System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting traffic information; means for collecting weather information; means for collecting business hours information of a delivery destination; means for collecting data related to a transportation means; means for training an artificial intelligence model using pre-processed data; means for receiving real-time data and immediately reflecting the real-time data to the artificial intelligence model; and means for suggesting an optimal delivery route and transportation means.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 recent years, the logistics industry has faced a variety of challenges due to the rapid growth of e-commerce. The logistics crisis predicted for 2024 includes sudden increases in demand, supply shortages, and delays and increased costs due to uncertainties. In particular, the complex interplay of factors such as fluctuating traffic information, weather conditions, delivery destination business hours, and transportation methods makes it difficult to optimize using traditional manual methods. This could lead to serious problems such as delivery delays, decreased customer satisfaction, and increased costs. Therefore, there is a need to solve these issues and achieve logistics efficiency and cost reduction. [Means for solving the problem]

[0005] The present invention is a logistics network optimization system that collects traffic information, weather information, delivery destination business hours, transportation mode data, and other data and utilizes an AI model. The system includes the following means: a means for collecting traffic information, a means for collecting weather information, a means for collecting delivery destination business hours, a means for collecting transportation mode data, a means for training an AI model using preprocessed data, a means for receiving real-time data and immediately reflecting it in the AI ​​model, and a means for proposing optimal delivery routes and transportation modes. The system further includes a means for calculating the optimal delivery route from the preprocessed data, a means for selecting the optimal transportation mode, a means for assessing environmental impact, and a means for assessing delivery costs, thereby simultaneously considering these complex factors and achieving continuous optimization of the logistics network. The system also includes a means for collecting user feedback data and using it to retrain the AI ​​model, thereby continuously improving accuracy and providing optimal logistics solutions.

[0006] An "AI model" is an artificial intelligence algorithm that learns from massive amounts of data and makes predictions and classifications according to specific purposes.

[0007] "Traffic information" refers to information that mainly refers to real-time conditions on the roads, such as road conditions, traffic congestion, and accident information.

[0008] "Weather information" refers to information about current and forecasted weather and meteorological conditions. Examples include the probability of precipitation, wind speed, and temperature.

[0009] "Business hours information of delivery destination" is information about the hours during which each delivery destination can receive the item.

[0010] "Transportation data" refers to information about the attributes of various transportation modes, such as trucks, ships, and trains, including their costs, operating times, and environmental impacts.

[0011] "Preprocessing" refers to the process of converting raw data into an analyzable format. Examples include data normalization and missing value imputation.

[0012] "Real-time data" is data that instantly reflects events and situations occurring at the present time.

[0013] "Feedback data" is information provided by users after using the system, and is useful for subsequent improvements and adjustments.

[0014] "Optimization" is the process of finding the best possible solution for a specific goal (e.g., reducing delivery time or cost). [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 present invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize a logistics network. This system is implemented as follows.

[0037] System Configuration

[0038] 1. Data Collection Module

[0039] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[0040] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours at each delivery destination, and operational and cost information for trucks, trains, and ships.

[0041] 2. Data Preprocessing Module

[0042] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0043] 3. AI model training module

[0044] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[0045] Past logistics data is also used in the training to optimize various parameters.

[0046] 4. Real-time data update module

[0047] The device sends the latest traffic and weather information to the server in real time.

[0048] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[0049] 5. Optimization Algorithm Module

[0050] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[0051] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[0052] 6. Notification Module

[0053] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[0054] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[0055] 7. Feedback Collection Module

[0056] The user provides feedback on the actual delivery results and problems to the server via the terminal.

[0057] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes" or "delays occur during certain times of the day."

[0058] 8. AI model retraining module

[0059] The server uses the collected feedback data to retrain the AI ​​model, which continuously improves the model's predictive accuracy and helps with future deliveries.

[0060] Specific examples

[0061] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[0062] 1. Data Collection:

[0063] The server collects weather and traffic information from various APIs. For example, it checks that "traffic congestion is predicted due to heavy rain on Expressway Section A."

[0064] 2. Data Preprocessing:

[0065] The server formats the collected data, imputes missing values, and normalizes it as needed.

[0066] 3. Training the AI ​​model:

[0067] The server trains the AI ​​model using past logistics data and newly collected data.

[0068] 4. Run the optimization algorithm:

[0069] The server uses trained AI models to calculate optimal delivery routes and modes of transport, for example, choosing detours when heavy rain is forecast and even suggesting a combination of rail and truck transport.

[0070] 5. Notice:

[0071] The server notifies the user of the calculation results and instructs the user on the optimal delivery method.

[0072] 6. Feedback:

[0073] Once completed, the user reports the delivery results from their device to the server, which uses the results as data to improve the accuracy of the AI ​​model.

[0074] The above is an embodiment of the logistics network information optimization system based on the present invention. This system utilizes real-time data to constantly maintain an optimal logistics network and achieve efficient delivery.

[0075] The processing flow will be explained below.

[0076] Step 1:

[0077] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[0078] Step 2:

[0079] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[0080] Step 3:

[0081] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[0082] Step 4:

[0083] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[0084] Step 5:

[0085] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[0086] Step 6:

[0087] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[0088] Step 7:

[0089] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[0090] Step 8:

[0091] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[0092] Step 9:

[0093] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[0094] Step 10:

[0095] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[0096] Step 11:

[0097] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[0098] Step 12:

[0099] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[0100] Step 13:

[0101] The server uses the collected feedback data to retrain the AI ​​model, improving its prediction accuracy for future deliveries.

[0102] This is the specific processing flow of the AI-based logistics network information optimization system. By using this system, an optimized logistics network can be maintained at all times, enabling efficient and fast delivery.

[0103] Example 1

[0104] 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."

[0105] In the logistics industry, it is important to appropriately collect information on traffic conditions, weather, delivery destination business hours, and transportation methods, and to select the optimal delivery route and transportation method based on this data. However, it is difficult to reflect this data in real time and operate it efficiently. Furthermore, there is a lack of a mechanism to collect user feedback and continuously improve the model, which means that delivery efficiency and cost optimization cannot be fully achieved.

[0106] 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.

[0107] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation methods, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for receiving real-time data and immediately reflecting it in the AI ​​model, means for proposing an optimal delivery route and transportation method, means for notifying the user of the optimized delivery route and transportation method, means for collecting feedback data from users, and means for retraining the AI ​​model using the feedback data. This allows for traffic conditions, weather, and business hours of delivery destinations to be reflected in real time, making it possible to always select the optimal delivery route and transportation method. Furthermore, the model can be continuously improved using user feedback, thereby achieving logistics efficiency and cost reduction.

[0108] "Traffic information" refers to data related to traffic movement, such as road congestion, traffic jam information, and accident information.

[0109] "Weather information" refers to weather-related data such as weather forecasts, precipitation, wind speed, and temperature.

[0110] "Delivery destination business hours information" refers to data relating to the hours during which the delivery destination facility is open.

[0111] "Data on transportation means" refers to data on transportation means used in logistics, such as the operating status and operating costs of trucks, trains, ships, etc.

[0112] "Preprocessing" refers to the process of normalizing collected data, filling in missing values, and converting it into a format that is easy for an AI model to learn.

[0113] An "artificial intelligence model" is a model that uses machine learning to make predictions and classifications from data.

[0114] "Real-time data" refers to data that is collected immediately to reflect ongoing situations or events.

[0115] The "optimal delivery route" is the most efficient delivery route selected to improve logistics efficiency.

[0116] The "optimal means of transportation" refers to the most efficient and effective transportation method selected to improve logistics efficiency.

[0117] "Users" refer to delivery drivers and logistics managers who use the system to carry out delivery tasks.

[0118] "Feedback Data" refers to data provided by a user to report actual delivery results or problems.

[0119] This invention is a system that collects data on traffic information, weather information, business hours of delivery destinations, and transportation methods, and optimizes a logistics network using an AI model. The system includes a server, a terminal, and a user.

[0120] Hardware and software used

[0121] The server handles data collection, preprocessing, AI model training, real-time updates, optimization algorithm execution, notifications, feedback collection, and AI model retraining. Specific software used is the Python Requests library for data collection, Pandas for data preprocessing, and TensorFlow and PyTorch for AI model training.

[0122] The device is used to send real-time traffic and weather information to a server. For example, a delivery driver's smartphone or tablet sends GPS data and traffic information to the server.

[0123] The user receives suggestions from the system for optimal delivery routes and transportation methods, and then performs the actual delivery. After completing the delivery, the user provides feedback to the server via their terminal.

[0124] Specific examples

[0125] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[0126] The server collects data from traffic information APIs (e.g., Google Maps API) and weather information APIs (e.g., OpenWeatherMap API). The server periodically sends requests to these API endpoints and analyzes the JSON data received as a response. For example, it verifies that "traffic congestion is predicted due to heavy rain on section A of the highway."

[0127] The server preprocesses the collected data using the Pandas library, filling in missing weather information with data from the previous day and normalizing all numerical data to the same scale.

[0128] The server then uses the preprocessed data to train an AI model using TensorFlow or PyTorch. For example, it creates a model that predicts the optimal route for trucks based on past logistics data. The server improves prediction accuracy by training the model using both past data and newly collected data.

[0129] The device then sends the latest traffic and weather information to the server in real time. The delivery driver's smartphone then sends their current location and traffic congestion information to the server, and the server immediately updates the AI ​​model with the received real-time data, updating the forecast.

[0130] The server uses a trained AI model to calculate the optimal delivery route and transportation method, and notifies the user's device. For example, it provides specific instructions such as "If heavy rain is predicted, select a detour route and suggest using both rail and truck."

[0131] After completing the delivery, the user reports the delivery result to the server from their device, which serves as feedback data. The server uses the collected feedback data to retrain the AI ​​model, thereby continuously improving the model's prediction accuracy.

[0132] Prompt Sentence Examples

[0133] "Please suggest the best delivery route to the Kansai region."

[0134] "Please tell me the delivery route in bad weather."

[0135] In this way, the system utilizes real-time data to maintain an optimal logistics network at all times.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] Data collection

[0139] The server collects information from traffic information APIs, weather information APIs, customer databases, etc. Specifically, the server periodically sends requests to API endpoints and analyzes the JSON data received as a response.

[0140] Input: Traffic API, Weather API, Data from customer database

[0141] Output: Analyzed traffic, weather, delivery opening hours, and transportation data

[0142] Step 2:

[0143] Data Preprocessing

[0144] The server preprocesses the collected data, for example, by imputing missing data and normalizing numerical data. It uses the Python Pandas library to format the data and impute missing values.

[0145] Input: Parsed data

[0146] Output: Preprocessed data

[0147] Step 3:

[0148] Training an AI model

[0149] The server uses the preprocessed data to train an AI model, specifically by building a neural network using TensorFlow or PyTorch, inputting the data, and optimizing the model.

[0150] Input: Preprocessed data

[0151] Output: A trained AI model

[0152] Step 4:

[0153] Real-time data updates

[0154] The device sends real-time traffic and weather information to the server. For example, a delivery driver's mobile device uses GPS data to send current location and traffic information to the server.

[0155] Input: Real-time traffic and weather information

[0156] Output: Real-time data sent to the server

[0157] Step 5:

[0158] Running the optimization algorithm

[0159] The server uses the latest data to optimize delivery routes and transportation methods, using Python's Scipy library and other optimization libraries to solve complex optimization problems.

[0160] Input: Real-time data and pre-trained AI models

[0161] Output: Optimal delivery route and transportation method suggestions

[0162] Step 6:

[0163] notification

[0164] The server notifies the user's device of the optimal delivery route and transportation method, specifically by sending a pop-up notification or email to the delivery driver or logistics manager.

[0165] Input: Optimal delivery route and transportation suggestions

[0166] Output: User notification

[0167] Step 7:

[0168] Collecting feedback

[0169] Users can report actual delivery results and problems to the server via their devices, specifically by reporting problems using a mobile app or web interface.

[0170] Input: Actual delivery results and issues

[0171] Output: Feedback data sent to the server

[0172] Step 8:

[0173] Retraining AI models

[0174] The server uses the collected feedback data to retrain the AI ​​model, retraining it with new data and comparing it with the previous model to evaluate its accuracy.

[0175] Input: Feedback data

[0176] Output: Retrained AI model

[0177] (Application example 1)

[0178] 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."

[0179] In recent years, the logistics industry has become increasingly difficult to create efficient delivery plans due to a wide variety of delivery destinations and variable factors such as weather and traffic conditions. Conventional methods make it difficult to update information in real time and select optimal delivery routes, resulting in increased delivery costs and environmental impact. To solve these issues, a system is needed that can collect information in real time and instantly calculate and propose optimal delivery routes.

[0180] 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.

[0181] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting information on transportation means, means for normalizing the collected traffic information, weather information, business hours of delivery destinations, and information on transportation means, means for imputing missing values, and converting the collected information on traffic information, weather information, business hours of delivery destinations, and transportation means into a format usable for training an artificial intelligence model, means for training the artificial intelligence model using the preprocessed data, means for receiving real-time traffic information, weather information, business hours of delivery destinations, and information on transportation means and immediately reflecting the information in the artificial intelligence model, means for calculating an optimal delivery route and transportation means using the artificial intelligence model and notifying a user, means for notifying the user of the optimal delivery route and transportation means in real time via the user's smart device, means for collecting behavior related to delivery results and problems from the user, and means for retraining the artificial intelligence model based on the collected behavior data, thereby enabling the selection of efficient and cost-effective delivery routes in a logistics center.

