such as the weather in a particular area, temperature, probability of precipitation, wind speed, etc.

[1359] "Delivery destination business hours" refers to general information about the dates and times when each delivery destination can receive packages.

[1360] "Transportation costs" are the economic costs incurred to transport a load over a specific distance or weight.

[1361] "Environmental impact data" is information about the adverse environmental impacts, such as carbon dioxide emissions, caused by a particular mode of transportation.

[1362] "Preprocessing" is the process of formatting collected data, filling in missing values, and normalizing it to make it suitable for analysis or model input.

[1363] A "machine learning model" is an algorithm or computational method that learns patterns and knowledge through data analysis and makes predictions and classifications based on new data.

[1364] "Optimal delivery route and transportation mode selection" is the process of determining the most efficient and cost-effective delivery route and transportation mode by taking into account various data.

[1365] "Notifying" refers to the act of communicating the determined information or results to the user.

[1366] "Real-time monitoring" means continuously obtaining the latest data at the current time and immediately grasping changes in the situation.

[1367] "Dynamic re-optimization" is the process of recalculating and, if necessary, changing the optimal route or mode of transportation based on new information that becomes available in real time.

[1368] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time.

[1369] Data collection

[1370] server

[1371] The server utilizes several external APIs and databases to collect the following data:

[1372] 1. Collection of traffic information

[1373] The server uses the API of a traffic information service (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads, such as road congestion levels, accident information, and construction information.

[1374] 2. Weather data collection

[1375] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route, including local weather, temperature, chance of precipitation, wind speed, etc.

[1376] 3. Obtaining delivery address business hours

[1377] The server queries the database of delivery destinations to obtain the acceptable opening hours for each delivery destination, e.g., opening and closing times for stores.

[1378] 4. Collecting transportation cost and environmental impact data

[1379] The server collects cost and CO2 emissions data for each mode of transport from the APIs or internal databases of truck rental and rail companies, including the cost of delivering a certain distance and the carbon footprint of that mode of transport.

[1380] Data preprocessing and input to AI models

[1381] server

[1382] The collected data is first preprocessed. The server formats the data, imputes missing values, and normalizes it to prepare it in a format suitable for machine learning models. The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow) to calculate the optimal delivery route and transportation method. For example, it suggests routes that avoid traffic jams or safe routes in bad weather.

[1383] Notification of optimization results and execution management

[1384] server

[1385] Once the optimization results are obtained, the server generates a message to notify the user based on the results, including details such as the optimal route, transportation method, and estimated delivery time.

[1386] Terminal

[1387] The delivery manager's terminal receives the notification sent from the server and displays this information to the user in real time through the notification system.

[1388] User

[1389] The delivery manager checks the notification from the server and approves the proposed optimal route and transportation means, thereby carrying out the delivery work.

[1390] Real-time monitoring and dynamic re-optimization

[1391] server

[1392] While the delivery is in progress, the server continues to monitor traffic and weather data in real time. When new traffic congestion information or weather changes are collected, the server restarts the AI ​​model and re-optimizes it. The server then notifies the user again based on the new optimization results, promptly informing them of any necessary changes.

[1393] Terminal

[1394] The terminal receives new notifications and displays the necessary information to the user in real time.

[1395] User

[1396] The user confirms the re-notification and issues new instructions to the logistics company, who then carries out delivery using the proposed new route.

[1397] Specific examples

[1398] As a specific example, the following case can be mentioned.

[1399] Example: Optimizing delivery routes from Tokyo to Osaka. Collect data using a traffic information API, weather API, delivery destination business hours database, and truck rental API, and use a machine learning model to calculate the optimal route taking traffic congestion and weather into account.

[1400] Example prompt for a generative AI model:

[1401] "Calculate the optimal delivery route from Tokyo to Osaka. Recommend the best route and transportation method, taking into account traffic information, weather data, destination opening hours, truck rental costs and environmental impact."

[1402] In this way, the system of the present invention integrates and analyzes various types of data, and by always providing an optimal logistics network based on the latest information, it is possible to reduce delivery delays, improve cost efficiency, and be environmentally friendly.

[1403] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1404] Step 1: Collect data

[1405] server

[1406] The server uses multiple external APIs and databases to gather traffic information, weather data, delivery location opening hours, transportation costs, and environmental impact data. Specifically, it sends a "GET" request to retrieve the following data:

[1407] Input: A request containing an API key and query parameters

[1408] Output: Traffic information, weather data, business hours data, and transportation data in JSON format

[1409] Examples:

[1410] Traffic information: congestion, accident information, construction information

[1411] Weather data: weather, temperature, chance of precipitation, wind speed

[1412] Business hours: Opening and closing times for each delivery location

[1413] Cost and environmental impact data: shipping costs, CO2 emissions

[1414] Step 2: Data Preprocessing

[1415] server

[1416] The collected data is preprocessed and formatted so that it can be fed into a machine learning model. Specifically, missing values ​​are imputed and the data is normalized.

[1417] Input: JSON formatted collected data

[1418] Output: Preprocessed dataset

[1419] Examples:

[1420] Missing Value Imputation: Impute missing weather data with the mean value

[1421] Data normalization: Scaling numerical data such as traffic information or temperature to a range of 0 to 1

[1422] Step 3: Input to the AI ​​model

[1423] server

[1424] The preprocessed data is fed into a machine learning model to calculate the optimal delivery route and transportation method. A TensorFlow model is used.

[1425] Input: Preprocessed dataset

[1426] Output: Prediction results of the AI ​​model

[1427] Examples:

[1428] Suggesting routes to avoid traffic jams

[1429] Choosing a safe route in bad weather

[1430] Step 4: Extracting optimization results

[1431] server

[1432] The optimal route and mode of transport is extracted from the output of the AI ​​model and the results are shaped.

[1433] Input: AI model prediction results

[1434] Output: Optimal route and transportation details

[1435] Examples:

[1436] Optimal Route: Recommended route from origin to destination

[1437] Transportation: Preferred transportation method (truck or rail)

[1438] Step 5: Generate notifications

[1439] server

[1440] Based on the optimization results, a message is generated to notify the user.

[1441] Input: Best route and transportation details

[1442] Output: Information message

[1443] Examples:

[1444] Message content: Delivery schedule, route details, transportation method, estimated delivery time

[1445] Step 6: Receive and view notifications

[1446] Terminal

[1447] The delivery manager's terminal receives the notification sent from the server and displays it on the screen.

[1448] Input: Notification message sent by the server

[1449] Output: Notification displayed on the screen

[1450] Examples:

[1451] Use smartphone and PC notification systems to notify users in real time

[1452] Step 7: Review and approve the notification

[1453] User

[1454] The delivery manager checks the notification sent from the server and approves the proposed optimal route and transportation means.

[1455] Input: Notification message displayed on the screen

[1456] Output: Approval or correction instructions

[1457] Examples:

[1458] After checking on your smartphone or PC, press the approval button

[1459] Step 8: Monitor real-time data

[1460] server

[1461] Even while the delivery is in progress, traffic and weather data is monitored in real time to collect the latest information.

[1462] Input: Real-time data from API

[1463] Output: Updated traffic and weather data

[1464] Examples:

[1465] Timely acquisition of new traffic congestion information and weather change data

[1466] Step 9: Dynamic Reoptimization

[1467] server

[1468] The AI ​​model is reactivated based on real-time data and re-optimized according to changes in the situation.

[1469] Input: Updated traffic and weather data

[1470] Output: New optimal route and transportation details

[1471] Examples:

[1472] Proposing the best alternative route in the event of a sudden accident

[1473] Step 10: Generate and send a snooze notification

[1474] server

[1475] Based on the results of the re-optimization, a notification message is generated and sent to the user again.

[1476] Input: New best route and transportation details

[1477] Output: New notification message

[1478] Examples:

[1479] Clearly state the changes and notify users again

[1480] Step 11: Receive and view snooze notifications

[1481] Terminal

[1482] The delivery manager's terminal receives the new notification message and displays it on the screen.

[1483] Input: New notification message sent by the server

[1484] Output: The new notification displayed on the screen.

[1485] Examples:

[1486] Use smartphone or PC notification systems to notify users again in real time

[1487] Step 12: Review and adjust instructions

[1488] User

[1489] The delivery manager will review the new notification and issue new instructions to the logistics company if necessary.

[1490] Input: New notification displayed on screen

[1491] Output: Sending new instructions

[1492] Examples:

[1493] Instructing logistics companies to continue deliveries using new recommended routes

[1494] These steps ensure that the system always provides the most optimal logistics network based on up-to-date information, reducing delivery delays, improving cost efficiency, and being environmentally friendly.

[1495] (Application example 1)

[1496] 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."

[1497] In today's world, where efficiency and sustainability are required for logistics, it is necessary to select the optimal delivery route taking into account traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact. However, existing systems are unable to support dynamic optimization in real time, making it difficult to respond quickly to sudden traffic congestion or weather changes. In addition, there is a lack of concrete improvement measures to achieve efficient delivery at logistics centers.

[1498] 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.

[1499] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for calculating a delivery route in conjunction with the collected data and displaying the optimization result through an application installed on the transport robot. This makes it possible to select an optimal delivery route and transportation means in real time at a logistics center, thereby achieving efficient and sustainable delivery.

[1500] "Traffic information" refers to data related to traffic, such as road congestion, accidents, and construction work.

[1501] "Weather data" refers to various information related to weather, such as weather, temperature, precipitation, and wind speed.

[1502] "Business hours of delivery destination" refers to the opening and closing hours of the facility or store to which the logistics center delivers.

[1503] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[1504] "Environmental impact data" refers to data on the impact that a means of transportation has on the environment, specifically data on CO2 emissions, etc.

[1505] The "optimal delivery route" is the most efficient and economical delivery route calculated based on multiple conditions.

[1506] "Transportation" means the means (e.g., truck, rail, etc.) used to transport goods from a distribution center to a delivery destination.

[1507] A "notification" is a means by which a system communicates information to a user.

[1508] "Real-time data monitoring" means that the system continuously monitors data according to the current situation.

[1509] "Dynamic reoptimization" refers to the process by which the AI ​​model recalculates new optimal delivery routes and modes of transportation whenever conditions change.

[1510] An "application" is software designed to perform a specific task.

[1511] A "transport robot" is an automated mechanical device used in logistics centers to transport and organize cargo.

[1512] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system is realized through the cooperation of a server, terminals, and users.

[1513] Data collection

[1514] server:

[1515] 1. Traffic information collection:

[1516] The server uses external APIs to obtain traffic conditions and forecasts for major roads, specifically road congestion, accident information, and construction information.

[1517] 2. Weather data collection:

[1518] The server uses a weather information API to obtain weather information and forecasts for the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each region.

[1519] 3. Get delivery location business hours:

[1520] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[1521] 4. Collecting transportation cost and environmental impact data:

[1522] The server collects data on the cost and CO2 emissions of each transportation mode from the APIs or internal databases of truck rental companies and rail companies.

[1523] Data analysis and optimal route selection

[1524] server:

[1525] 1. Data Preprocessing:

[1526] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[1527] 2. Input to the AI ​​model:

[1528] The server uses machine learning models (such as TensorFlow) to calculate optimal delivery routes and transportation methods based on the preprocessed data, for example, proposing routes to avoid traffic jams or safe routes in bad weather.

[1529] 3. Extracting optimization results:

[1530] The server extracts the optimal route and transportation method from the output of the AI ​​model.

[1531] User notification and execution management

[1532] server:

[1533] 1. Generate notification:

[1534] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[1535] Device:

[1536] 1. Receiving notifications:

[1537] The delivery manager's device receives the notification sent from the server and displays it on the screen. For example, a notification system on a smartphone or PC can be used to notify the user in real time.

[1538] User:

[1539] 1. Check the notification:

[1540] The delivery manager checks the notification from the server and approves the proposal for the optimized route and transportation means.

[1541] Real-time monitoring and dynamic re-optimization

[1542] server:

[1543] 1. Real-time data monitoring:

[1544] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1545] 2. Dynamic reoptimization:

[1546] The server then reactivates the AI ​​model based on real-time data and dynamically recalculates the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, the server immediately suggests an optimal alternative route.

[1547] Device:

[1548] 1. Reminder:

[1549] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[1550] User:

[1551] 1. Review and adjust instructions:

[1552] The user checks the re-notification and issues new instructions to the distributor if new instructions are required.

[1553] In this way, optimization results can be displayed through an application installed on the delivery robots within the logistics center, enabling efficient delivery management in real time.

[1554] Specific processing examples

[1555] Road congestion and accident information obtained from the traffic information API is input into the AI ​​model to calculate the optimal route from the logistics center to a specific store.

[1556] In the event of a sudden change in weather or a new traffic accident, the information is reloaded in real time, and the AI ​​model is recalculated to present a new route.

[1557] Example prompt for a generative AI model:

[1558] "Can you calculate the optimal route from the logistics center to each delivery destination based on traffic, weather, and business information? Specifically, please suggest routes that avoid traffic jams and are safe in bad weather."

[1559] This will enable a significant improvement in delivery efficiency at logistics centers.

[1560] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1561] Step 1:

[1562] The server collects traffic information. Specifically, it uses an external API to obtain current and forecast traffic conditions for major roads. In this case, it sends an API request and receives data such as road congestion, accident information, and construction information. The input is the response data from the API, and the output is structured traffic information data.

[1563] Step 2:

[1564] The server collects weather data. It uses a weather information API to obtain weather information and forecasts for the delivery route. For example, it obtains data such as the weather, temperature, precipitation probability, and wind speed for each region via an API request and processes that information. The input is the response data from the API, and the output is structured weather information data.

[1565] Step 3:

[1566] The server retrieves the business hours of delivery destinations. It sends a query to the delivery destination database to retrieve the acceptable business hours for each delivery destination. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information from the database. The input is the response data from the database, and the output is structured business hours data.

[1567] Step 4:

[1568] The server collects data on the cost and environmental impact of transportation modes. It collects data such as the cost and CO2 emissions of each transportation mode from the APIs of truck rental companies and railway companies, or from an internal database. The input is the response data from the API or database, and the output is structured cost and environmental impact data.

[1569] Step 5:

[1570] The server preprocesses the collected data. Specifically, it normalizes the data, fills in missing values, and formats it so that it can be input into an AI model. The input is various collected data, and the output is a compiled dataset.

[1571] Step 6:

[1572] The server uses an AI model based on the preprocessed data to calculate the optimal delivery route and transportation method. Using machine learning libraries such as TensorFlow, the server inputs data into the model to make predictions. The input is the preprocessed dataset, and the output is a proposal for an optimized delivery route and transportation method.

[1573] Step 7:

[1574] The server generates a message to notify the user based on the optimization results. Specifically, it creates detailed information including the optimal route, transportation method, and expected delivery time, and prepares it to be sent to the user's device. The input is the output data of the AI ​​model, and the output is the notification message.

[1575] Step 8:

[1576] The device receives notifications sent from the server and displays them on the screen. For example, it notifies the user in real time using the notification system of a smartphone or PC. The input is the notification message from the server, and the output is the notification displayed on the device.

[1577] Step 9:

[1578] The user checks the notification from the server and approves the proposed optimized route and transportation means. The input is the notification content displayed on the terminal, and the output is the user's approval action.

[1579] Step 10:

[1580] The server monitors traffic and weather data in real time while the delivery is in progress. New traffic congestion information and weather change data are collected as they arrive and updated within the system. The input is real-time data, and the output is updated status data.

[1581] Step 11:

[1582] The server then runs the AI ​​model again based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, it will immediately suggest an optimal alternative route. The input is updated real-time data, and the output is the recalculated optimal route.

[1583] Step 12:

[1584] The server re-notifies the user terminal of the new optimization results and promptly notifies them of any necessary changes. The input is the recalculated optimal route, and the output is the re-notification message.

[1585] Step 13:

[1586] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The input is the re-notification message and the output is the user's new instructions.

[1587] Through the above steps, efficient and sustainable delivery management can be achieved using applications installed on delivery robots within logistics centers.

[1588] 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.

[1589] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, delivery destination business hours, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on those emotions. The operation of this system will be explained below based on a specific example of the system.