[0182] "Traffic information" refers to all information that affects vehicle movement, such as traffic flow, congestion, and road closure information.

[0183] "Weather information" refers to all information related to weather conditions, such as rain, snow, wind speed, and temperature.

[0184] "Delivery destination business hours information" is information about the hours during which packages can be received.

[0185] "Information about transportation means" refers to information about the operation status and costs of transportation means such as trucks, trains, and ships.

[0186] An "artificial intelligence model" is a machine learning algorithm trained to predict optimal delivery routes and modes of transportation based on data.

[0187] "Real-time data" refers to information that is currently in progress or has recently been updated.

[0188] An "optimal delivery route" is a cargo movement route calculated to minimize cost, time, and environmental impact.

[0189] "Transportation" refers to the means by which cargo is transported to its destination, such as road, rail, or ship.

[0190] "Users" are logistics managers and delivery drivers who use this system to determine delivery routes and transportation methods.

[0191] A "smart device" is a portable electronic device with internet connectivity, such as a smartphone or tablet.

[0192] "Delivery results" refers to information such as the results of the actual delivery and any problems encountered.

[0193] "Behavioral data" is information based on user actions and behavior, and is used to retrain artificial intelligence models.

[0194] The present invention is a system for optimizing delivery routes within a logistics center. This system collects real-time traffic information, weather information, delivery destination business hours, and information on transportation methods, and trains an artificial intelligence model based on this data to propose optimal delivery routes. Specific embodiments are as follows.

[0195] Hardware and software used

[0196] server:

[0197] AWS EC2 instances: Used for data collection, preprocessing, and training the AI ​​model.

[0198] MySQL: Used to store and access data.

[0199] Device:

[0200] Smartphones and tablets: Used as operating devices for logistics drivers and managers.

[0201] Google Maps API: Used to collect traffic information.

[0202] OpenWeatherMap API: Used to collect weather information.

[0203] software:

[0204] TensorFlow: Used to train and optimize artificial intelligence models.

[0205] Data collection and preprocessing

[0206] The server collects real-time traffic information using the Google Maps API, weather information using the OpenWeatherMap API, business hours information for delivery destinations obtained from the customer database, and information on transportation modes collected from various operation statuses and costs. This collected data is normalized and missing values ​​are imputed.

[0207] Training and optimizing artificial intelligence models

[0208] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow. By also using past logistics data, a more accurate predictive model is built. This trained model instantly reflects real-time data and calculates the optimal delivery route and transportation method.

[0209] Notifications and Feedback

[0210] The optimal delivery route and transportation suggestions are sent to the user in real time via the device. For example, a smartphone may display instructions such as, "Section A of the highway is congested, so please select a route that combines rail and truck." Feedback on delivery results and problems is also collected via the device, and the server uses this information to retrain the AI ​​model, continuously improving prediction accuracy.

[0211] Examples of concrete examples and prompts

[0212] As a concrete example, suppose the weather information is "rain" and the traffic information is "highway section A is congested." Based on this information, the system will suggest a detour route.

[0213] Example prompt sentence:

[0214] "If it's raining and there's traffic on Highway A, please suggest the best delivery route."

[0215] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0216] Program processing steps

[0217] Step 1: Collect data

[0218] The server collects traffic information using the Google Maps API, weather information using the OpenWeatherMap API, and business hours of delivery destinations from the customer database, as well as various operational status and cost information.

[0219] Input: Traffic information obtained from API, weather information, opening hours information from customer database, operation status and cost information.

[0220] Output: Raw data summarizing the acquired data.

[0221] Specific operation: Sends requests to each API and receives response data in JSON format. Similarly, queries and retrieves business hours information from the database.

[0222] Step 2: Preprocessing the data

[0223] The server normalizes the collected raw data, imputes missing values, and converts the data format into a format that can be used by machine learning models.

[0224] Input: The raw data collected.

[0225] Output: Preprocessed data.

[0226] Specific operation: Uses standardization logic to convert traffic, weather, and business hours information into a unified format. Imputes missing values ​​with the mean or median.

[0227] Step 3: Training the AI ​​model

[0228] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow, along with historical logistics data.

[0229] Input: Preprocessed data, historical logistics data.

[0230] Output: A trained artificial intelligence model.

[0231] What it does: It feeds data to TensorFlow and runs a training loop using the backpropagation algorithm, selects optimal hyperparameters, and evaluates the model's accuracy.

[0232] Step 4: Update real-time data

[0233] The server receives real-time traffic and weather information, as well as delivery destination business hours, and reflects this information in a trained artificial intelligence model.

[0234] Input: Real-time traffic, weather, and business hours information.

[0235] Output: An updated artificial intelligence model.

[0236] Specific operation: The acquired real-time data is added to the model and reflected in the model calculations. Parameters are fine-tuned as necessary.

[0237] Step 5: Optimization calculation

[0238] The server uses the updated artificial intelligence model to calculate the optimal delivery route and means of transportation.

[0239] Input: Updated artificial intelligence model, real-time data.

[0240] Output: Optimal delivery route and mode of transport.

[0241] Specific operation: Performs inference processing on the model to select the optimal route and transportation method. Formats the results in JSON format or similar.

[0242] Step 6: Notification

[0243] The server notifies the user's smart device of the optimal delivery route and transportation suggestions.

[0244] Input: Optimal delivery route and mode of transport.

[0245] Output: Notification message displayed on the user's terminal.

[0246] Specific operation: A push notification is sent to the smart device, displaying a message such as "Section A of the expressway is congested, so please choose a route that combines rail and truck traffic."

[0247] Step 7: Gather feedback

[0248] The user sends feedback regarding delivery results and problems to the server via the terminal.

[0249] Input: Feedback data from users.

[0250] Output: Feedback data stored on the server.

[0251] Specific operation: Feedback data collected from user terminals is sent to the server and stored in a database.

[0252] Step 8: Retraining the AI ​​model

[0253] The server retrains the artificial intelligence model based on the collected feedback data.

[0254] Input: Feedback data.

[0255] Output: A retrained artificial intelligence model.

[0256] Specific operation: The training process is run again using the feedback data to improve the accuracy of the model.

[0257] These steps enable the logistics center to select efficient and cost-effective delivery routes and transportation methods.

[0258] 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.

[0259] This invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize the logistics network. Furthermore, by combining it with an emotion engine that recognizes user emotions, it aims to improve the user experience. This system is implemented as follows.

[0260] System Configuration

[0261] 1. Data Collection Module

[0262] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[0263] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and operational and cost information for trucks, trains, and ships.

[0264] 2. Data Preprocessing Module

[0265] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0266] 3. AI model training module

[0267] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[0268] Past logistics data is also used in the training to optimize various parameters.

[0269] 4. Real-time data update module

[0270] The device sends the latest traffic and weather information to the server in real time.

[0271] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[0272] 5. Optimization Algorithm Module

[0273] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[0274] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[0275] 6. Emotion Engine Module

[0276] The server analyzes the user's feedback data and recognizes their emotions, which are then used to retrain the AI ​​model and adjust the optimization results presented.

[0277] The emotion engine extracts and analyzes emotions from users' text and voice feedback and classifies them into categories such as "satisfied," "dissatisfied," and "abnormal."

[0278] 7. Notification Module

[0279] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[0280] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[0281] 8. Feedback Collection Module

[0282] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[0283] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes," "delays occurred at certain times," or "customers were dissatisfied with the service."

[0284] 9. AI model retraining module

[0285] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continually improves the model's predictive accuracy and aids in future deliveries.

[0286] Specific examples

[0287] Consider an e-commerce company making a large volume of deliveries from the Tokyo metropolitan area to the Kansai region. The company needs to consider weather forecasts for heavy rain and traffic conditions on expressways based on traffic information. Feedback and sentiment data collected from drivers are also taken into consideration.

[0288] 1. Data Collection:

[0289] The server obtains current road conditions from the traffic information API and obtains heavy rain forecast information from the weather forecast API.

[0290] The server obtains the delivery destination's business hours information from the customer database.

[0291] 2. Data Preprocessing:

[0292] The server formats and normalizes the collected data and imputes missing values.

[0293] 3. Training the AI ​​model:

[0294] The server trains an AI model based on the pre-processed data to predict the optimal delivery route and transportation method.

[0295] 4. Run the optimization algorithm:

[0296] The server optimizes delivery routes and transportation methods based on the latest data. For example, if heavy rain is predicted to cause congestion, it will choose a detour route and suggest using both rail and truck.

[0297] 5. Notice:

[0298] The server notifies the user of the calculation results and suggests the optimal delivery method.

[0299] 6. Feedback and Emotion Recognition:

[0300] Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[0301] 7. Retraining the AI ​​model:

[0302] The server uses the feedback and sentiment data to retrain the AI ​​model and improve its prediction accuracy.

[0303] This system utilizes real-time data and sentiment data to maintain a constantly optimized logistics network, which leads to efficient and fast delivery and contributes to an improved user experience.

[0304] The processing flow will be explained below.

[0305] Step 1:

[0306] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[0307] Step 2:

[0308] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[0309] Step 3:

[0310] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[0311] Step 4:

[0312] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[0313] Step 5:

[0314] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[0315] Step 6:

[0316] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[0317] Step 7:

[0318] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[0319] Step 8:

[0320] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[0321] Step 9:

[0322] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[0323] Step 10:

[0324] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[0325] Step 11:

[0326] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[0327] Step 12:

[0328] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[0329] Step 13:

[0330] The server uses the collected feedback data to retrain the AI ​​model, which improves the model's prediction accuracy and helps with future deliveries.

[0331] Step 14:

[0332] The server operates an emotion engine based on the user's feedback data. The emotion engine analyzes the user's emotions from text and voice data and classifies them into emotions such as "satisfied," "dissatisfied," and "abnormal."

[0333] Step 15:

[0334] The server retrains the AI ​​model based on the results of the emotion analysis, enabling optimization based on user emotions.

[0335] Step 16:

[0336] The server adjusts the optimal delivery route and transportation proposals based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, further improvements will be identified and reflected in the next optimization.

[0337] Example 2

[0338] 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."

[0339] In logistics networks, it is important to select efficient delivery routes and transportation methods. However, conventional systems lack the means to integrate and optimize data related to traffic information, weather information, delivery destination business hours, and transportation methods. As a result, costs and delays are likely to increase. In addition, re-optimization is not performed taking user feedback and emotions into account, making it difficult to improve customer satisfaction.

[0340] 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.

[0341] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training a machine learning model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the machine learning model, means for optimizing delivery routes and transportation means based on the latest data, means for proposing optimal delivery routes and transportation means, means for collecting user feedback data and performing sentiment analysis, and means for retraining the machine learning model using the feedback data and sentiment data. This makes it possible to maintain a constantly optimized logistics network by utilizing real-time data and user feedback, thereby enabling efficient and fast delivery and improved customer satisfaction.

[0342] "Traffic information" refers to data including road congestion status, traffic volume, accident information, and so on.

[0343] "Weather information" is data including current weather conditions, forecasts, temperature, probability of precipitation, etc.

[0344] "Delivery destination business hours information" is data indicating the hours during which each delivery destination is open.

[0345] "Transportation data" refers to data that includes information on the operation status, costs, and available transportation means such as trucks, trains, and ships.

[0346] "Means for training machine learning models using preprocessed data" refers to a mechanism for formatting raw data and training a model using a machine learning algorithm.

[0347] "Means of receiving real-time data and immediately reflecting it in the machine learning model" refers to a mechanism that receives the latest information in real time and updates the predictions of the machine learning model based on this information.

[0348] "Means for optimizing delivery routes and transportation methods based on the latest data" refers to an algorithm that uses newly collected data to determine the most efficient delivery routes and transportation methods.

[0349] "Means for proposing optimal delivery routes and transportation methods" is a function that presents the calculated optimization results to the user.

[0350] The "means for collecting user feedback data and performing emotion analysis" is a technology for collecting feedback from users and analyzing the emotions contained therein.

[0351] "Means for retraining machine learning models using feedback data and emotion data" refers to a mechanism for retraining machine learning models to improve their accuracy using collected feedback and emotion data.

[0352] This system optimizes logistics networks by collecting data on traffic, weather, delivery destination business hours, and transportation methods, and utilizes machine learning models. Furthermore, it combines an emotion engine that recognizes user emotions to improve the user experience.

[0353] System Configuration and Operation

[0354] Data collection

[0355] The server retrieves traffic information from the Google Maps API, weather information from the OpenWeatherMap API, and delivery location business hours information from a customer database (e.g., MySQL database), thereby comprehensively collecting data on transportation modes.

[0356] Data Preprocessing

[0357] The server uses the Python Pandas library to format and normalize the collected data, and imputes missing values ​​using the fillna function.

[0358] AI model training

[0359] The server uses the preprocessed data to train a machine learning model using libraries like TensorFlow and PyTorch, and also uses historical logistics data to set optimal parameters for the model.

[0360] Real-time data updates

[0361] The device sends the latest traffic and weather information to the server in real time using the MQTT protocol. The server then immediately applies the received real-time data to the machine learning model, providing the latest prediction results.

[0362] Delivery route and transportation optimization

[0363] The server uses the latest data to optimize delivery routes and transportation methods, using combinatorial optimization algorithms (e.g., genetic algorithms) that take into account multiple criteria, including cost, time, and environmental impact.

[0364] Information Notification

[0365] The server notifies the user's device of the calculated optimal delivery route and transportation suggestions, for example, by using a push notification API to send the optimization results to the mobile device.

[0366] Feedback and Emotion Recognition

[0367] The user provides feedback on delivery results and problems to the server via the terminal. This feedback includes emotional data and is analyzed by the emotion engine. The feedback is entered in text format using the terminal's feedback form.

[0368] AI model retraining

[0369] The server uses the collected feedback and sentiment data to retrain the machine learning model, which improves the model's predictive accuracy and allows for the continuous maintenance of an optimal logistics network.

[0370] Specific examples

[0371] When an e-commerce company makes a large delivery from the Tokyo metropolitan area to the Kansai region, it must take into account forecasts of heavy rain and traffic congestion on highways, as well as feedback and sentiment data collected from drivers.

[0372] Data collection: The server obtains current road conditions from the traffic information API, heavy rain forecast information from the weather forecast API, and business hours information for delivery destinations from the customer database.

[0373] Data preprocessing: The server formats and normalizes the collected data and imputes missing values.

[0374] Training the AI ​​model: The server trains the AI ​​model based on the pre-processed data to predict the optimal delivery route and transportation method.

[0375] Execution of optimization algorithm: The server proposes the best delivery route and transportation method based on the latest data.

[0376] Notification: The server notifies the user of the calculation results and suggests the optimal delivery method.

[0377] Feedback and emotion recognition: Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[0378] Retraining the AI ​​model: The server uses the feedback and sentiment data to retrain the AI ​​model to improve prediction accuracy.

[0379] Example prompt sentence:

[0380] "Generate Python code to develop a logistics network optimization system based on traffic and weather information. The system will use real-time data to suggest optimal delivery routes and analyze user feedback and sentiment data to retrain the AI ​​model."

[0381] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0382] Program processing flow

[0383] Step 1:

[0384] The server collects traffic information from the Google Maps API. Specifically, it sends an HTTP request to the Google Maps API and receives current road condition data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the obtained traffic information data.

[0385] Step 2:

[0386] The server collects weather information from the OpenWeatherMap API. Specifically, it sends an HTTP request to the OpenWeatherMap API and receives weather forecast data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the retrieved weather information data.

[0387] Step 3:

[0388] The server retrieves the delivery destination's business hours information from the customer database. Specifically, it executes a MySQL query to extract the required business hours information from the database. The input is the SQL query, and the output is the retrieved business hours data.

[0389] Step 4:

[0390] The server formats and normalizes the collected traffic, weather, and business hours information. Specifically, it uses Python's Pandas library to create a data frame, standardize the data, and impute missing values. The input is raw data, and the output is formatted and normalized data.

[0391] Step 5:

[0392] The server trains a machine learning model using the reshaped and normalized data. Specifically, it uses the TensorFlow library to build a neural network model and optimizes the model's parameters through backpropagation. The input is the preprocessed data, and the output is the trained model.

[0393] Step 6:

[0394] The terminal sends the latest traffic and weather information to the server in real time. Specifically, the terminal continuously transmits real-time data using the MQTT protocol. The input is the real-time data, and the output is the updated server database.

[0395] Step 7:

[0396] The server updates the machine learning model based on the latest real-time data to optimize delivery routes and transportation methods. Specifically, it runs a combinatorial optimization algorithm using the latest data to generate an optimal logistics plan. The input is the latest real-time data and the existing model, and the output is a proposal for an optimized delivery route and transportation method.

[0397] Step 8:

[0398] The server notifies the user's device of the optimal delivery route and transportation method proposal. Specifically, it uses a push notification API to send the proposal to the user. The input is the optimized logistics plan, and the output is a notification sent to the user's device.

[0399] Step 9:

[0400] The user provides feedback on delivery results and problems to the server via the terminal. Specifically, the user enters the feedback in text format using the terminal's feedback form and sends it to the server. The input is the user's feedback data, and the output is the feedback data saved on the server.

[0401] Step 10:

[0402] The server retrains the machine learning model using the feedback data and the emotion data. Specifically, the server performs retraining using a dataset containing the collected feedback and emotion data. The input is the feedback and emotion data, and the output is the retrained model.

[0403] (Application example 2)

[0404] 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."

[0405] In modern logistics systems, obtaining real-time traffic and weather information is a given, and proposing optimal delivery routes is also important. However, in addition to these, flexible responses that take into account user emotional feedback are also required. There is a lack of systems that can make such fine adjustments, making it difficult to build efficient logistics networks.

[0406] 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.

[0407] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training an AI model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the AI ​​model, means for proposing optimal delivery routes and transportation means, means for collecting user emotional feedback using an emotion recognition function, and means for sending notifications to users, thereby enabling optimization of a logistics network that effectively incorporates real-time data and emotional feedback.

[0408] "Means for collecting traffic information" refers to a device or system that has the function of collecting data on road conditions, such as traffic conditions and congestion information.

[0409] A "means for collecting weather information" is a device or system that has the function of collecting data related to local weather, such as weather conditions and weather forecasts.

[0410] The "means for collecting business hours information of delivery destinations" refers to a device or system that has the function of collecting data related to business hours, such as opening and closing times of delivery destinations.

[0411] "Means for collecting data on transportation means" refers to devices or systems that have the function of collecting operational status and cost information on various transportation means, such as trucks, trains, and ships.

[0412] A "means for training an AI model using preprocessed data" is a device or system that has the function of normalizing collected data, filling in missing values, and then processing the data to train an AI model.

[0413] "Means for receiving real-time data and immediately reflecting it in an artificial intelligence model" refers to a device or system that has the function of receiving the latest data obtained in real time and immediately applying that data to an artificial intelligence model.

[0414] A "means for proposing optimal delivery routes and transportation means" is a device or system that has the function of calculating and proposing efficient and optimal delivery routes and transportation means using a trained artificial intelligence model.

[0415] The "means for collecting user emotional feedback using an emotion recognition function" refers to a device or system that has the technology to analyze text or voice feedback from a user and recognize their emotional state.

[0416] The "means for sending notifications to the user" refers to a device or system that has the function of sending emails or app notifications to notify the user of the calculation results or suggestions.

[0417] A "means for retraining an AI model based on emotional feedback" is a device or system that has the function of retraining an AI model to improve its predictive ability using emotional data collected from users.

[0418] The present invention is a system for optimizing logistics networks. The system collects data on traffic, weather, delivery destination business hours, and transportation methods, and uses the preprocessed data to train an artificial intelligence model (AI model). The method is detailed below.

[0419] System Configuration

[0420] 1. Data Collection Module

[0421] The server collects necessary data from traffic information APIs, weather information APIs, customer databases, etc. Specifically, it collects nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and transportation operation status and cost information.

[0422] 2. Data Preprocessing Module

[0423] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0424] 3. AI model training module

[0425] The server uses the preprocessed data to train an AI model, using a deep learning framework such as TensorFlow or Keras.

[0426] 4. Real-time data update module

[0427] The device sends the latest traffic and weather information to the server in real time, and the server immediately reflects the received real-time data in the AI ​​model.

[0428] 5. Optimization Algorithm Module

[0429] The server uses the latest data to optimize delivery routes and transportation methods, implementing optimization algorithms using Python and R, with cost, time, and environmental impact as criteria.

[0430] 6. Emotion Engine Module

[0431] The server analyzes the user's feedback data and recognizes their emotions. It uses a natural language processing library such as TextBlob to extract emotions from the user's text feedback and classify them as "Satisfied," "Dissatisfied," or "Abnormal."

[0432] 7. Notification Module

[0433] The server then notifies the user (delivery driver or logistics manager) of the optimal delivery route and transportation method proposal via email via the SMTP server.

[0434] 8. Feedback Collection Module

[0435] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[0436] 9. AI model retraining module

[0437] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continuously improves its prediction accuracy for future deliveries.

[0438] Specific examples

[0439] For example, when making a large delivery from the Tokyo metropolitan area to the Kansai region, the server obtains current road conditions through a traffic information API and heavy rain forecast information from a weather information API. The collected data is preprocessed using Pandas and Sklearn. An AI model (built using TensorFlow and Keras) is then trained based on the preprocessed data. Real-time data updates are received using Flask and reflected in the model. The trained model calculates the optimal delivery route and transportation method using optimization algorithms using Python and R, and notifies the user via a notification module. User feedback and sentiment data are analyzed using TextBlob, and the AI ​​model is retrained.

[0440] Prompt Sentence Examples

[0441] "Please suggest the best delivery route and transportation method based on current traffic and weather information. Also, please take into account the user's emotional feedback on the delivery results to retrain your AI model."

[0442] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0443] Step 1:

[0444] Data collection

[0445] The server collects data from a traffic information API, a weather information API, and a customer database. Specifically, it uses the API to obtain road congestion information, weather forecasts, opening hours for each delivery location, and the operation status and cost information of various transportation modes. The inputs are API requests and database queries, and the output is a set of selected data.

[0446] Step 2:

[0447] Data Preprocessing

[0448] The server uses the Pandas library to reshape and normalize the collected data and impute missing values, for example, imputing the mean or median for missing data points and min-max scaling for numerical data. The input is the raw data collected in the previous step, and the output is the preprocessed dataset.

[0449] Step 3:

[0450] Training an AI model

[0451] The server trains an AI model using the preprocessed data using the TensorFlow and Keras libraries. Specifically, it splits the dataset into training data and validation data, and generates and trains the model using a deep learning algorithm. The input is the preprocessed dataset, and the output is the trained AI model.

[0452] Step 4:

[0453] Real-time data updates

[0454] The device obtains the latest traffic and weather information in real time and sends it to the server. The server immediately updates the AI ​​model based on the received real-time data. The input is new information obtained in real time, and the output is an AI model that reflects the latest data.

[0455] Step 5:

[0456] Running the optimization algorithm

[0457] The server uses a trained AI model to calculate and propose optimal delivery routes and transportation methods. The algorithm uses Python and R to evaluate cost, time, and environmental impact. The input is the latest AI model and a preprocessed dataset, and the output is the optimal delivery plan and transportation method.

[0458] Step 6:

[0459] Collecting emotional feedback

[0460] The user reports feedback and emotional data about the delivery results to the server via their terminal. Specifically, text and voice data are input as feedback. The input is the feedback data from the user, and the output is emotional data that has been classified and stored by the server.

[0461] Step 7:

[0462] Emotion data analysis and notification

[0463] The server analyzes the user's emotional feedback using natural language processing libraries such as TextBlob and classifies it into emotional categories. Based on the analysis results, an optimized delivery route and transportation method are notified. The input is the user's feedback data, and the output is a next optimization proposal including the emotional data.

[0464] Step 8:

[0465] Retraining AI models

[0466] The server uses the collected feedback and emotion data to retrain the AI ​​model, which continuously improves the model's prediction accuracy and helps with the next delivery plan. The input is the feedback and emotion data, and the output is an updated AI model.

[0467] 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.

[0468] 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.

[0469] 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.

[0470] [Second embodiment]

[0471] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0472] 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.

[0473] 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).

[0474] 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.

[0475] 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.

[0476] 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).

[0477] 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.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] 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.

[0482] 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."

[0483] The present invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize a logistics network. This system is implemented as follows.

[0484] System Configuration

[0485] 1. Data Collection Module

[0486] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[0487] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours at each delivery destination, and operational and cost information for trucks, trains, and ships.

[0488] 2. Data Preprocessing Module

[0489] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0490] 3. AI model training module

[0491] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[0492] Past logistics data is also used in the training to optimize various parameters.

[0493] 4. Real-time data update module

[0494] The device sends the latest traffic and weather information to the server in real time.

[0495] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[0496] 5. Optimization Algorithm Module

[0497] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[0498] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[0499] 6. Notification Module

[0500] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[0501] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[0502] 7. Feedback Collection Module

[0503] The user provides feedback on the actual delivery results and problems to the server via the terminal.

[0504] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes" or "delays occur during certain times of the day."

[0505] 8. AI model retraining module

[0506] The server uses the collected feedback data to retrain the AI ​​model, which continuously improves the model's predictive accuracy and helps with future deliveries.

[0507] Specific examples

[0508] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[0509] 1. Data Collection:

[0510] The server collects weather and traffic information from various APIs. For example, it checks that "traffic congestion is predicted due to heavy rain on Expressway Section A."

[0511] 2. Data Preprocessing:

[0512] The server formats the collected data, imputes missing values, and normalizes it as needed.

[0513] 3. Training the AI ​​model:

[0514] The server trains the AI ​​model using past logistics data and newly collected data.

[0515] 4. Run the optimization algorithm:

[0516] The server uses trained AI models to calculate optimal delivery routes and modes of transport, for example, choosing detours when heavy rain is forecast and even suggesting a combination of rail and truck transport.

[0517] 5. Notice:

[0518] The server notifies the user of the calculation results and instructs the user on the optimal delivery method.

[0519] 6. Feedback:

[0520] Once completed, the user reports the delivery results from their device to the server, which uses the results as data to improve the accuracy of the AI ​​model.

[0521] The above is an embodiment of the logistics network information optimization system based on the present invention. This system utilizes real-time data to constantly maintain an optimal logistics network and achieve efficient delivery.

[0522] The processing flow will be explained below.

[0523] Step 1:

[0524] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[0525] Step 2:

[0526] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[0527] Step 3:

[0528] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[0529] Step 4:

[0530] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[0531] Step 5:

[0532] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[0533] Step 6:

[0534] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[0535] Step 7:

[0536] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[0537] Step 8:

[0538] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[0539] Step 9:

[0540] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[0541] Step 10:

[0542] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[0543] Step 11:

[0544] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[0545] Step 12:

[0546] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[0547] Step 13:

[0548] The server uses the collected feedback data to retrain the AI ​​model, improving its prediction accuracy for future deliveries.