[1590] Data collection

[1591] server

[1592] 1. Collection of traffic information

[1593] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[1594] 2. Weather data collection

[1595] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[1596] 3. Obtaining delivery address business hours

[1597] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[1598] 4. Collecting transportation cost and environmental impact data

[1599] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[1600] Data analysis and optimal route selection

[1601] server

[1602] 1. Data Preprocessing

[1603] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[1604] 2. Input to the AI ​​model

[1605] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[1606] 3. Extracting optimization results

[1607] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as optimization results.

[1608] User emotion recognition and response

[1609] server

[1610] 1. Emotional Engine Activation

[1611] The emotion engine installed on the server collects emotion data through user voice input and facial recognition. For example, a user sets up a scene where facial recognition is performed using a smartphone camera.

[1612] Terminal

[1613] 1. Emotion analysis via voice input or facial recognition

[1614] The user device uses voice input and a camera to analyze the user's emotions in real time, for example, detecting when the user expresses dissatisfaction with a delivery delay.

[1615] server

[1616] 1. Emotional Data Analysis

[1617] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, for example, re-proposing a different delivery route if the user expresses dissatisfaction.

[1618] User notification and execution management

[1619] server

[1620] 1. Generate a notification

[1621] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[1622] Terminal

[1623] 1. Receiving notifications

[1624] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[1625] User

[1626] 1. Check the notification content

[1627] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1628] Real-time monitoring and dynamic re-optimization

[1629] server

[1630] 1. Real-time data monitoring

[1631] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1632] 2. Dynamic Reoptimization

[1633] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[1634] Terminal

[1635] 1. Reminder

[1636] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[1637] User

[1638] 1. Reconfirmation and adjustment of instructions

[1639] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[1640] In this way, the server, terminals, users, and emotion engine work together to create a logistics network that is always the most efficient and satisfies users, thereby reducing delivery delays, cutting costs, being environmentally friendly, and improving customer satisfaction.

[1641] The processing flow will be explained below.

[1642] Step 1: Collect data

[1643] server

[1644] The server uses the Google Maps API to collect current and forecast traffic conditions on major roads, specifically traffic flow, congestion information, and accident information.

[1645] The server uses the Weather API to collect current weather information along the delivery route, specifically the weather, temperature, precipitation probability, wind speed, etc. for each area.

[1646] The server retrieves the acceptable business hours of each delivery destination from the delivery destination database, for example, the business hours and holiday information of each store.

[1647] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and railroad companies, specifically, the costs and environmental impact data of each transportation method.

[1648] Step 2: Data Preprocessing

[1649] server

[1650] The server prepares the collected data in a format suitable for analysis, for example by filling in missing data and standardizing the data format.

[1651] Normalize and scale the data to prepare it for input into the AI ​​model.

[1652] Step 3: Input to the AI ​​model

[1653] server

[1654] The server inputs the pre-processed data into an AI model for real-time analysis, using machine learning algorithms to calculate the optimal delivery route and transportation method.

[1655] Step 4: Extracting optimization results

[1656] server

[1657] The server extracts the optimization results obtained from the AI ​​model, such as the optimal route and means of transportation.

[1658] The optimization results are compiled as a delivery plan.

[1659] Step 5: Collecting emotion data

[1660] Terminal

[1661] The user device collects the user's emotions using voice input or a camera, for example, by the user speaking into a smartphone or pointing their face at the device's camera.

[1662] Step 6: Analyze the sentiment data

[1663] server

[1664] The emotion engine installed on the server analyzes the collected emotion data, for example, analyzing voice data to determine whether the user is angry or happy.

[1665] Step 7: Emotional Adjustment

[1666] server

[1667] The server adjusts the optimization results based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, it will re-propose a different delivery route.

[1668] Step 8: Generate notifications

[1669] server

[1670] The server generates a message based on the optimization and sentiment analysis results, creating a notification that includes detailed information such as the delivery route, transportation method, and estimated delivery time.

[1671] Step 9: Receive notifications

[1672] Terminal

[1673] The user device receives the notification sent from the server and displays it on the screen. For example, the notification system of a smartphone or PC is used to notify the user in real time.

[1674] Step 10: Review and approve the notification

[1675] User

[1676] The delivery manager (user) checks the notification displayed on the terminal, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1677] Step 11: Instructions for the carrier

[1678] User

[1679] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation method information. Specifically, the instructions are notified to the company through the delivery management system.

[1680] Step 12: Monitor real-time data

[1681] server

[1682] The server monitors traffic and weather information in real time while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1683] Step 13: Dynamic Reoptimization

[1684] server

[1685] The server then uses the AI ​​model to dynamically optimize the route and transportation method based on real-time data, and if conditions change, it recalculates the optimal route and transportation method.

[1686] Step 14: Snooze

[1687] server

[1688] The server notifies the user terminal of the new optimization results, providing a new delivery plan that responds to real-time fluctuations.

[1689] Step 15: Review and adjust instructions

[1690] User

[1691] The user can then review the re-notification and issue new instructions to the delivery company if necessary, and the delivery company will then continue delivery using the proposed new route.

[1692] In this way, the server, terminals, users, and emotion engine work together to create the most efficient logistics network possible, which always provides the highest level of user satisfaction. This reduces delivery delays, cuts costs, contributes to environmental friendliness, and improves customer satisfaction.

[1693] Example 2

[1694] 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."

[1695] Conventional logistics network systems face the problem of difficult integrated control of multiple data sources, as they individually manage and analyze traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact data. Dynamic real-time re-optimization and adjustment of optimization content based on user emotion recognition are also difficult, resulting in reduced customer satisfaction and efficiency. Furthermore, data preprocessing and the use of machine learning models are difficult to implement, increasing the system's complexity and making implementation difficult.

[1696] 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.

[1697] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, a means for acquiring business hours of delivery destinations, and a means for collecting data on transportation costs and environmental impacts. This allows for a means for selecting an optimal delivery route and transportation means based on the collected data, which in turn includes a means for analyzing data using a machine learning model, a means for notifying the user of the selected delivery route and transportation means, a means for monitoring the data in real time and dynamically re-optimizing the data, and a means for collecting and analyzing user emotion data and adjusting the optimization content based on the data. This allows for integrated control of various data sources, dynamic optimization in real time, and flexible optimization based on user emotion, thereby improving the efficiency of the logistics network and customer satisfaction.

[1698] "Traffic information" refers to data on the current state and forecast of road traffic, such as road congestion, accident information, and construction information.

[1699] "Weather data" refers to data relating to weather conditions, such as the weather, temperature, probability of precipitation, and wind speed, for a particular area.

[1700] "Delivery destination business hours" is information about the hours during which a specific delivery destination can accept packages.

[1701] "Cost of transportation" refers to data on the fees and expenses incurred when using a particular transportation method.

[1702] "Environmental impact data" refers to data on the environmental impact, such as CO2 emissions, that occurs when a particular means of transportation is used.

[1703] A "machine learning model" is an algorithm or framework for analyzing data and making predictions or classifications based on that data.

[1704] "Preprocessing means" refers to the process of standardizing and normalizing collected data, filling in missing values, and otherwise preparing the data in an analyzable format.

[1705] "Dynamic reoptimization" is the process of recalculating and updating optimal delivery routes and modes of transportation in response to changes in data monitored in real time.

[1706] "User emotion data" refers to data relating to the user's psychological state and emotions collected through voice input and facial recognition.

[1707] "Adjusting optimization content based on emotional data" is the process of analyzing collected user emotional data and changing the optimization content of delivery routes and transportation methods based on the results.

[1708] The logistics network optimization system according to the present invention selects and dynamically reoptimizes optimal delivery routes and transportation means by implementing the following multiple processes.

[1709] Data collection and analysis

[1710] Collection of traffic information

[1711] The server uses an external API (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads. The server calls the API every five minutes to collect new data such as road congestion, accident information, and construction information, and stores it in the database.

[1712] Weather data collection

[1713] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route. The server obtains weather information every hour and collects and stores data such as the weather, temperature, precipitation probability, and wind speed for each area.

[1714] Get delivery address business hours

[1715] The server references a database of destinations to obtain the acceptable business hours for each destination. The server queries the database once a day at night to update the business hours for each destination.

[1716] Collecting transportation cost and environmental impact data

[1717] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railway companies, or from an internal database. Once a month, the server calls the APIs of each service provider to obtain the latest pricing and environmental impact data.

[1718] Data preprocessing and using machine learning models

[1719] Data Preprocessing

[1720] The server runs the process of standardizing and normalizing the collected data and imputing missing values ​​using SQL scripts and ETL (Extract, Transform, Load) processes written in Python, for example, using the mean or median to impute missing values.

[1721] Input to the machine learning model

[1722] The server uses the preprocessed data to input into a machine learning model (for example, a TensorFlow or PyTorch model). The formatted data is passed to the AI ​​model in batches for inference. The machine learning model calculates the optimal delivery route and transportation method based on the given data.

[1723] User emotion recognition and analysis

[1724] Emotional Engine Activation

[1725] The server uses an emotion engine to collect emotion data through user voice input and facial recognition, and schedules a task to analyze the user's input data at regular intervals.

[1726] Sentiment analysis via voice input or facial recognition

[1727] The device uses a microphone and camera to analyze the user's emotions in real time. This includes analyzing the user's facial expressions and tone of voice using deep learning techniques. For example, if the user expresses dissatisfaction, emotional data will be collected.

[1728] Emotional Data Analysis

[1729] The server uses an emotion engine to analyze the collected emotion data and adjust the optimization results based on the results, enabling flexible optimization that takes user emotions into account.

[1730] User notification and execution management

[1731] Generating and Receiving Notifications

[1732] The server generates messages to notify users based on the optimization results and the emotion engine's analysis results. Specifically, it generates and executes HTML emails and push notifications. The distribution manager's device receives the notifications sent from the server and displays them on the screen. Information is conveyed to users in real time using the smartphone's notification system or PC's desktop notification function.

[1733] Checking notification content

[1734] The user can then review the notification from the server and approve the optimized route and transportation suggestions. Specifically, the user can review the notification in depth and make fine adjustments as needed, for example, based on new requirements or conditions.

[1735] Real-time monitoring and dynamic re-optimization

[1736] Real-time data monitoring

[1737] The server continues to monitor real-time traffic and weather data during delivery, retrieving new data from the API every 10 minutes and updating the situation.

[1738] Performing dynamic reoptimization

[1739] The server then re-executes the AI ​​model based on real-time data and recalculates the optimization results according to changes in the situation. For example, if information about a sudden accident is received, a new route will be calculated immediately and the user will be notified of the new optimization results.

[1740] Re-notification and instruction adjustment

[1741] The server notifies the user terminal of the new optimization results and promptly notifies the user of the changes. The user can then check the re-notification and, if necessary, issue new instructions to the logistics company.

[1742] Prompt Sentence Examples

[1743] Traffic: "There's been an accident on a major road, causing congestion. It's also raining along my route. My delivery destination is open from 9 AM to 6 PM. Please suggest the most cost-effective route and transportation method."

[1744] In this way, the system of the present invention performs dynamic optimization taking into account various data and user emotions, thereby improving the efficiency of the logistics network and increasing user satisfaction.

[1745] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1746] Step 1: Collect data

[1747] The server uses external APIs to collect traffic information, weather data, delivery destination business hours, and transportation cost and environmental impact data. Specifically, the server obtains traffic information every five minutes from the Google Maps API and weather data every hour from the OpenWeatherMap API. Delivery destination business hours are obtained from the database once a day at night, and transportation cost and environmental impact data are collected once a month through the API. This collected data is stored in the database and used in the next step.

[1748] Input: Raw data obtained from API

[1749] Output: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[1750] Step 2: Data Preprocessing

[1751] The server formats the collected data and converts it into a format that can be input to the machine learning model. Specifically, it uses Python scripts to normalize the data (e.g., scaling the value range to 0-1) and impute missing values ​​(e.g., imputing missing values ​​with the mean). The preprocessed data is then prepared as input for the AI ​​model.

[1752] Input: Formatted data (traffic information, weather data, delivery location opening hours, transportation costs and environmental impact data)

[1753] Output: Preprocessed data (normalized and imputed data)

[1754] Step 3: Input to the machine learning model

[1755] The server inputs the preprocessed data into a machine learning model. Specifically, the data is passed in batches to an AI model built using TensorFlow or PyTorch, which performs inference. The AI ​​model then calculates the optimal delivery route and transportation method.

[1756] Input: Preprocessed data

[1757] Output: Optimal delivery route and transportation means

[1758] Step 4: Collect and analyze emotion data

[1759] The device collects user emotional data using a camera and microphone. For example, it uses a deep learning model to analyze the user's facial expressions and voice tone captured by the camera in real time and extract emotional data. The extracted emotional data is then sent to a server.

[1760] Input: User's face image and voice input

[1761] Output: Emotion data (e.g., dissatisfied, satisfied, surprised)

[1762] Step 5: Adjust optimization based on sentiment data

[1763] The server analyzes the received emotional data and adjusts the optimization results based on the results. For example, if the user expresses dissatisfaction, it will run the AI ​​model again to calculate a different delivery route and transportation method, and generate a new optimization result.

[1764] Input: Sentiment data, initial results of optimal delivery routes and transportation methods

[1765] Output: Coordinated optimal delivery routes and modes

[1766] Step 6: Generate and send notifications

[1767] The server generates a notification message based on the optimization results and the emotion engine analysis results. Specifically, it generates an HTML email or push notification and sends it to the user's device.

[1768] Input: Optimization results, sentiment analysis results

[1769] Output: Notification messages (e.g., delivery route, transportation method, expected delivery time)

[1770] Step 7: Receive and confirm notifications

[1771] The device receives notification messages sent from the server and displays them on the screen. The user can then review the notification content and fine-tune their delivery plan as needed. For example, they can view optimized route and transportation suggestions in real time via push notifications on their smartphone or desktop notifications on their PC.

[1772] Input: Notification message

[1773] Output: User confirmation and approval

[1774] Step 8: Real-time monitoring and dynamic re-optimization

[1775] The server continues to monitor traffic and weather information in real time even during deliveries. When new data is acquired, the AI ​​model is reactivated as needed to recalculate the optimization results according to the situation. For example, if information about a sudden accident is received, a recalculated delivery route will be immediately proposed.

[1776] Input: Real-time data (traffic information, weather data)

[1777] Output: Recalculated optimal delivery route and means

[1778] Step 9: Re-notification and instruction adjustment

[1779] The server notifies the user terminal of the new optimization results and promptly notifies the user if new instructions are required. The user checks the re-notification and, if new instructions are required, issues new instructions to the logistics company.

[1780] Input: Recalculated optimization results

[1781] Output: Reminder message, user instruction adjustment

[1782] In this way, this system collects, analyzes, and optimizes data through each processing step, realizing flexible logistics management that also takes user emotions into consideration.

[1783] (Application example 2)

[1784] 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."

[1785] Conventional logistics network optimization systems have been able to optimize delivery routes based on traffic information, weather data, and transportation methods, but no systems have been able to flexibly respond by taking user emotions into account. As a result, they have been unable to adequately address the stress and dissatisfaction felt by users due to unforeseen circumstances. The present invention aims to provide a system that further improves user satisfaction by recognizing user emotions and dynamically re-optimizing delivery routes and transportation methods based on those emotions.

[1786] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1787] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the user of the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for recognizing user emotions and re-optimizing the delivery route and transportation means based on the emotion data. This enables more flexible and satisfying responses that take user emotions into consideration when optimizing a logistics network.

[1788] "Traffic information" refers to data about the current and predicted state of road traffic, such as road congestion, accident information, and construction information.

[1789] "Weather data" refers to meteorological information such as the current weather, temperature, probability of precipitation, and wind speed in areas along the delivery route.

[1790] "Delivery destination business hours" refers to the hours during which each delivery destination can receive packages.

[1791] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[1792] "Environmental Impact Data" means data showing the environmental impact, such as carbon dioxide emissions, associated with the use of a means of transportation.

[1793] The "optimal delivery route" refers to the most efficient route, taking into account factors such as traffic conditions, weather, opening hours at the delivery destination, transportation costs, and environmental impact.

[1794] "Means of transport" refers to the method of transporting goods, such as truck or rail.

[1795] "Recognizing user emotions" refers to detecting the user's emotional state through voice input or facial recognition.