[0549] This is the specific processing flow of the AI-based logistics network information optimization system. By using this system, an optimized logistics network can be maintained at all times, enabling efficient and fast delivery.

[0550] Example 1

[0551] 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."

[0552] In the logistics industry, it is important to appropriately collect information on traffic conditions, weather, delivery destination business hours, and transportation methods, and to select the optimal delivery route and transportation method based on this data. However, it is difficult to reflect this data in real time and operate it efficiently. Furthermore, there is a lack of a mechanism to collect user feedback and continuously improve the model, which means that delivery efficiency and cost optimization cannot be fully achieved.

[0553] 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.

[0554] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation methods, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for receiving real-time data and immediately reflecting it in the AI ​​model, means for proposing an optimal delivery route and transportation method, means for notifying the user of the optimized delivery route and transportation method, means for collecting feedback data from users, and means for retraining the AI ​​model using the feedback data. This allows for traffic conditions, weather, and business hours of delivery destinations to be reflected in real time, making it possible to always select the optimal delivery route and transportation method. Furthermore, the model can be continuously improved using user feedback, thereby achieving logistics efficiency and cost reduction.

[0555] "Traffic information" refers to data related to traffic movement, such as road congestion, traffic jam information, and accident information.

[0556] "Weather information" refers to weather-related data such as weather forecasts, precipitation, wind speed, and temperature.

[0557] "Delivery destination business hours information" refers to data relating to the hours during which the delivery destination facility is open.

[0558] "Data on transportation means" refers to data on transportation means used in logistics, such as the operating status and operating costs of trucks, trains, ships, etc.

[0559] "Preprocessing" refers to the process of normalizing collected data, filling in missing values, and converting it into a format that is easy for an AI model to learn.

[0560] An "artificial intelligence model" is a model that uses machine learning to make predictions and classifications from data.

[0561] "Real-time data" refers to data that is collected immediately to reflect ongoing situations or events.

[0562] The "optimal delivery route" is the most efficient delivery route selected to improve logistics efficiency.

[0563] The "optimal means of transportation" refers to the most efficient and effective transportation method selected to improve logistics efficiency.

[0564] "Users" refer to delivery drivers and logistics managers who use the system to carry out delivery tasks.

[0565] "Feedback Data" refers to data provided by a user to report actual delivery results or problems.

[0566] This invention is a system that collects data on traffic information, weather information, business hours of delivery destinations, and transportation methods, and optimizes a logistics network using an AI model. The system includes a server, a terminal, and a user.

[0567] Hardware and software used

[0568] The server handles data collection, preprocessing, AI model training, real-time updates, optimization algorithm execution, notifications, feedback collection, and AI model retraining. Specific software used is the Python Requests library for data collection, Pandas for data preprocessing, and TensorFlow and PyTorch for AI model training.

[0569] The device is used to send real-time traffic and weather information to a server. For example, a delivery driver's smartphone or tablet sends GPS data and traffic information to the server.

[0570] The user receives suggestions from the system for optimal delivery routes and transportation methods, and then performs the actual delivery. After completing the delivery, the user provides feedback to the server via their terminal.

[0571] Specific examples

[0572] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[0573] The server collects data from traffic information APIs (e.g., Google Maps API) and weather information APIs (e.g., OpenWeatherMap API). The server periodically sends requests to these API endpoints and analyzes the JSON data received as a response. For example, it verifies that "traffic congestion is predicted due to heavy rain on section A of the highway."

[0574] The server preprocesses the collected data using the Pandas library, filling in missing weather information with data from the previous day and normalizing all numerical data to the same scale.

[0575] The server then uses the preprocessed data to train an AI model using TensorFlow or PyTorch. For example, it creates a model that predicts the optimal route for trucks based on past logistics data. The server improves prediction accuracy by training the model using both past data and newly collected data.

[0576] The device then sends the latest traffic and weather information to the server in real time. The delivery driver's smartphone then sends their current location and traffic congestion information to the server, and the server immediately updates the AI ​​model with the received real-time data, updating the forecast.

[0577] The server uses a trained AI model to calculate the optimal delivery route and transportation method, and notifies the user's device. For example, it provides specific instructions such as "If heavy rain is predicted, select a detour route and suggest using both rail and truck."

[0578] After completing the delivery, the user reports the delivery result to the server from their device, which serves as feedback data. The server uses the collected feedback data to retrain the AI ​​model, thereby continuously improving the model's prediction accuracy.

[0579] Prompt Sentence Examples

[0580] "Please suggest the best delivery route to the Kansai region."

[0581] "Please tell me the delivery route in bad weather."

[0582] In this way, the system utilizes real-time data to maintain an optimal logistics network at all times.

[0583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0584] Step 1:

[0585] Data collection

[0586] The server collects information from traffic information APIs, weather information APIs, customer databases, etc. Specifically, the server periodically sends requests to API endpoints and analyzes the JSON data received as a response.

[0587] Input: Traffic API, Weather API, Data from customer database

[0588] Output: Analyzed traffic, weather, delivery opening hours, and transportation data

[0589] Step 2:

[0590] Data Preprocessing

[0591] The server preprocesses the collected data, for example, by imputing missing data and normalizing numerical data. It uses the Python Pandas library to format the data and impute missing values.

[0592] Input: Parsed data

[0593] Output: Preprocessed data

[0594] Step 3:

[0595] Training an AI model

[0596] The server uses the preprocessed data to train an AI model, specifically by building a neural network using TensorFlow or PyTorch, inputting the data, and optimizing the model.

[0597] Input: Preprocessed data

[0598] Output: A trained AI model

[0599] Step 4:

[0600] Real-time data updates

[0601] The device sends real-time traffic and weather information to the server. For example, a delivery driver's mobile device uses GPS data to send current location and traffic information to the server.

[0602] Input: Real-time traffic and weather information

[0603] Output: Real-time data sent to the server

[0604] Step 5:

[0605] Running the optimization algorithm

[0606] The server uses the latest data to optimize delivery routes and transportation methods, using Python's Scipy library and other optimization libraries to solve complex optimization problems.

[0607] Input: Real-time data and pre-trained AI models

[0608] Output: Optimal delivery route and transportation method suggestions

[0609] Step 6:

[0610] notification

[0611] The server notifies the user's device of the optimal delivery route and transportation method, specifically by sending a pop-up notification or email to the delivery driver or logistics manager.

[0612] Input: Optimal delivery route and transportation suggestions

[0613] Output: User notification

[0614] Step 7:

[0615] Collecting feedback

[0616] Users can report actual delivery results and problems to the server via their devices, specifically by reporting problems using a mobile app or web interface.

[0617] Input: Actual delivery results and issues

[0618] Output: Feedback data sent to the server

[0619] Step 8:

[0620] Retraining AI models

[0621] The server uses the collected feedback data to retrain the AI ​​model, retraining it with new data and comparing it with the previous model to evaluate its accuracy.

[0622] Input: Feedback data

[0623] Output: Retrained AI model

[0624] (Application example 1)

[0625] 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."

[0626] In recent years, the logistics industry has become increasingly difficult to create efficient delivery plans due to a wide variety of delivery destinations and variable factors such as weather and traffic conditions. Conventional methods make it difficult to update information in real time and select optimal delivery routes, resulting in increased delivery costs and environmental impact. To solve these issues, a system is needed that can collect information in real time and instantly calculate and propose optimal delivery routes.

[0627] 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.

[0628] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting information on transportation means, means for normalizing the collected traffic information, weather information, business hours of delivery destinations, and information on transportation means, means for imputing missing values, and converting the collected information on traffic information, weather information, business hours of delivery destinations, and transportation means into a format usable for training an artificial intelligence model, means for training the artificial intelligence model using the preprocessed data, means for receiving real-time traffic information, weather information, business hours of delivery destinations, and information on transportation means and immediately reflecting the information in the artificial intelligence model, means for calculating an optimal delivery route and transportation means using the artificial intelligence model and notifying a user, means for notifying the user of the optimal delivery route and transportation means in real time via the user's smart device, means for collecting behavior related to delivery results and problems from the user, and means for retraining the artificial intelligence model based on the collected behavior data, thereby enabling the selection of efficient and cost-effective delivery routes in a logistics center.

[0629] "Traffic information" refers to all information that affects vehicle movement, such as traffic flow, congestion, and road closure information.

[0630] "Weather information" refers to all information related to weather conditions, such as rain, snow, wind speed, and temperature.

[0631] "Delivery destination business hours information" is information about the hours during which packages can be received.

[0632] "Information about transportation means" refers to information about the operation status and costs of transportation means such as trucks, trains, and ships.

[0633] An "artificial intelligence model" is a machine learning algorithm trained to predict optimal delivery routes and modes of transportation based on data.

[0634] "Real-time data" refers to information that is currently in progress or has recently been updated.

[0635] An "optimal delivery route" is a cargo movement route calculated to minimize cost, time, and environmental impact.

[0636] "Transportation" refers to the means by which cargo is transported to its destination, such as road, rail, or ship.

[0637] "Users" are logistics managers and delivery drivers who use this system to determine delivery routes and transportation methods.

[0638] A "smart device" is a portable electronic device with internet connectivity, such as a smartphone or tablet.

[0639] "Delivery results" refers to information such as the results of the actual delivery and any problems encountered.

[0640] "Behavioral data" is information based on user actions and behavior, and is used to retrain artificial intelligence models.

[0641] The present invention is a system for optimizing delivery routes within a logistics center. This system collects real-time traffic information, weather information, delivery destination business hours, and information on transportation methods, and trains an artificial intelligence model based on this data to propose optimal delivery routes. Specific embodiments are as follows.

[0642] Hardware and software used

[0643] server:

[0644] AWS EC2 instances: Used for data collection, preprocessing, and training the AI ​​model.

[0645] MySQL: Used to store and access data.

[0646] Device:

[0647] Smartphones and tablets: Used as operating devices for logistics drivers and managers.

[0648] Google Maps API: Used to collect traffic information.

[0649] OpenWeatherMap API: Used to collect weather information.

[0650] software:

[0651] TensorFlow: Used to train and optimize artificial intelligence models.

[0652] Data collection and preprocessing

[0653] The server collects real-time traffic information using the Google Maps API, weather information using the OpenWeatherMap API, business hours information for delivery destinations obtained from the customer database, and information on transportation modes collected from various operation statuses and costs. This collected data is normalized and missing values ​​are imputed.

[0654] Training and optimizing artificial intelligence models

[0655] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow. By also using past logistics data, a more accurate predictive model is built. This trained model instantly reflects real-time data and calculates the optimal delivery route and transportation method.

[0656] Notifications and Feedback

[0657] The optimal delivery route and transportation suggestions are sent to the user in real time via the device. For example, a smartphone may display instructions such as, "Section A of the highway is congested, so please select a route that combines rail and truck." Feedback on delivery results and problems is also collected via the device, and the server uses this information to retrain the AI ​​model, continuously improving prediction accuracy.

[0658] Examples of concrete examples and prompts

[0659] As a concrete example, suppose the weather information is "rain" and the traffic information is "highway section A is congested." Based on this information, the system will suggest a detour route.

[0660] Example prompt sentence:

[0661] "If it's raining and there's traffic on Highway A, please suggest the best delivery route."

[0662] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0663] Program processing steps

[0664] Step 1: Collect data

[0665] The server collects traffic information using the Google Maps API, weather information using the OpenWeatherMap API, and business hours of delivery destinations from the customer database, as well as various operational status and cost information.

[0666] Input: Traffic information obtained from API, weather information, opening hours information from customer database, operation status and cost information.

[0667] Output: Raw data summarizing the acquired data.

[0668] Specific operation: Sends requests to each API and receives response data in JSON format. Similarly, queries and retrieves business hours information from the database.

[0669] Step 2: Preprocessing the data

[0670] The server normalizes the collected raw data, imputes missing values, and converts the data format into a format that can be used by machine learning models.

[0671] Input: The raw data collected.

[0672] Output: Preprocessed data.

[0673] Specific operation: Uses standardization logic to convert traffic, weather, and business hours information into a unified format. Imputes missing values ​​with the mean or median.

[0674] Step 3: Training the AI ​​model

[0675] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow, along with historical logistics data.

[0676] Input: Preprocessed data, historical logistics data.

[0677] Output: A trained artificial intelligence model.

[0678] What it does: It feeds data to TensorFlow and runs a training loop using the backpropagation algorithm, selects optimal hyperparameters, and evaluates the model's accuracy.

[0679] Step 4: Update real-time data

[0680] The server receives real-time traffic and weather information, as well as delivery destination business hours, and reflects this information in a trained artificial intelligence model.

[0681] Input: Real-time traffic, weather, and business hours information.

[0682] Output: An updated artificial intelligence model.

[0683] Specific operation: The acquired real-time data is added to the model and reflected in the model calculations. Parameters are fine-tuned as necessary.

[0684] Step 5: Optimization calculation

[0685] The server uses the updated artificial intelligence model to calculate the optimal delivery route and means of transportation.

[0686] Input: Updated artificial intelligence model, real-time data.

[0687] Output: Optimal delivery route and mode of transport.

[0688] Specific operation: Performs inference processing on the model to select the optimal route and transportation method. Formats the results in JSON format or similar.

[0689] Step 6: Notification

[0690] The server notifies the user's smart device of the optimal delivery route and transportation suggestions.

[0691] Input: Optimal delivery route and mode of transport.

[0692] Output: Notification message displayed on the user's terminal.