[1796] "Emotion data" refers to data obtained as a result of emotion recognition of a user, and includes, for example, emotional states such as joy or stress.

[1797] "Dynamic re-optimization" refers to constantly recalculating the optimal route and transportation method based on real-time changes in traffic information, weather data, user sentiment, and other factors.

[1798] "Notifying" refers to conveying information about the selected delivery route and transportation means to the user and other relevant parties.

[1799] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on them.

[1800] Data collection

[1801] server

[1802] First, the server collects traffic information using an external API. This data includes road congestion, accident information, and construction information. Similarly, weather data is collected using a weather information API. This data includes information on the current weather along the delivery route, temperature, precipitation probability, wind speed, and other information. The server also obtains the business hours of delivery destinations through a database and API, confirming the times when each destination can accept packages. Furthermore, data on the cost and environmental impact of transportation methods is collected from the APIs of truck rental companies and railway companies.

[1803] Data analysis and optimal route selection

[1804] server

[1805] The server preprocesses this collected data and formats it so that it can be input into the AI ​​model. Specifically, it normalizes the data and fills in missing values. Using the formatted data, a machine learning model is used to calculate the optimal delivery route and means of transportation. For example, it can suggest routes that avoid traffic jams or safe routes in bad weather. The optimal route and means of transportation are extracted from the calculation results and compiled as the optimization results.

[1806] User emotion recognition and response

[1807] server

[1808] To recognize the user's emotions, an emotion engine installed on the server runs. This emotion engine collects emotion data through the user's voice input and facial recognition. For example, the user can use the camera on their smartphone to perform facial recognition.

[1809] Terminal

[1810] The user device, such as a smartphone or smart glasses, analyzes the user's emotions in real time using voice input and a camera, detecting when the user expresses dissatisfaction with a delivery delay.

[1811] server

[1812] The emotion engine analyzes the collected emotional data and adjusts the optimization results based on the results, re-proposing an alternative delivery route if the user expresses dissatisfaction.

[1813] User notification and execution management

[1814] server

[1815] The server generates a message to notify the user based on the optimization results and the emotion engine analysis results, including detailed information such as the optimal route, transportation method, and estimated delivery time.

[1816] Terminal

[1817] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system of the smartphone or PC is used to notify the user in real time.

[1818] User

[1819] The delivery manager (user) checks the notification from the server, approves the optimized route and transportation proposal, and fine-tunes the delivery plan as necessary.

[1820] Real-time monitoring and dynamic re-optimization

[1821] server

[1822] While the delivery is in progress, the server continues to monitor real-time traffic and weather data. For example, it collects new traffic congestion information and weather changes as they occur. It then re-runs the AI ​​model based on the real-time data, dynamically recalculating the optimization results if the situation changes.

[1823] Terminal

[1824] The new optimization results are notified to the user terminal again, and any necessary changes are quickly notified.

[1825] User

[1826] The re-notification is checked, and if new instructions are required, new instructions are issued to the logistics company, who then carries out delivery using the proposed route.

[1827] As a specific example, while a logistics manager is patrolling a site wearing smart glasses, if a delivery route is predicted to be delayed due to traffic congestion, the camera built into the glasses detects the manager's anxious facial expression and collects emotional data using an emotion recognition API. Based on this data, the AI ​​model re-proposes a safe and quick alternative route and immediately notifies the smart glasses. An example of a prompt is, "When a logistics manager is wearing smart glasses and the delivery route is likely to be delayed due to traffic congestion, the camera detects an anxious facial expression. Please process this data using the emotion API, have the AI ​​model recalculate an alternative route, and generate code to notify the new route."

[1828] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1829] Step 1:

[1830] The server uses an external API to collect traffic information. The data obtained from this external API includes road congestion status, accident information, and construction information. The API endpoint is called as input, and the latest traffic information data is obtained as output. Specifically, the server sends an HTTP request and receives JSON format data as a response.

[1831] Step 2:

[1832] The server collects weather data using a weather information API. The data obtained from this API includes weather, temperature, precipitation probability, and wind speed. The API request parameters are set as input, and weather forecast data is obtained as output. Specifically, the server makes an API request with the set parameters and receives a response.

[1833] Step 3:

[1834] The server retrieves business hours information for each destination from the destination database. This includes the times when each destination can receive packages. The server queries the destination ID or address as input and retrieves the business hours data as output. Specifically, the server executes the database query and extracts the required information.

[1835] Step 4:

[1836] The server collects cost and environmental impact data (e.g., CO2 emissions) for transportation modes through the APIs of truck rental companies and railway companies. It specifies the API key and query parameters as input, and obtains the cost and environmental data for each transportation mode as output. Specific operations include sending an API request and analyzing the response data.

[1837] Step 5:

[1838] The server consolidates all collected data and performs preprocessing. This involves normalizing the data, filling in missing values, and formatting it for input into the AI ​​model. It uses all the raw data it acquires as input and creates a formatted dataset as output. Specifically, it uses a data frame processing library (e.g., Pandas) to format the data.

[1839] Step 6:

[1840] The server inputs the formatted data into a machine learning model to calculate the optimal delivery route and transportation method. It uses the preprocessed data as input and gets the optimal route proposal as output. Specifically, it inputs the data into a pre-trained AI model (e.g., a Scikit-learn or TensorFlow model) and gets the prediction results.

[1841] Step 7:

[1842] The server generates a notification message based on the optimization results. It uses the AI ​​model's prediction results and the user's emotional data as input, and creates a notification message to send to the user as output. Specifically, it uses a text generation algorithm to construct a message containing the necessary information.

[1843] Step 8:

[1844] The device receives notifications sent from the server and displays them to the user. It receives notification data from the server as input and displays a message on the user's screen as output. Specific operations involve using the notification function of the mobile app or web app.

[1845] Step 9:

[1846] The user checks the notification from the server and approves or modifies the optimized route and transportation proposal. The user checks the notification content displayed on the terminal as input and gives instructions for approval or modification as output. Specific actions include tapping a button on the user interface.

[1847] Step 10:

[1848] While the delivery is in progress, the server continuously monitors real-time traffic and weather data. It receives the latest API data as input and generates re-optimized results as output, making periodic API requests to collect and analyze new data.

[1849] Step 11:

[1850] The server then re-sends notifications to the user, if necessary, based on the results of the re-optimization. It uses the newly calculated optimal route as input and generates a re-notification message as output. Specifically, it re-executes the notification generation process described above.

[1851] Step 12:

[1852] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The user checks the content of the re-notification as input and issues instructions to the logistics company as output. The specific operation is to perform a new operation according to the use case.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] [Fourth embodiment]

[1857] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1858] 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.

[1859] 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).

[1860] 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.

[1861] 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.

[1862] 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).

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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."

[1870] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. The operation of the system will be explained below based on a specific example embodiment.

[1871] Data collection

[1872] server

[1873] 1. Collection of traffic information

[1874] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[1875] 2. Weather data collection

[1876] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[1877] 3. Obtaining delivery address business hours

[1878] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[1879] 4. Collecting transportation cost and environmental impact data

[1880] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[1881] Data analysis and optimal route selection

[1882] server

[1883] 1. Data Preprocessing

[1884] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[1885] 2. Input to the AI ​​model

[1886] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[1887] 3. Extracting optimization results

[1888] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as the optimization results.

[1889] User notification and execution management

[1890] server

[1891] 1. Generate a notification

[1892] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[1893] Terminal

[1894] 1. Receiving notifications

[1895] The delivery manager's device receives the notification sent from the server and displays it on the screen. The notification system on the smartphone or PC is used to notify the user in real time.

[1896] User

[1897] 1. Check the notification content

[1898] The delivery manager (user) checks the notification from the server and approves the proposed optimized route and transportation means.

[1899] Real-time monitoring and dynamic re-optimization

[1900] server

[1901] 1. Real-time data monitoring

[1902] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[1903] 2. Dynamic Reoptimization

[1904] The server then re-executes the AI ​​model based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if a sudden accident occurs, the server immediately suggests an optimal alternative route.

[1905] Terminal

[1906] 1. Reminder

[1907] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[1908] User

[1909] 1. Reconfirmation and adjustment of instructions

[1910] The user checks the re-notification and, if new instructions are required, issues new instructions to the distributor, who then carries out delivery using the proposed route.

[1911] In this way, each component of this system, including the server, terminals, and users, works together to create an optimal logistics network based on the latest information, which can effectively resolve issues facing the entire logistics industry, such as reducing delivery delays, improving cost efficiency, and being environmentally conscious.

[1912] The processing flow will be explained below.

[1913] Step 1: Collect data

[1914] server

[1915] The server uses the Google Maps API to collect current traffic conditions and forecasts for major roads.

[1916] The server uses the Weather API to obtain current weather information and forecasts along the delivery route.

[1917] The server obtains business hours information for each delivery destination from the delivery destination database.

[1918] The server collects data on the cost and CO2 emissions of each transportation method from the APIs or internal databases of truck rental companies and rail companies.

[1919] Step 2: Data Preprocessing

[1920] server

[1921] The server formats the collected data and prepares it in a format that can be input into the AI ​​model.

[1922] Specifically, it normalizes data, fills in missing values, and converts data types as necessary.

[1923] Step 3: Input to the AI ​​model

[1924] server

[1925] The server inputs the preprocessed data into a machine learning model and performs analysis.

[1926] Calculate optimal routes and modes of transport, taking into account traffic, weather, opening hours, transport costs and environmental impacts.

[1927] Step 4: Extracting optimization results

[1928] server

[1929] The optimal route and transportation method are extracted from the output of the AI ​​model.

[1930] This provides a detailed dispatch plan for optimization.

[1931] Step 5: Generate notifications

[1932] server

[1933] The server generates a message to notify the user based on the optimization result.

[1934] Specifically, it creates detailed information including the best route, transportation method, and estimated delivery time.

[1935] Step 6: Receive notifications

[1936] Terminal

[1937] The user device (smartphone or PC) receives the notification sent from the server and displays it on the screen.

[1938] Allow delivery managers to check notifications in real time.

[1939] Step 7: Review and approve the notification

[1940] User

[1941] The delivery manager reviews the notification displayed on the terminal and approves the optimized route and transportation proposal.

[1942] Tweak your delivery plan if necessary.

[1943] Step 8: Instructions for the carrier

[1944] User

[1945] The delivery manager issues instructions to the delivery company based on the approved optimized route and transportation information.

[1946] Specifically, instructions are sent to the supplier via the delivery management system.

[1947] Step 9: Monitor real-time data

[1948] server

[1949] The server continues to monitor traffic and weather data in real time while the delivery is in progress.

[1950] The database is updated as new information becomes available.

[1951] Step 10: Dynamic Reoptimization

[1952] server

[1953] The server then uses the AI ​​model again based on real-time data to dynamically perform optimization.

[1954] Depending on the situation, new optimal routes and means of transportation are recalculated.

[1955] Step 11: Snooze

[1956] server

[1957] If necessary, the new optimization results are notified to the user terminal.

[1958] Provides optimization information that responds to real-time fluctuations.

[1959] Step 12: Review and adjust instructions

[1960] User

[1961] The user checks the re-notification and issues new instructions to the delivery company if necessary.

[1962] The logistics company will then continue delivery using the proposed new route.

[1963] In this way, the server, terminals, and users work together to maintain an optimal logistics network based on the latest information, which reduces delivery delays, cuts costs, and is environmentally friendly.

[1964] Example 1

[1965] 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."

[1966] In current logistics networks, it is difficult to select the optimal delivery route and transportation method in real time, taking into account traffic information, weather data, delivery destination business hours, and the cost and environmental impact of transportation methods. Furthermore, collected data is not pre-processed sufficiently, and there is no mechanism for dynamic re-optimization when conditions change. This results in increased risks of delivery delays, increased costs, and negative environmental impacts, hindering efficient logistics.

[1967] 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.

[1968] In this invention, the server includes a means for collecting traffic information, a means for collecting weather data, and a means for acquiring business hours of delivery destinations. It also includes a means for collecting data on the cost and environmental impact of transportation means, a means for preprocessing the collected data, a means for selecting an optimal delivery route and transportation means using a machine learning model, a means for notifying the selected delivery route and transportation means, and a means for monitoring the data in real time and dynamically re-optimizing the data. This enables comprehensive analysis of various data and the provision of an optimal logistics network based on the latest information.

[1969] "Traffic information" refers to general information relating to vehicle traffic, such as road congestion, accident information, and construction information.

[1970] "Weather data" refers to general information about the weather, such as the weather in a particular area, temperature, probability of precipitation, wind speed, etc.

[1971] "Delivery destination business hours" refers to general information about the dates and times when each delivery destination can receive packages.

[1972] "Transportation costs" are the economic costs incurred to transport a load over a specific distance or weight.

[1973] "Environmental impact data" is information about the adverse environmental impacts, such as carbon dioxide emissions, caused by a particular mode of transportation.

[1974] "Preprocessing" is the process of formatting collected data, filling in missing values, and normalizing it to make it suitable for analysis or model input.

[1975] A "machine learning model" is an algorithm or computational method that learns patterns and knowledge through data analysis and makes predictions and classifications based on new data.

[1976] "Optimal delivery route and transportation mode selection" is the process of determining the most efficient and cost-effective delivery route and transportation mode by taking into account various data.

[1977] "Notifying" refers to the act of communicating the determined information or results to the user.

[1978] "Real-time monitoring" means continuously obtaining the latest data at the current time and immediately grasping changes in the situation.

[1979] "Dynamic re-optimization" is the process of recalculating and, if necessary, changing the optimal route or mode of transportation based on new information that becomes available in real time.

[1980] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time.

[1981] Data collection

[1982] server

[1983] The server utilizes several external APIs and databases to collect the following data:

[1984] 1. Collection of traffic information

[1985] The server uses the API of a traffic information service (e.g., Google Maps API) to obtain current traffic conditions and forecast data for major roads, such as road congestion levels, accident information, and construction information.

[1986] 2. Weather data collection

[1987] The server uses a weather information API (e.g., OpenWeatherMap API) to obtain current weather information and forecasts along the delivery route, including local weather, temperature, chance of precipitation, wind speed, etc.

[1988] 3. Obtaining delivery address business hours

[1989] The server queries the database of delivery destinations to obtain the acceptable opening hours for each delivery destination, e.g., opening and closing times for stores.

[1990] 4. Collecting transportation cost and environmental impact data

[1991] The server collects cost and CO2 emissions data for each mode of transport from the APIs or internal databases of truck rental and rail companies, including the cost of delivering a certain distance and the carbon footprint of that mode of transport.

[1992] Data preprocessing and input to AI models

[1993] server

[1994] The collected data is first preprocessed. The server formats the data, imputes missing values, and normalizes it to prepare it in a format suitable for machine learning models. The server then inputs the preprocessed data into a machine learning model (e.g., TensorFlow) to calculate the optimal delivery route and transportation method. For example, it suggests routes that avoid traffic jams or safe routes in bad weather.

[1995] Notification of optimization results and execution management

[1996] server

[1997] Once the optimization results are obtained, the server generates a message to notify the user based on the results, including details such as the optimal route, transportation method, and estimated delivery time.

[1998] Terminal

[1999] The delivery manager's terminal receives the notification sent from the server and displays this information to the user in real time through the notification system.

[2000] User

[2001] The delivery manager checks the notification from the server and approves the proposed optimal route and transportation means, thereby carrying out the delivery work.

[2002] Real-time monitoring and dynamic re-optimization

[2003] server

[2004] While the delivery is in progress, the server continues to monitor traffic and weather data in real time. When new traffic congestion information or weather changes are collected, the server restarts the AI ​​model and re-optimizes it. The server then notifies the user again based on the new optimization results, promptly informing them of any necessary changes.

[2005] Terminal

[2006] The terminal receives new notifications and displays the necessary information to the user in real time.

[2007] User

[2008] The user confirms the re-notification and issues new instructions to the logistics company, who then carries out delivery using the proposed new route.

[2009] Specific examples

[2010] As a specific example, the following case can be mentioned.

[2011] Example: Optimizing delivery routes from Tokyo to Osaka. Collect data using a traffic information API, weather API, delivery destination business hours database, and truck rental API, and use a machine learning model to calculate the optimal route taking traffic congestion and weather into account.