[0693] Specific operation: A push notification is sent to the smart device, displaying a message such as "Section A of the expressway is congested, so please choose a route that combines rail and truck traffic."

[0694] Step 7: Gather feedback

[0695] The user sends feedback regarding delivery results and problems to the server via the terminal.

[0696] Input: Feedback data from users.

[0697] Output: Feedback data stored on the server.

[0698] Specific operation: Feedback data collected from user terminals is sent to the server and stored in a database.

[0699] Step 8: Retraining the AI ​​model

[0700] The server retrains the artificial intelligence model based on the collected feedback data.

[0701] Input: Feedback data.

[0702] Output: A retrained artificial intelligence model.

[0703] Specific operation: The training process is run again using the feedback data to improve the accuracy of the model.

[0704] These steps enable the logistics center to select efficient and cost-effective delivery routes and transportation methods.

[0705] 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.

[0706] This invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize the logistics network. Furthermore, by combining it with an emotion engine that recognizes user emotions, it aims to improve the user experience. This system is implemented as follows.

[0707] System Configuration

[0708] 1. Data Collection Module

[0709] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[0710] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and operational and cost information for trucks, trains, and ships.

[0711] 2. Data Preprocessing Module

[0712] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0713] 3. AI model training module

[0714] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[0715] Past logistics data is also used in the training to optimize various parameters.

[0716] 4. Real-time data update module

[0717] The device sends the latest traffic and weather information to the server in real time.

[0718] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[0719] 5. Optimization Algorithm Module

[0720] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[0721] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[0722] 6. Emotion Engine Module

[0723] The server analyzes the user's feedback data and recognizes their emotions, which are then used to retrain the AI ​​model and adjust the optimization results presented.

[0724] The emotion engine extracts and analyzes emotions from users' text and voice feedback and classifies them into categories such as "satisfied," "dissatisfied," and "abnormal."

[0725] 7. Notification Module

[0726] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[0727] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[0728] 8. Feedback Collection Module

[0729] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[0730] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes," "delays occurred at certain times," or "customers were dissatisfied with the service."

[0731] 9. AI model retraining module

[0732] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continually improves the model's predictive accuracy and aids in future deliveries.

[0733] Specific examples

[0734] Consider an e-commerce company making a large volume of deliveries from the Tokyo metropolitan area to the Kansai region. The company needs to consider weather forecasts for heavy rain and traffic conditions on expressways based on traffic information. Feedback and sentiment data collected from drivers are also taken into consideration.

[0735] 1. Data Collection:

[0736] The server obtains current road conditions from the traffic information API and obtains heavy rain forecast information from the weather forecast API.

[0737] The server obtains the delivery destination's business hours information from the customer database.

[0738] 2. Data Preprocessing:

[0739] The server formats and normalizes the collected data and imputes missing values.

[0740] 3. Training the AI ​​model:

[0741] The server trains an AI model based on the pre-processed data to predict the optimal delivery route and transportation method.

[0742] 4. Run the optimization algorithm:

[0743] The server optimizes delivery routes and transportation methods based on the latest data. For example, if heavy rain is predicted to cause congestion, it will choose a detour route and suggest using both rail and truck.

[0744] 5. Notice:

[0745] The server notifies the user of the calculation results and suggests the optimal delivery method.

[0746] 6. Feedback and Emotion Recognition:

[0747] Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[0748] 7. Retraining the AI ​​model:

[0749] The server uses the feedback and sentiment data to retrain the AI ​​model and improve its prediction accuracy.

[0750] This system utilizes real-time data and sentiment data to maintain a constantly optimized logistics network, which leads to efficient and fast delivery and contributes to an improved user experience.

[0751] The processing flow will be explained below.

[0752] Step 1:

[0753] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[0754] Step 2:

[0755] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[0756] Step 3:

[0757] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[0758] Step 4:

[0759] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[0760] Step 5:

[0761] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[0762] Step 6:

[0763] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[0764] Step 7:

[0765] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[0766] Step 8:

[0767] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[0768] Step 9:

[0769] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[0770] Step 10:

[0771] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[0772] Step 11:

[0773] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[0774] Step 12:

[0775] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[0776] Step 13:

[0777] The server uses the collected feedback data to retrain the AI ​​model, which improves the model's prediction accuracy and helps with future deliveries.

[0778] Step 14:

[0779] The server operates an emotion engine based on the user's feedback data. The emotion engine analyzes the user's emotions from text and voice data and classifies them into emotions such as "satisfied," "dissatisfied," and "abnormal."

[0780] Step 15:

[0781] The server retrains the AI ​​model based on the results of the emotion analysis, enabling optimization based on user emotions.

[0782] Step 16:

[0783] The server adjusts the optimal delivery route and transportation proposals based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, further improvements will be identified and reflected in the next optimization.

[0784] Example 2

[0785] 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."

[0786] In logistics networks, it is important to select efficient delivery routes and transportation methods. However, conventional systems lack the means to integrate and optimize data related to traffic information, weather information, delivery destination business hours, and transportation methods. As a result, costs and delays are likely to increase. In addition, re-optimization is not performed taking user feedback and emotions into account, making it difficult to improve customer satisfaction.

[0787] 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.

[0788] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training a machine learning model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the machine learning model, means for optimizing delivery routes and transportation means based on the latest data, means for proposing optimal delivery routes and transportation means, means for collecting user feedback data and performing sentiment analysis, and means for retraining the machine learning model using the feedback data and sentiment data. This makes it possible to maintain a constantly optimized logistics network by utilizing real-time data and user feedback, thereby enabling efficient and fast delivery and improved customer satisfaction.

[0789] "Traffic information" refers to data including road congestion status, traffic volume, accident information, and so on.

[0790] "Weather information" is data including current weather conditions, forecasts, temperature, probability of precipitation, etc.

[0791] "Delivery destination business hours information" is data indicating the hours during which each delivery destination is open.

[0792] "Transportation data" refers to data that includes information on the operation status, costs, and available transportation means such as trucks, trains, and ships.

[0793] "Means for training machine learning models using preprocessed data" refers to a mechanism for formatting raw data and training a model using a machine learning algorithm.

[0794] "Means of receiving real-time data and immediately reflecting it in the machine learning model" refers to a mechanism that receives the latest information in real time and updates the predictions of the machine learning model based on this information.

[0795] "Means for optimizing delivery routes and transportation methods based on the latest data" refers to an algorithm that uses newly collected data to determine the most efficient delivery routes and transportation methods.

[0796] "Means for proposing optimal delivery routes and transportation methods" is a function that presents the calculated optimization results to the user.

[0797] The "means for collecting user feedback data and performing emotion analysis" is a technology for collecting feedback from users and analyzing the emotions contained therein.

[0798] "Means for retraining machine learning models using feedback data and emotion data" refers to a mechanism for retraining machine learning models to improve their accuracy using collected feedback and emotion data.

[0799] This system optimizes logistics networks by collecting data on traffic, weather, delivery destination business hours, and transportation methods, and utilizes machine learning models. Furthermore, it combines an emotion engine that recognizes user emotions to improve the user experience.

[0800] System Configuration and Operation

[0801] Data collection

[0802] The server retrieves traffic information from the Google Maps API, weather information from the OpenWeatherMap API, and delivery location business hours information from a customer database (e.g., MySQL database), thereby comprehensively collecting data on transportation modes.

[0803] Data Preprocessing

[0804] The server uses the Python Pandas library to format and normalize the collected data, and imputes missing values ​​using the fillna function.

[0805] AI model training

[0806] The server uses the preprocessed data to train a machine learning model using libraries like TensorFlow and PyTorch, and also uses historical logistics data to set optimal parameters for the model.

[0807] Real-time data updates

[0808] The device sends the latest traffic and weather information to the server in real time using the MQTT protocol. The server then immediately applies the received real-time data to the machine learning model, providing the latest prediction results.

[0809] Delivery route and transportation optimization

[0810] The server uses the latest data to optimize delivery routes and transportation methods, using combinatorial optimization algorithms (e.g., genetic algorithms) that take into account multiple criteria, including cost, time, and environmental impact.

[0811] Information Notification

[0812] The server notifies the user's device of the calculated optimal delivery route and transportation suggestions, for example, by using a push notification API to send the optimization results to the mobile device.

[0813] Feedback and Emotion Recognition

[0814] The user provides feedback on delivery results and problems to the server via the terminal. This feedback includes emotional data and is analyzed by the emotion engine. The feedback is entered in text format using the terminal's feedback form.

[0815] AI model retraining

[0816] The server uses the collected feedback and sentiment data to retrain the machine learning model, which improves the model's predictive accuracy and allows for the continuous maintenance of an optimal logistics network.

[0817] Specific examples

[0818] When an e-commerce company makes a large delivery from the Tokyo metropolitan area to the Kansai region, it must take into account forecasts of heavy rain and traffic congestion on highways, as well as feedback and sentiment data collected from drivers.

[0819] Data collection: The server obtains current road conditions from the traffic information API, heavy rain forecast information from the weather forecast API, and business hours information for delivery destinations from the customer database.

[0820] Data preprocessing: The server formats and normalizes the collected data and imputes missing values.

[0821] Training the AI ​​model: The server trains the AI ​​model based on the pre-processed data to predict the optimal delivery route and transportation method.

[0822] Execution of optimization algorithm: The server proposes the best delivery route and transportation method based on the latest data.

[0823] Notification: The server notifies the user of the calculation results and suggests the optimal delivery method.

[0824] Feedback and emotion recognition: Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[0825] Retraining the AI ​​model: The server uses the feedback and sentiment data to retrain the AI ​​model to improve prediction accuracy.

[0826] Example prompt sentence:

[0827] "Generate Python code to develop a logistics network optimization system based on traffic and weather information. The system will use real-time data to suggest optimal delivery routes and analyze user feedback and sentiment data to retrain the AI ​​model."

[0828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0829] Program processing flow

[0830] Step 1:

[0831] The server collects traffic information from the Google Maps API. Specifically, it sends an HTTP request to the Google Maps API and receives current road condition data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the obtained traffic information data.

[0832] Step 2:

[0833] The server collects weather information from the OpenWeatherMap API. Specifically, it sends an HTTP request to the OpenWeatherMap API and receives weather forecast data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the retrieved weather information data.

[0834] Step 3:

[0835] The server retrieves the delivery destination's business hours information from the customer database. Specifically, it executes a MySQL query to extract the required business hours information from the database. The input is the SQL query, and the output is the retrieved business hours data.

[0836] Step 4:

[0837] The server formats and normalizes the collected traffic, weather, and business hours information. Specifically, it uses Python's Pandas library to create a data frame, standardize the data, and impute missing values. The input is raw data, and the output is formatted and normalized data.

[0838] Step 5:

[0839] The server trains a machine learning model using the reshaped and normalized data. Specifically, it uses the TensorFlow library to build a neural network model and optimizes the model's parameters through backpropagation. The input is the preprocessed data, and the output is the trained model.

[0840] Step 6:

[0841] The terminal sends the latest traffic and weather information to the server in real time. Specifically, the terminal continuously transmits real-time data using the MQTT protocol. The input is the real-time data, and the output is the updated server database.

[0842] Step 7:

[0843] The server updates the machine learning model based on the latest real-time data to optimize delivery routes and transportation methods. Specifically, it runs a combinatorial optimization algorithm using the latest data to generate an optimal logistics plan. The input is the latest real-time data and the existing model, and the output is a proposal for an optimized delivery route and transportation method.

[0844] Step 8:

[0845] The server notifies the user's device of the optimal delivery route and transportation method proposal. Specifically, it uses a push notification API to send the proposal to the user. The input is the optimized logistics plan, and the output is a notification sent to the user's device.

[0846] Step 9:

[0847] The user provides feedback on delivery results and problems to the server via the terminal. Specifically, the user enters the feedback in text format using the terminal's feedback form and sends it to the server. The input is the user's feedback data, and the output is the feedback data saved on the server.

[0848] Step 10:

[0849] The server retrains the machine learning model using the feedback data and the emotion data. Specifically, the server performs retraining using a dataset containing the collected feedback and emotion data. The input is the feedback and emotion data, and the output is the retrained model.

[0850] (Application example 2)

[0851] 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."

[0852] In modern logistics systems, obtaining real-time traffic and weather information is a given, and proposing optimal delivery routes is also important. However, in addition to these, flexible responses that take into account user emotional feedback are also required. There is a lack of systems that can make such fine adjustments, making it difficult to build efficient logistics networks.

[0853] 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.

[0854] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training an AI model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the AI ​​model, means for proposing optimal delivery routes and transportation means, means for collecting user emotional feedback using an emotion recognition function, and means for sending notifications to users, thereby enabling optimization of a logistics network that effectively incorporates real-time data and emotional feedback.

[0855] "Means for collecting traffic information" refers to a device or system that has the function of collecting data on road conditions, such as traffic conditions and congestion information.

[0856] A "means for collecting weather information" is a device or system that has the function of collecting data related to local weather, such as weather conditions and weather forecasts.

[0857] The "means for collecting business hours information of delivery destinations" refers to a device or system that has the function of collecting data related to business hours, such as opening and closing times of delivery destinations.

[0858] "Means for collecting data on transportation means" refers to devices or systems that have the function of collecting operational status and cost information on various transportation means, such as trucks, trains, and ships.

[0859] A "means for training an AI model using preprocessed data" is a device or system that has the function of normalizing collected data, filling in missing values, and then processing the data to train an AI model.

[0860] "Means for receiving real-time data and immediately reflecting it in an artificial intelligence model" refers to a device or system that has the function of receiving the latest data obtained in real time and immediately applying that data to an artificial intelligence model.