[2012] Example prompt for a generative AI model:

[2013] "Calculate the optimal delivery route from Tokyo to Osaka. Recommend the best route and transportation method, taking into account traffic information, weather data, destination opening hours, truck rental costs and environmental impact."

[2014] In this way, the system of the present invention integrates and analyzes various types of data, and by always providing an optimal logistics network based on the latest information, it is possible to reduce delivery delays, improve cost efficiency, and be environmentally friendly.

[2015] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2016] Step 1: Collect data

[2017] server

[2018] The server uses multiple external APIs and databases to gather traffic information, weather data, delivery location opening hours, transportation costs, and environmental impact data. Specifically, it sends a "GET" request to retrieve the following data:

[2019] Input: A request containing an API key and query parameters

[2020] Output: Traffic information, weather data, business hours data, and transportation data in JSON format

[2021] Examples:

[2022] Traffic information: congestion, accident information, construction information

[2023] Weather data: weather, temperature, chance of precipitation, wind speed

[2024] Business hours: Opening and closing times for each delivery location

[2025] Cost and environmental impact data: shipping costs, CO2 emissions

[2026] Step 2: Data Preprocessing

[2027] server

[2028] The collected data is preprocessed and formatted so that it can be fed into a machine learning model. Specifically, missing values ​​are imputed and the data is normalized.

[2029] Input: JSON formatted collected data

[2030] Output: Preprocessed dataset

[2031] Examples:

[2032] Missing Value Imputation: Impute missing weather data with the mean value

[2033] Data normalization: Scaling numerical data such as traffic information or temperature to a range of 0 to 1

[2034] Step 3: Input to the AI ​​model

[2035] server

[2036] The preprocessed data is fed into a machine learning model to calculate the optimal delivery route and transportation method. A TensorFlow model is used.

[2037] Input: Preprocessed dataset

[2038] Output: Prediction results of the AI ​​model

[2039] Examples:

[2040] Suggesting routes to avoid traffic jams

[2041] Choosing a safe route in bad weather

[2042] Step 4: Extracting optimization results

[2043] server

[2044] The optimal route and mode of transport is extracted from the output of the AI ​​model and the results are shaped.

[2045] Input: AI model prediction results

[2046] Output: Optimal route and transportation details

[2047] Examples:

[2048] Optimal Route: Recommended route from origin to destination

[2049] Transportation: Preferred transportation method (truck or rail)

[2050] Step 5: Generate notifications

[2051] server

[2052] Based on the optimization results, a message is generated to notify the user.

[2053] Input: Best route and transportation details

[2054] Output: Information message

[2055] Examples:

[2056] Message content: Delivery schedule, route details, transportation method, estimated delivery time

[2057] Step 6: Receive and view notifications

[2058] Terminal

[2059] The delivery manager's terminal receives the notification sent from the server and displays it on the screen.

[2060] Input: Notification message sent by the server

[2061] Output: Notification displayed on the screen

[2062] Examples:

[2063] Use smartphone and PC notification systems to notify users in real time

[2064] Step 7: Review and approve the notification

[2065] User

[2066] The delivery manager checks the notification sent from the server and approves the proposed optimal route and transportation means.

[2067] Input: Notification message displayed on the screen

[2068] Output: Approval or correction instructions

[2069] Examples:

[2070] After checking on your smartphone or PC, press the approval button

[2071] Step 8: Monitor real-time data

[2072] server

[2073] Even while the delivery is in progress, traffic and weather data is monitored in real time to collect the latest information.

[2074] Input: Real-time data from API

[2075] Output: Updated traffic and weather data

[2076] Examples:

[2077] Timely acquisition of new traffic congestion information and weather change data

[2078] Step 9: Dynamic Reoptimization

[2079] server

[2080] The AI ​​model is reactivated based on real-time data and re-optimized according to changes in the situation.

[2081] Input: Updated traffic and weather data

[2082] Output: New optimal route and transportation details

[2083] Examples:

[2084] Proposing the best alternative route in the event of a sudden accident

[2085] Step 10: Generate and send a snooze notification

[2086] server

[2087] Based on the results of the re-optimization, a notification message is generated and sent to the user again.

[2088] Input: New best route and transportation details

[2089] Output: New notification message

[2090] Examples:

[2091] Clearly state the changes and notify users again

[2092] Step 11: Receive and view snooze notifications

[2093] Terminal

[2094] The delivery manager's terminal receives the new notification message and displays it on the screen.

[2095] Input: New notification message sent by the server

[2096] Output: The new notification displayed on the screen.

[2097] Examples:

[2098] Use smartphone or PC notification systems to notify users again in real time

[2099] Step 12: Review and adjust instructions

[2100] User

[2101] The delivery manager will review the new notification and issue new instructions to the logistics company if necessary.

[2102] Input: New notification displayed on screen

[2103] Output: Sending new instructions

[2104] Examples:

[2105] Instructing logistics companies to continue deliveries using new recommended routes

[2106] These steps ensure that the system always provides the most optimal logistics network based on up-to-date information, reducing delivery delays, improving cost efficiency, and being environmentally friendly.

[2107] (Application example 1)

[2108] 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."

[2109] In today's world, where efficiency and sustainability are required for logistics, it is necessary to select the optimal delivery route taking into account traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact. However, existing systems are unable to support dynamic optimization in real time, making it difficult to respond quickly to sudden traffic congestion or weather changes. In addition, there is a lack of concrete improvement measures to achieve efficient delivery at logistics centers.

[2110] 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.

[2111] In this invention, the server includes means for collecting traffic information, means for collecting weather data, means for acquiring business hours of delivery destinations, means for collecting data on the cost and environmental impact of transportation means, means for selecting an optimal delivery route and transportation means based on the collected data, means for notifying the selected delivery route and transportation means, means for monitoring the data in real time and dynamically re-optimizing, and means for calculating a delivery route in conjunction with the collected data and displaying the optimization result through an application installed on the transport robot. This makes it possible to select an optimal delivery route and transportation means in real time at a logistics center, thereby achieving efficient and sustainable delivery.

[2112] "Traffic information" refers to data related to traffic, such as road congestion, accidents, and construction work.

[2113] "Weather data" refers to various information related to weather, such as weather, temperature, precipitation, and wind speed.

[2114] "Business hours of delivery destination" refers to the opening and closing hours of the facility or store to which the logistics center delivers.

[2115] "Transportation costs" refers to the costs incurred in using a particular transportation method.

[2116] "Environmental impact data" refers to data on the impact that a means of transportation has on the environment, specifically data on CO2 emissions, etc.

[2117] The "optimal delivery route" is the most efficient and economical delivery route calculated based on multiple conditions.

[2118] "Transportation" means the means (e.g., truck, rail, etc.) used to transport goods from a distribution center to a delivery destination.

[2119] A "notification" is a means by which a system communicates information to a user.

[2120] "Real-time data monitoring" means that the system continuously monitors data according to the current situation.

[2121] "Dynamic reoptimization" refers to the process by which the AI ​​model recalculates new optimal delivery routes and modes of transportation whenever conditions change.

[2122] An "application" is software designed to perform a specific task.

[2123] A "transport robot" is an automated mechanical device used in logistics centers to transport and organize cargo.

[2124] The logistics network optimization system of the present invention is a system that selects the optimal delivery route and transportation means based on traffic information, weather data, business hours of delivery destinations, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system is realized through the cooperation of a server, terminals, and users.

[2125] Data collection

[2126] server:

[2127] 1. Traffic information collection:

[2128] The server uses external APIs to obtain traffic conditions and forecasts for major roads, specifically road congestion, accident information, and construction information.

[2129] 2. Weather data collection:

[2130] The server uses a weather information API to obtain weather information and forecasts for the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each region.

[2131] 3. Get delivery location business hours:

[2132] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[2133] 4. Collecting transportation cost and environmental impact data:

[2134] The server collects data on the cost and CO2 emissions of each transportation mode from the APIs or internal databases of truck rental companies and rail companies.

[2135] Data analysis and optimal route selection

[2136] server:

[2137] 1. Data Preprocessing:

[2138] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[2139] 2. Input to the AI ​​model:

[2140] The server uses machine learning models (such as TensorFlow) to calculate optimal delivery routes and transportation methods based on the preprocessed data, for example, proposing routes to avoid traffic jams or safe routes in bad weather.