[0861] A "means for proposing optimal delivery routes and transportation means" is a device or system that has the function of calculating and proposing efficient and optimal delivery routes and transportation means using a trained artificial intelligence model.

[0862] The "means for collecting user emotional feedback using an emotion recognition function" refers to a device or system that has the technology to analyze text or voice feedback from a user and recognize their emotional state.

[0863] The "means for sending notifications to the user" refers to a device or system that has the function of sending emails or app notifications to notify the user of the calculation results or suggestions.

[0864] A "means for retraining an AI model based on emotional feedback" is a device or system that has the function of retraining an AI model to improve its predictive ability using emotional data collected from users.

[0865] The present invention is a system for optimizing logistics networks. The system collects data on traffic, weather, delivery destination business hours, and transportation methods, and uses the preprocessed data to train an artificial intelligence model (AI model). The method is detailed below.

[0866] System Configuration

[0867] 1. Data Collection Module

[0868] The server collects necessary data from traffic information APIs, weather information APIs, customer databases, etc. Specifically, it collects nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and transportation operation status and cost information.

[0869] 2. Data Preprocessing Module

[0870] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0871] 3. AI model training module

[0872] The server uses the preprocessed data to train an AI model, using a deep learning framework such as TensorFlow or Keras.

[0873] 4. Real-time data update module

[0874] The device sends the latest traffic and weather information to the server in real time, and the server immediately reflects the received real-time data in the AI ​​model.

[0875] 5. Optimization Algorithm Module

[0876] The server uses the latest data to optimize delivery routes and transportation methods, implementing optimization algorithms using Python and R, with cost, time, and environmental impact as criteria.

[0877] 6. Emotion Engine Module

[0878] The server analyzes the user's feedback data and recognizes their emotions. It uses a natural language processing library such as TextBlob to extract emotions from the user's text feedback and classify them as "Satisfied," "Dissatisfied," or "Abnormal."

[0879] 7. Notification Module

[0880] The server then notifies the user (delivery driver or logistics manager) of the optimal delivery route and transportation method proposal via email via the SMTP server.

[0881] 8. Feedback Collection Module

[0882] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[0883] 9. AI model retraining module

[0884] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continuously improves its prediction accuracy for future deliveries.

[0885] Specific examples

[0886] For example, when making a large delivery from the Tokyo metropolitan area to the Kansai region, the server obtains current road conditions through a traffic information API and heavy rain forecast information from a weather information API. The collected data is preprocessed using Pandas and Sklearn. An AI model (built using TensorFlow and Keras) is then trained based on the preprocessed data. Real-time data updates are received using Flask and reflected in the model. The trained model calculates the optimal delivery route and transportation method using optimization algorithms using Python and R, and notifies the user via a notification module. User feedback and sentiment data are analyzed using TextBlob, and the AI ​​model is retrained.

[0887] Prompt Sentence Examples

[0888] "Please suggest the best delivery route and transportation method based on current traffic and weather information. Also, please take into account the user's emotional feedback on the delivery results to retrain your AI model."

[0889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0890] Step 1:

[0891] Data collection

[0892] The server collects data from a traffic information API, a weather information API, and a customer database. Specifically, it uses the API to obtain road congestion information, weather forecasts, opening hours for each delivery location, and the operation status and cost information of various transportation modes. The inputs are API requests and database queries, and the output is a set of selected data.

[0893] Step 2:

[0894] Data Preprocessing

[0895] The server uses the Pandas library to reshape and normalize the collected data and impute missing values, for example, imputing the mean or median for missing data points and min-max scaling for numerical data. The input is the raw data collected in the previous step, and the output is the preprocessed dataset.

[0896] Step 3:

[0897] Training an AI model

[0898] The server trains an AI model using the preprocessed data using the TensorFlow and Keras libraries. Specifically, it splits the dataset into training data and validation data, and generates and trains the model using a deep learning algorithm. The input is the preprocessed dataset, and the output is the trained AI model.

[0899] Step 4:

[0900] Real-time data updates

[0901] The device obtains the latest traffic and weather information in real time and sends it to the server. The server immediately updates the AI ​​model based on the received real-time data. The input is new information obtained in real time, and the output is an AI model that reflects the latest data.

[0902] Step 5:

[0903] Running the optimization algorithm

[0904] The server uses a trained AI model to calculate and propose optimal delivery routes and transportation methods. The algorithm uses Python and R to evaluate cost, time, and environmental impact. The input is the latest AI model and a preprocessed dataset, and the output is the optimal delivery plan and transportation method.

[0905] Step 6:

[0906] Collecting emotional feedback

[0907] The user reports feedback and emotional data about the delivery results to the server via their terminal. Specifically, text and voice data are input as feedback. The input is the feedback data from the user, and the output is emotional data that has been classified and stored by the server.

[0908] Step 7:

[0909] Emotion data analysis and notification

[0910] The server analyzes the user's emotional feedback using natural language processing libraries such as TextBlob and classifies it into emotional categories. Based on the analysis results, an optimized delivery route and transportation method are notified. The input is the user's feedback data, and the output is a next optimization proposal including the emotional data.

[0911] Step 8:

[0912] Retraining AI models

[0913] The server uses the collected feedback and emotion data to retrain the AI ​​model, which continuously improves the model's prediction accuracy and helps with the next delivery plan. The input is the feedback and emotion data, and the output is an updated AI model.

[0914] 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.

[0915] 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.

[0916] 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.

[0917] [Third embodiment]

[0918] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0919] 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.

[0920] 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).

[0921] 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.

[0922] 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.

[0923] 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).

[0924] 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.

[0925] 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.

[0926] 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.

[0927] 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.

[0928] 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.

[0929] 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."

[0930] The present invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize a logistics network. This system is implemented as follows.

[0931] System Configuration

[0932] 1. Data Collection Module

[0933] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[0934] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours at each delivery destination, and operational and cost information for trucks, trains, and ships.

[0935] 2. Data Preprocessing Module

[0936] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[0937] 3. AI model training module

[0938] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[0939] Past logistics data is also used in the training to optimize various parameters.

[0940] 4. Real-time data update module

[0941] The device sends the latest traffic and weather information to the server in real time.

[0942] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[0943] 5. Optimization Algorithm Module

[0944] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[0945] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[0946] 6. Notification Module

[0947] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[0948] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[0949] 7. Feedback Collection Module

[0950] The user provides feedback on the actual delivery results and problems to the server via the terminal.

[0951] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes" or "delays occur during certain times of the day."

[0952] 8. AI model retraining module

[0953] The server uses the collected feedback data to retrain the AI ​​model, which continuously improves the model's predictive accuracy and helps with future deliveries.

[0954] Specific examples

[0955] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[0956] 1. Data Collection:

[0957] The server collects weather and traffic information from various APIs. For example, it checks that "traffic congestion is predicted due to heavy rain on Expressway Section A."

[0958] 2. Data Preprocessing:

[0959] The server formats the collected data, imputes missing values, and normalizes it as needed.

[0960] 3. Training the AI ​​model:

[0961] The server trains the AI ​​model using past logistics data and newly collected data.

[0962] 4. Run the optimization algorithm:

[0963] The server uses trained AI models to calculate optimal delivery routes and modes of transport, for example, choosing detours when heavy rain is forecast and even suggesting a combination of rail and truck transport.

[0964] 5. Notice:

[0965] The server notifies the user of the calculation results and instructs the user on the optimal delivery method.

[0966] 6. Feedback:

[0967] Once completed, the user reports the delivery results from their device to the server, which uses the results as data to improve the accuracy of the AI ​​model.

[0968] The above is an embodiment of the logistics network information optimization system based on the present invention. This system utilizes real-time data to constantly maintain an optimal logistics network and achieve efficient delivery.

[0969] The processing flow will be explained below.

[0970] Step 1:

[0971] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[0972] Step 2:

[0973] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[0974] Step 3:

[0975] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[0976] Step 4:

[0977] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[0978] Step 5:

[0979] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[0980] Step 6:

[0981] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[0982] Step 7:

[0983] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[0984] Step 8:

[0985] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[0986] Step 9:

[0987] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[0988] Step 10:

[0989] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[0990] Step 11:

[0991] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[0992] Step 12:

[0993] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[0994] Step 13:

[0995] The server uses the collected feedback data to retrain the AI ​​model, improving its prediction accuracy for future deliveries.

[0996] This is the specific processing flow of the AI-based logistics network information optimization system. By using this system, an optimized logistics network can be maintained at all times, enabling efficient and fast delivery.

[0997] Example 1

[0998] 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."

[0999] In the logistics industry, it is important to appropriately collect information on traffic conditions, weather, delivery destination business hours, and transportation methods, and to select the optimal delivery route and transportation method based on this data. However, it is difficult to reflect this data in real time and operate it efficiently. Furthermore, there is a lack of a mechanism to collect user feedback and continuously improve the model, which means that delivery efficiency and cost optimization cannot be fully achieved.

[1000] 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.

[1001] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation methods, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for receiving real-time data and immediately reflecting it in the AI ​​model, means for proposing an optimal delivery route and transportation method, means for notifying the user of the optimized delivery route and transportation method, means for collecting feedback data from users, and means for retraining the AI ​​model using the feedback data. This allows for traffic conditions, weather, and business hours of delivery destinations to be reflected in real time, making it possible to always select the optimal delivery route and transportation method. Furthermore, the model can be continuously improved using user feedback, thereby achieving logistics efficiency and cost reduction.

[1002] "Traffic information" refers to data related to traffic movement, such as road congestion, traffic jam information, and accident information.

[1003] "Weather information" refers to weather-related data such as weather forecasts, precipitation, wind speed, and temperature.

[1004] "Delivery destination business hours information" refers to data relating to the hours during which the delivery destination facility is open.

[1005] "Data on transportation means" refers to data on transportation means used in logistics, such as the operating status and operating costs of trucks, trains, ships, etc.

[1006] "Preprocessing" refers to the process of normalizing collected data, filling in missing values, and converting it into a format that is easy for an AI model to learn.

[1007] An "artificial intelligence model" is a model that uses machine learning to make predictions and classifications from data.

[1008] "Real-time data" refers to data that is collected immediately to reflect ongoing situations or events.

[1009] The "optimal delivery route" is the most efficient delivery route selected to improve logistics efficiency.

[1010] The "optimal means of transportation" refers to the most efficient and effective transportation method selected to improve logistics efficiency.

[1011] "Users" refer to delivery drivers and logistics managers who use the system to carry out delivery tasks.

[1012] "Feedback Data" refers to data provided by a user to report actual delivery results or problems.

[1013] This invention is a system that collects data on traffic information, weather information, business hours of delivery destinations, and transportation methods, and optimizes a logistics network using an AI model. The system includes a server, a terminal, and a user.

[1014] Hardware and software used

[1015] The server handles data collection, preprocessing, AI model training, real-time updates, optimization algorithm execution, notifications, feedback collection, and AI model retraining. Specific software used is the Python Requests library for data collection, Pandas for data preprocessing, and TensorFlow and PyTorch for AI model training.

[1016] The device is used to send real-time traffic and weather information to a server. For example, a delivery driver's smartphone or tablet sends GPS data and traffic information to the server.

[1017] The user receives suggestions from the system for optimal delivery routes and transportation methods, and then performs the actual delivery. After completing the delivery, the user provides feedback to the server via their terminal.

[1018] Specific examples

[1019] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[1020] The server collects data from traffic information APIs (e.g., Google Maps API) and weather information APIs (e.g., OpenWeatherMap API). The server periodically sends requests to these API endpoints and analyzes the JSON data received as a response. For example, it verifies that "traffic congestion is predicted due to heavy rain on section A of the highway."

[1021] The server preprocesses the collected data using the Pandas library, filling in missing weather information with data from the previous day and normalizing all numerical data to the same scale.

[1022] The server then uses the preprocessed data to train an AI model using TensorFlow or PyTorch. For example, it creates a model that predicts the optimal route for trucks based on past logistics data. The server improves prediction accuracy by training the model using both past data and newly collected data.

[1023] The device then sends the latest traffic and weather information to the server in real time. The delivery driver's smartphone then sends their current location and traffic congestion information to the server, and the server immediately updates the AI ​​model with the received real-time data, updating the forecast.

[1024] The server uses a trained AI model to calculate the optimal delivery route and transportation method, and notifies the user's device. For example, it provides specific instructions such as "If heavy rain is predicted, select a detour route and suggest using both rail and truck."

[1025] After completing the delivery, the user reports the delivery result to the server from their device, which serves as feedback data. The server uses the collected feedback data to retrain the AI ​​model, thereby continuously improving the model's prediction accuracy.

[1026] Prompt Sentence Examples

[1027] "Please suggest the best delivery route to the Kansai region."

[1028] "Please tell me the delivery route in bad weather."

[1029] In this way, the system utilizes real-time data to maintain an optimal logistics network at all times.

[1030] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1031] Step 1:

[1032] Data collection

[1033] The server collects information from traffic information APIs, weather information APIs, customer databases, etc. Specifically, the server periodically sends requests to API endpoints and analyzes the JSON data received as a response.

[1034] Input: Traffic API, Weather API, Data from customer database

[1035] Output: Analyzed traffic, weather, delivery opening hours, and transportation data

[1036] Step 2:

[1037] Data Preprocessing

[1038] The server preprocesses the collected data, for example, by imputing missing data and normalizing numerical data. It uses the Python Pandas library to format the data and impute missing values.

[1039] Input: Parsed data

[1040] Output: Preprocessed data

[1041] Step 3:

[1042] Training an AI model

[1043] The server uses the preprocessed data to train an AI model, specifically by building a neural network using TensorFlow or PyTorch, inputting the data, and optimizing the model.

[1044] Input: Preprocessed data

[1045] Output: A trained AI model

[1046] Step 4:

[1047] Real-time data updates

[1048] The device sends real-time traffic and weather information to the server. For example, a delivery driver's mobile device uses GPS data to send current location and traffic information to the server.

[1049] Input: Real-time traffic and weather information

[1050] Output: Real-time data sent to the server

[1051] Step 5:

[1052] Running the optimization algorithm

[1053] The server uses the latest data to optimize delivery routes and transportation methods, using Python's Scipy library and other optimization libraries to solve complex optimization problems.

[1054] Input: Real-time data and pre-trained AI models

[1055] Output: Optimal delivery route and transportation method suggestions

[1056] Step 6:

[1057] notification

[1058] The server notifies the user's device of the optimal delivery route and transportation method, specifically by sending a pop-up notification or email to the delivery driver or logistics manager.

[1059] Input: Optimal delivery route and transportation suggestions

[1060] Output: User notification

[1061] Step 7:

[1062] Collecting feedback

[1063] Users can report actual delivery results and problems to the server via their devices, specifically by reporting problems using a mobile app or web interface.

[1064] Input: Actual delivery results and issues

[1065] Output: Feedback data sent to the server

[1066] Step 8:

[1067] Retraining AI models

[1068] The server uses the collected feedback data to retrain the AI ​​model, retraining it with new data and comparing it with the previous model to evaluate its accuracy.

[1069] Input: Feedback data

[1070] Output: Retrained AI model

[1071] (Application example 1)

[1072] 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."

[1073] In recent years, the logistics industry has become increasingly difficult to create efficient delivery plans due to a wide variety of delivery destinations and variable factors such as weather and traffic conditions. Conventional methods make it difficult to update information in real time and select optimal delivery routes, resulting in increased delivery costs and environmental impact. To solve these issues, a system is needed that can collect information in real time and instantly calculate and propose optimal delivery routes.

[1074] 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.

[1075] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting information on transportation means, means for normalizing the collected traffic information, weather information, business hours of delivery destinations, and information on transportation means, means for imputing missing values, and converting the collected information on traffic information, weather information, business hours of delivery destinations, and transportation means into a format usable for training an artificial intelligence model, means for training the artificial intelligence model using the preprocessed data, means for receiving real-time traffic information, weather information, business hours of delivery destinations, and information on transportation means and immediately reflecting the information in the artificial intelligence model, means for calculating an optimal delivery route and transportation means using the artificial intelligence model and notifying a user, means for notifying the user of the optimal delivery route and transportation means in real time via the user's smart device, means for collecting behavior related to delivery results and problems from the user, and means for retraining the artificial intelligence model based on the collected behavior data, thereby enabling the selection of efficient and cost-effective delivery routes in a logistics center.

[1076] "Traffic information" refers to all information that affects vehicle movement, such as traffic flow, congestion, and road closure information.

[1077] "Weather information" refers to all information related to weather conditions, such as rain, snow, wind speed, and temperature.

[1078] "Delivery destination business hours information" is information about the hours during which packages can be received.

[1079] "Information about transportation means" refers to information about the operation status and costs of transportation means such as trucks, trains, and ships.

[1080] An "artificial intelligence model" is a machine learning algorithm trained to predict optimal delivery routes and modes of transportation based on data.

[1081] "Real-time data" refers to information that is currently in progress or has recently been updated.

[1082] An "optimal delivery route" is a cargo movement route calculated to minimize cost, time, and environmental impact.

[1083] "Transportation" refers to the means by which cargo is transported to its destination, such as road, rail, or ship.

[1084] "Users" are logistics managers and delivery drivers who use this system to determine delivery routes and transportation methods.

[1085] A "smart device" is a portable electronic device with internet connectivity, such as a smartphone or tablet.

[1086] "Delivery results" refers to information such as the results of the actual delivery and any problems encountered.

[1087] "Behavioral data" is information based on user actions and behavior, and is used to retrain artificial intelligence models.

[1088] The present invention is a system for optimizing delivery routes within a logistics center. This system collects real-time traffic information, weather information, delivery destination business hours, and information on transportation methods, and trains an artificial intelligence model based on this data to propose optimal delivery routes. Specific embodiments are as follows.

[1089] Hardware and software used

[1090] server:

[1091] AWS EC2 instances: Used for data collection, preprocessing, and training the AI ​​model.

[1092] MySQL: Used to store and access data.

[1093] Device:

[1094] Smartphones and tablets: Used as operating devices for logistics drivers and managers.

[1095] Google Maps API: Used to collect traffic information.

[1096] OpenWeatherMap API: Used to collect weather information.

[1097] software:

[1098] TensorFlow: Used to train and optimize artificial intelligence models.

[1099] Data collection and preprocessing

[1100] The server collects real-time traffic information using the Google Maps API, weather information using the OpenWeatherMap API, business hours information for delivery destinations obtained from the customer database, and information on transportation modes collected from various operation statuses and costs. This collected data is normalized and missing values ​​are imputed.

[1101] Training and optimizing artificial intelligence models

[1102] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow. By also using past logistics data, a more accurate predictive model is built. This trained model instantly reflects real-time data and calculates the optimal delivery route and transportation method.

[1103] Notifications and Feedback

[1104] The optimal delivery route and transportation suggestions are sent to the user in real time via the device. For example, a smartphone may display instructions such as, "Section A of the highway is congested, so please select a route that combines rail and truck." Feedback on delivery results and problems is also collected via the device, and the server uses this information to retrain the AI ​​model, continuously improving prediction accuracy.

[1105] Examples of concrete examples and prompts

[1106] As a concrete example, suppose the weather information is "rain" and the traffic information is "highway section A is congested." Based on this information, the system will suggest a detour route.

[1107] Example prompt sentence:

[1108] "If it's raining and there's traffic on Highway A, please suggest the best delivery route."

[1109] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1110] Program processing steps

[1111] Step 1: Collect data

[1112] The server collects traffic information using the Google Maps API, weather information using the OpenWeatherMap API, and business hours of delivery destinations from the customer database, as well as various operational status and cost information.

[1113] Input: Traffic information obtained from API, weather information, opening hours information from customer database, operation status and cost information.

[1114] Output: Raw data summarizing the acquired data.

[1115] Specific operation: Sends requests to each API and receives response data in JSON format. Similarly, queries and retrieves business hours information from the database.

[1116] Step 2: Preprocessing the data

[1117] The server normalizes the collected raw data, imputes missing values, and converts the data format into a format that can be used by machine learning models.

[1118] Input: The raw data collected.

[1119] Output: Preprocessed data.

[1120] Specific operation: Uses standardization logic to convert traffic, weather, and business hours information into a unified format. Imputes missing values ​​with the mean or median.

[1121] Step 3: Training the AI ​​model

[1122] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow, along with historical logistics data.

[1123] Input: Preprocessed data, historical logistics data.

[1124] Output: A trained artificial intelligence model.

[1125] What it does: It feeds data to TensorFlow and runs a training loop using the backpropagation algorithm, selects optimal hyperparameters, and evaluates the model's accuracy.

[1126] Step 4: Update real-time data

[1127] The server receives real-time traffic and weather information, as well as delivery destination business hours, and reflects this information in a trained artificial intelligence model.

[1128] Input: Real-time traffic, weather, and business hours information.

[1129] Output: An updated artificial intelligence model.

[1130] Specific operation: The acquired real-time data is added to the model and reflected in the model calculations. Parameters are fine-tuned as necessary.

[1131] Step 5: Optimization calculation

[1132] The server uses the updated artificial intelligence model to calculate the optimal delivery route and means of transportation.

[1133] Input: Updated artificial intelligence model, real-time data.

[1134] Output: Optimal delivery route and mode of transport.

[1135] Specific operation: Performs inference processing on the model to select the optimal route and transportation method. Formats the results in JSON format or similar.

[1136] Step 6: Notification

[1137] The server notifies the user's smart device of the optimal delivery route and transportation suggestions.

[1138] Input: Optimal delivery route and mode of transport.

[1139] Output: Notification message displayed on the user's terminal.

[1140] Specific operation: A push notification is sent to the smart device, displaying a message such as "Section A of the expressway is congested, so please choose a route that combines rail and truck traffic."

[1141] Step 7: Gather feedback

[1142] The user sends feedback regarding delivery results and problems to the server via the terminal.

[1143] Input: Feedback data from users.

[1144] Output: Feedback data stored on the server.

[1145] Specific operation: Feedback data collected from user terminals is sent to the server and stored in a database.

[1146] Step 8: Retraining the AI ​​model

[1147] The server retrains the artificial intelligence model based on the collected feedback data.

[1148] Input: Feedback data.

[1149] Output: A retrained artificial intelligence model.

[1150] Specific operation: The training process is run again using the feedback data to improve the accuracy of the model.

[1151] These steps enable the logistics center to select efficient and cost-effective delivery routes and transportation methods.

[1152] 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.

[1153] This invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize the logistics network. Furthermore, by combining it with an emotion engine that recognizes user emotions, it aims to improve the user experience. This system is implemented as follows.

[1154] System Configuration

[1155] 1. Data Collection Module

[1156] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[1157] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and operational and cost information for trucks, trains, and ships.

[1158] 2. Data Preprocessing Module

[1159] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[1160] 3. AI model training module

[1161] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[1162] Past logistics data is also used in the training to optimize various parameters.

[1163] 4. Real-time data update module

[1164] The device sends the latest traffic and weather information to the server in real time.

[1165] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[1166] 5. Optimization Algorithm Module

[1167] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[1168] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[1169] 6. Emotion Engine Module

[1170] The server analyzes the user's feedback data and recognizes their emotions, which are then used to retrain the AI ​​model and adjust the optimization results presented.

[1171] The emotion engine extracts and analyzes emotions from users' text and voice feedback and classifies them into categories such as "satisfied," "dissatisfied," and "abnormal."

[1172] 7. Notification Module

[1173] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[1174] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[1175] 8. Feedback Collection Module

[1176] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[1177] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes," "delays occurred at certain times," or "customers were dissatisfied with the service."

[1178] 9. AI model retraining module

[1179] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continually improves the model's predictive accuracy and aids in future deliveries.

[1180] Specific examples

[1181] Consider an e-commerce company making a large volume of deliveries from the Tokyo metropolitan area to the Kansai region. The company needs to consider weather forecasts for heavy rain and traffic conditions on expressways based on traffic information. Feedback and sentiment data collected from drivers are also taken into consideration.

[1182] 1. Data Collection:

[1183] The server obtains current road conditions from the traffic information API and obtains heavy rain forecast information from the weather forecast API.

[1184] The server obtains the delivery destination's business hours information from the customer database.

[1185] 2. Data Preprocessing:

[1186] The server formats and normalizes the collected data and imputes missing values.

[1187] 3. Training the AI ​​model:

[1188] The server trains an AI model based on the pre-processed data to predict the optimal delivery route and transportation method.

[1189] 4. Run the optimization algorithm:

[1190] The server optimizes delivery routes and transportation methods based on the latest data. For example, if heavy rain is predicted to cause congestion, it will choose a detour route and suggest using both rail and truck.

[1191] 5. Notice:

[1192] The server notifies the user of the calculation results and suggests the optimal delivery method.

[1193] 6. Feedback and Emotion Recognition:

[1194] Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[1195] 7. Retraining the AI ​​model:

[1196] The server uses the feedback and sentiment data to retrain the AI ​​model and improve its prediction accuracy.

[1197] This system utilizes real-time data and sentiment data to maintain a constantly optimized logistics network, which leads to efficient and fast delivery and contributes to an improved user experience.

[1198] The processing flow will be explained below.

[1199] Step 1:

[1200] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[1201] Step 2:

[1202] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[1203] Step 3:

[1204] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[1205] Step 4:

[1206] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[1207] Step 5:

[1208] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[1209] Step 6:

[1210] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[1211] Step 7:

[1212] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[1213] Step 8:

[1214] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[1215] Step 9:

[1216] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[1217] Step 10:

[1218] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[1219] Step 11:

[1220] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[1221] Step 12:

[1222] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[1223] Step 13:

[1224] The server uses the collected feedback data to retrain the AI ​​model, which improves the model's prediction accuracy and helps with future deliveries.

[1225] Step 14:

[1226] The server operates an emotion engine based on the user's feedback data. The emotion engine analyzes the user's emotions from text and voice data and classifies them into emotions such as "satisfied," "dissatisfied," and "abnormal."

[1227] Step 15:

[1228] The server retrains the AI ​​model based on the results of the emotion analysis, enabling optimization based on user emotions.

[1229] Step 16:

[1230] The server adjusts the optimal delivery route and transportation proposals based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, further improvements will be identified and reflected in the next optimization.

[1231] Example 2

[1232] 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."

[1233] In logistics networks, it is important to select efficient delivery routes and transportation methods. However, conventional systems lack the means to integrate and optimize data related to traffic information, weather information, delivery destination business hours, and transportation methods. As a result, costs and delays are likely to increase. In addition, re-optimization is not performed taking user feedback and emotions into account, making it difficult to improve customer satisfaction.

[1234] 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.

[1235] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training a machine learning model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the machine learning model, means for optimizing delivery routes and transportation means based on the latest data, means for proposing optimal delivery routes and transportation means, means for collecting user feedback data and performing sentiment analysis, and means for retraining the machine learning model using the feedback data and sentiment data. This makes it possible to maintain a constantly optimized logistics network by utilizing real-time data and user feedback, thereby enabling efficient and fast delivery and improved customer satisfaction.