[2141] 3. Extracting optimization results:

[2142] The server extracts the optimal route and transportation method from the output of the AI ​​model.

[2143] User notification and execution management

[2144] server:

[2145] 1. Generate notification:

[2146] The server generates a message to notify the user based on the optimization results, including detailed information such as the optimal route, transportation means, and estimated delivery time.

[2147] Device:

[2148] 1. Receiving notifications:

[2149] The delivery manager's device receives the notification sent from the server and displays it on the screen. For example, a notification system on a smartphone or PC can be used to notify the user in real time.

[2150] User:

[2151] 1. Check the notification:

[2152] The delivery manager checks the notification from the server and approves the proposal for the optimized route and transportation means.

[2153] Real-time monitoring and dynamic re-optimization

[2154] server:

[2155] 1. Real-time data monitoring:

[2156] The server continues to monitor real-time traffic and weather data while the delivery is in progress, collecting new traffic congestion information and weather changes as they occur.

[2157] 2. Dynamic reoptimization:

[2158] The server then reactivates the AI ​​model based on real-time data and dynamically recalculates the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, the server immediately suggests an optimal alternative route.

[2159] Device:

[2160] 1. Reminder:

[2161] The server notifies the user terminal of the new optimization results and promptly notifies the user of any necessary changes.

[2162] User:

[2163] 1. Review and adjust instructions:

[2164] The user checks the re-notification and issues new instructions to the distributor if new instructions are required.

[2165] In this way, optimization results can be displayed through an application installed on the delivery robots within the logistics center, enabling efficient delivery management in real time.

[2166] Specific processing examples

[2167] Road congestion and accident information obtained from the traffic information API is input into the AI ​​model to calculate the optimal route from the logistics center to a specific store.

[2168] In the event of a sudden change in weather or a new traffic accident, the information is reloaded in real time, and the AI ​​model is recalculated to present a new route.

[2169] Example prompt for a generative AI model:

[2170] "Can you calculate the optimal route from the logistics center to each delivery destination based on traffic, weather, and business information? Specifically, please suggest routes that avoid traffic jams and are safe in bad weather."

[2171] This will enable a significant improvement in delivery efficiency at logistics centers.

[2172] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2173] Step 1:

[2174] The server collects traffic information. Specifically, it uses an external API to obtain current and forecast traffic conditions for major roads. In this case, it sends an API request and receives data such as road congestion, accident information, and construction information. The input is the response data from the API, and the output is structured traffic information data.

[2175] Step 2:

[2176] The server collects weather data. It uses a weather information API to obtain weather information and forecasts for the delivery route. For example, it obtains data such as the weather, temperature, precipitation probability, and wind speed for each region via an API request and processes that information. The input is the response data from the API, and the output is structured weather information data.

[2177] Step 3:

[2178] The server retrieves the business hours of delivery destinations. It sends a query to the delivery destination database to retrieve the acceptable business hours for each delivery destination. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information from the database. The input is the response data from the database, and the output is structured business hours data.

[2179] Step 4:

[2180] The server collects data on the cost and environmental impact of transportation modes. It collects data such as the cost and CO2 emissions of each transportation mode from the APIs of truck rental companies and railway companies, or from an internal database. The input is the response data from the API or database, and the output is structured cost and environmental impact data.

[2181] Step 5:

[2182] The server preprocesses the collected data. Specifically, it normalizes the data, fills in missing values, and formats it so that it can be input into an AI model. The input is various collected data, and the output is a compiled dataset.

[2183] Step 6:

[2184] The server uses an AI model based on the preprocessed data to calculate the optimal delivery route and transportation method. Using machine learning libraries such as TensorFlow, the server inputs data into the model to make predictions. The input is the preprocessed dataset, and the output is a proposal for an optimized delivery route and transportation method.

[2185] Step 7:

[2186] The server generates a message to notify the user based on the optimization results. Specifically, it creates detailed information including the optimal route, transportation method, and expected delivery time, and prepares it to be sent to the user's device. The input is the output data of the AI ​​model, and the output is the notification message.

[2187] Step 8:

[2188] The device receives notifications sent from the server and displays them on the screen. For example, it notifies the user in real time using the notification system of a smartphone or PC. The input is the notification message from the server, and the output is the notification displayed on the device.

[2189] Step 9:

[2190] The user checks the notification from the server and approves the proposed optimized route and transportation means. The input is the notification content displayed on the terminal, and the output is the user's approval action.

[2191] Step 10:

[2192] The server monitors traffic and weather data in real time while the delivery is in progress. New traffic congestion information and weather change data are collected as they arrive and updated within the system. The input is real-time data, and the output is updated status data.

[2193] Step 11:

[2194] The server then runs the AI ​​model again based on real-time data, dynamically recalculating the optimization results if the situation changes. For example, if an unexpected accident occurs along a delivery route, it will immediately suggest an optimal alternative route. The input is updated real-time data, and the output is the recalculated optimal route.

[2195] Step 12:

[2196] The server re-notifies the user terminal of the new optimization results and promptly notifies them of any necessary changes. The input is the recalculated optimal route, and the output is the re-notification message.

[2197] Step 13:

[2198] The user checks the re-notification and issues new instructions to the logistics company if new instructions are required. The input is the re-notification message and the output is the user's new instructions.

[2199] Through the above steps, efficient and sustainable delivery management can be achieved using applications installed on delivery robots within logistics centers.

[2200] 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.

[2201] The logistics network optimization system of the present invention selects the optimal delivery route and transportation means based on traffic information, weather data, delivery destination business hours, transportation means costs, and environmental impact data, and dynamically optimizes them in real time. This system incorporates an emotion engine that recognizes user emotions and adjusts the optimization content based on those emotions. The operation of this system will be explained below based on a specific example of the system.

[2202] Data collection

[2203] server

[2204] 1. Collection of traffic information

[2205] The server uses an external API (traffic information service) to obtain current and forecast traffic conditions for major roads, such as road congestion levels, accident information, and construction information.

[2206] 2. Weather data collection

[2207] The server uses a weather information API to obtain current weather information and forecasts along the delivery route, such as the weather, temperature, precipitation probability, and wind speed for each area.

[2208] 3. Obtaining delivery address business hours

[2209] The server retrieves the acceptable business hours information for each delivery destination from the delivery destination database. For example, if a store is open from 9:00 AM to 6:00 PM on weekdays, it retrieves that information.

[2210] 4. Collecting transportation cost and environmental impact data

[2211] The server collects data on the cost and CO2 emissions of each transportation method from the APIs of truck rental companies and railroad companies or from internal databases, such as the cost of delivering a certain distance and the carbon dioxide emissions generated by that transportation method.

[2212] Data analysis and optimal route selection

[2213] server

[2214] 1. Data Preprocessing

[2215] The server formats the collected data so that it can be input into the AI ​​model, normalizing the data and filling in missing values.

[2216] 2. Input to the AI ​​model

[2217] The server uses machine learning models to calculate optimal delivery routes and transportation methods based on the pre-processed data, for example, suggesting routes that avoid traffic jams or safe routes in bad weather.

[2218] 3. Extracting optimization results

[2219] The server extracts the optimal route and transportation method from the output of the AI ​​model and compiles them as optimization results.

[2220] User emotion recognition and response

[2221] server

[2222] 1. Emotional Engine Activation

[2223] The emotion engine installed on the server collects emotion data through user voice input and facial recognition. F...

Claims

1. a means for collecting traffic information; a means for collecting weather data; A means for obtaining the business hours of the delivery destination; a means of collecting transportation cost and environmental impact data; A means for selecting an optimal delivery route and transportation means based on the collected data; a means of informing you of the selected delivery route and mode of transport; means for monitoring and dynamically re-optimizing said data in real time; A system including:

2. 10. The system of claim 1, The system wherein the means for collecting traffic information, weather data, delivery destination business hours, transportation costs, and environmental impact data includes means for utilizing an external database or API.

3. 10. The system of claim 1, A system in which the means for selecting optimal delivery routes and modes of transportation includes means for analyzing data using machine learning models.

Images