[1236] "Traffic information" refers to data including road congestion status, traffic volume, accident information, and so on.

[1237] "Weather information" is data including current weather conditions, forecasts, temperature, probability of precipitation, etc.

[1238] "Delivery destination business hours information" is data indicating the hours during which each delivery destination is open.

[1239] "Transportation data" refers to data that includes information on the operation status, costs, and available transportation means such as trucks, trains, and ships.

[1240] "Means for training machine learning models using preprocessed data" refers to a mechanism for formatting raw data and training a model using a machine learning algorithm.

[1241] "Means of receiving real-time data and immediately reflecting it in the machine learning model" refers to a mechanism that receives the latest information in real time and updates the predictions of the machine learning model based on this information.

[1242] "Means for optimizing delivery routes and transportation methods based on the latest data" refers to an algorithm that uses newly collected data to determine the most efficient delivery routes and transportation methods.

[1243] "Means for proposing optimal delivery routes and transportation methods" is a function that presents the calculated optimization results to the user.

[1244] The "means for collecting user feedback data and performing emotion analysis" is a technology for collecting feedback from users and analyzing the emotions contained therein.

[1245] "Means for retraining machine learning models using feedback data and emotion data" refers to a mechanism for retraining machine learning models to improve their accuracy using collected feedback and emotion data.

[1246] This system optimizes logistics networks by collecting data on traffic, weather, delivery destination business hours, and transportation methods, and utilizes machine learning models. Furthermore, it combines an emotion engine that recognizes user emotions to improve the user experience.

[1247] System Configuration and Operation

[1248] Data collection

[1249] The server retrieves traffic information from the Google Maps API, weather information from the OpenWeatherMap API, and delivery location business hours information from a customer database (e.g., MySQL database), thereby comprehensively collecting data on transportation modes.

[1250] Data Preprocessing

[1251] The server uses the Python Pandas library to format and normalize the collected data, and imputes missing values ​​using the fillna function.

[1252] AI model training

[1253] The server uses the preprocessed data to train a machine learning model using libraries like TensorFlow and PyTorch, and also uses historical logistics data to set optimal parameters for the model.

[1254] Real-time data updates

[1255] The device sends the latest traffic and weather information to the server in real time using the MQTT protocol. The server then immediately applies the received real-time data to the machine learning model, providing the latest prediction results.

[1256] Delivery route and transportation optimization

[1257] The server uses the latest data to optimize delivery routes and transportation methods, using combinatorial optimization algorithms (e.g., genetic algorithms) that take into account multiple criteria, including cost, time, and environmental impact.

[1258] Information Notification

[1259] The server notifies the user's device of the calculated optimal delivery route and transportation suggestions, for example, by using a push notification API to send the optimization results to the mobile device.

[1260] Feedback and Emotion Recognition

[1261] The user provides feedback on delivery results and problems to the server via the terminal. This feedback includes emotional data and is analyzed by the emotion engine. The feedback is entered in text format using the terminal's feedback form.

[1262] AI model retraining

[1263] The server uses the collected feedback and sentiment data to retrain the machine learning model, which improves the model's predictive accuracy and allows for the continuous maintenance of an optimal logistics network.

[1264] Specific examples

[1265] When an e-commerce company makes a large delivery from the Tokyo metropolitan area to the Kansai region, it must take into account forecasts of heavy rain and traffic congestion on highways, as well as feedback and sentiment data collected from drivers.

[1266] Data collection: The server obtains current road conditions from the traffic information API, heavy rain forecast information from the weather forecast API, and business hours information for delivery destinations from the customer database.

[1267] Data preprocessing: The server formats and normalizes the collected data and imputes missing values.

[1268] Training the AI ​​model: The server trains the AI ​​model based on the pre-processed data to predict the optimal delivery route and transportation method.

[1269] Execution of optimization algorithm: The server proposes the best delivery route and transportation method based on the latest data.

[1270] Notification: The server notifies the user of the calculation results and suggests the optimal delivery method.

[1271] Feedback and emotion recognition: Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[1272] Retraining the AI ​​model: The server uses the feedback and sentiment data to retrain the AI ​​model to improve prediction accuracy.

[1273] Example prompt sentence:

[1274] "Generate Python code to develop a logistics network optimization system based on traffic and weather information. The system will use real-time data to suggest optimal delivery routes and analyze user feedback and sentiment data to retrain the AI ​​model."

[1275] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1276] Program processing flow

[1277] Step 1:

[1278] The server collects traffic information from the Google Maps API. Specifically, it sends an HTTP request to the Google Maps API and receives current road condition data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the obtained traffic information data.

[1279] Step 2:

[1280] The server collects weather information from the OpenWeatherMap API. Specifically, it sends an HTTP request to the OpenWeatherMap API and receives weather forecast data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the retrieved weather information data.

[1281] Step 3:

[1282] The server retrieves the delivery destination's business hours information from the customer database. Specifically, it executes a MySQL query to extract the required business hours information from the database. The input is the SQL query, and the output is the retrieved business hours data.

[1283] Step 4:

[1284] The server formats and normalizes the collected traffic, weather, and business hours information. Specifically, it uses Python's Pandas library to create a data frame, standardize the data, and impute missing values. The input is raw data, and the output is formatted and normalized data.

[1285] Step 5:

[1286] The server trains a machine learning model using the reshaped and normalized data. Specifically, it uses the TensorFlow library to build a neural network model and optimizes the model's parameters through backpropagation. The input is the preprocessed data, and the output is the trained model.

[1287] Step 6:

[1288] The terminal sends the latest traffic and weather information to the server in real time. Specifically, the terminal continuously transmits real-time data using the MQTT protocol. The input is the real-time data, and the output is the updated server database.

[1289] Step 7:

[1290] The server updates the machine learning model based on the latest real-time data to optimize delivery routes and transportation methods. Specifically, it runs a combinatorial optimization algorithm using the latest data to generate an optimal logistics plan. The input is the latest real-time data and the existing model, and the output is a proposal for an optimized delivery route and transportation method.

[1291] Step 8:

[1292] The server notifies the user's device of the optimal delivery route and transportation method proposal. Specifically, it uses a push notification API to send the proposal to the user. The input is the optimized logistics plan, and the output is a notification sent to the user's device.

[1293] Step 9:

[1294] The user provides feedback on delivery results and problems to the server via the terminal. Specifically, the user enters the feedback in text format using the terminal's feedback form and sends it to the server. The input is the user's feedback data, and the output is the feedback data saved on the server.

[1295] Step 10:

[1296] The server retrains the machine learning model using the feedback data and the emotion data. Specifically, the server performs retraining using a dataset containing the collected feedback and emotion data. The input is the feedback and emotion data, and the output is the retrained model.

[1297] (Application example 2)

[1298] 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."

[1299] In modern logistics systems, obtaining real-time traffic and weather information is a given, and proposing optimal delivery routes is also important. However, in addition to these, flexible responses that take into account user emotional feedback are also required. There is a lack of systems that can make such fine adjustments, making it difficult to build efficient logistics networks.

[1300] 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.

[1301] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training an AI model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the AI ​​model, means for proposing optimal delivery routes and transportation means, means for collecting user emotional feedback using an emotion recognition function, and means for sending notifications to users, thereby enabling optimization of a logistics network that effectively incorporates real-time data and emotional feedback.

[1302] "Means for collecting traffic information" refers to a device or system that has the function of collecting data on road conditions, such as traffic conditions and congestion information.

[1303] A "means for collecting weather information" is a device or system that has the function of collecting data related to local weather, such as weather conditions and weather forecasts.

[1304] The "means for collecting business hours information of delivery destinations" refers to a device or system that has the function of collecting data related to business hours, such as opening and closing times of delivery destinations.

[1305] "Means for collecting data on transportation means" refers to devices or systems that have the function of collecting operational status and cost information on various transportation means, such as trucks, trains, and ships.

[1306] A "means for training an AI model using preprocessed data" is a device or system that has the function of normalizing collected data, filling in missing values, and then processing the data to train an AI model.

[1307] "Means for receiving real-time data and immediately reflecting it in an artificial intelligence model" refers to a device or system that has the function of receiving the latest data obtained in real time and immediately applying that data to an artificial intelligence model.

[1308] A "means for proposing optimal delivery routes and transportation means" is a device or system that has the function of calculating and proposing efficient and optimal delivery routes and transportation means using a trained artificial intelligence model.

[1309] The "means for collecting user emotional feedback using an emotion recognition function" refers to a device or system that has the technology to analyze text or voice feedback from a user and recognize their emotional state.

[1310] The "means for sending notifications to the user" refers to a device or system that has the function of sending emails or app notifications to notify the user of the calculation results or suggestions.

[1311] A "means for retraining an AI model based on emotional feedback" is a device or system that has the function of retraining an AI model to improve its predictive ability using emotional data collected from users.

[1312] The present invention is a system for optimizing logistics networks. The system collects data on traffic, weather, delivery destination business hours, and transportation methods, and uses the preprocessed data to train an artificial intelligence model (AI model). The method is detailed below.

[1313] System Configuration

[1314] 1. Data Collection Module

[1315] The server collects necessary data from traffic information APIs, weather information APIs, customer databases, etc. Specifically, it collects nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and transportation operation status and cost information.

[1316] 2. Data Preprocessing Module

[1317] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[1318] 3. AI model training module

[1319] The server uses the preprocessed data to train an AI model, using a deep learning framework such as TensorFlow or Keras.

[1320] 4. Real-time data update module

[1321] The device sends the latest traffic and weather information to the server in real time, and the server immediately reflects the received real-time data in the AI ​​model.

[1322] 5. Optimization Algorithm Module

[1323] The server uses the latest data to optimize delivery routes and transportation methods, implementing optimization algorithms using Python and R, with cost, time, and environmental impact as criteria.

[1324] 6. Emotion Engine Module

[1325] The server analyzes the user's feedback data and recognizes their emotions. It uses a natural language processing library such as TextBlob to extract emotions from the user's text feedback and classify them as "Satisfied," "Dissatisfied," or "Abnormal."

[1326] 7. Notification Module

[1327] The server then notifies the user (delivery driver or logistics manager) of the optimal delivery route and transportation method proposal via email via the SMTP server.

[1328] 8. Feedback Collection Module

[1329] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[1330] 9. AI model retraining module

[1331] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continuously improves its prediction accuracy for future deliveries.

[1332] Specific examples

[1333] For example, when making a large delivery from the Tokyo metropolitan area to the Kansai region, the server obtains current road conditions through a traffic information API and heavy rain forecast information from a weather information API. The collected data is preprocessed using Pandas and Sklearn. An AI model (built using TensorFlow and Keras) is then trained based on the preprocessed data. Real-time data updates are received using Flask and reflected in the model. The trained model calculates the optimal delivery route and transportation method using optimization algorithms using Python and R, and notifies the user via a notification module. User feedback and sentiment data are analyzed using TextBlob, and the AI ​​model is retrained.

[1334] Prompt Sentence Examples

[1335] "Please suggest the best delivery route and transportation method based on current traffic and weather information. Also, please take into account the user's emotional feedback on the delivery results to retrain your AI model."

[1336] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1337] Step 1:

[1338] Data collection

[1339] The server collects data from a traffic information API, a weather information API, and a customer database. Specifically, it uses the API to obtain road congestion information, weather forecasts, opening hours for each delivery location, and the operation status and cost information of various transportation modes. The inputs are API requests and database queries, and the output is a set of selected data.

[1340] Step 2:

[1341] Data Preprocessing

[1342] The server uses the Pandas library to reshape and normalize the collected data and impute missing values, for example, imputing the mean or median for missing data points and min-max scaling for numerical data. The input is the raw data collected in the previous step, and the output is the preprocessed dataset.

[1343] Step 3:

[1344] Training an AI model

[1345] The server trains an AI model using the preprocessed data using the TensorFlow and Keras libraries. Specifically, it splits the dataset into training data and validation data, and generates and trains the model using a deep learning algorithm. The input is the preprocessed dataset, and the output is the trained AI model.

[1346] Step 4:

[1347] Real-time data updates

[1348] The device obtains the latest traffic and weather information in real time and sends it to the server. The server immediately updates the AI ​​model based on the received real-time data. The input is new information obtained in real time, and the output is an AI model that reflects the latest data.

[1349] Step 5:

[1350] Running the optimization algorithm

[1351] The server uses a trained AI model to calculate and propose optimal delivery routes and transportation methods. The algorithm uses Python and R to evaluate cost, time, and environmental impact. The input is the latest AI model and a preprocessed dataset, and the output is the optimal delivery plan and transportation method.

[1352] Step 6:

[1353] Collecting emotional feedback

[1354] The user reports feedback and emotional data about the delivery results to the server via their terminal. Specifically, text and voice data are input as feedback. The input is the feedback data from the user, and the output is emotional data that has been classified and stored by the server.

[1355] Step 7:

[1356] Emotion data analysis and notification

[1357] The server analyzes the user's emotional feedback using natural language processing libraries such as TextBlob and classifies it into emotional categories. Based on the analysis results, an optimized delivery route and transportation method are notified. The input is the user's feedback data, and the output is a next optimization proposal including the emotional data.

[1358] Step 8:

[1359] Retraining AI models

[1360] The server uses the collected feedback and emotion data to retrain the AI ​​model, which continuously improves the model's prediction accuracy and helps with the next delivery plan. The input is the feedback and emotion data, and the output is an updated AI model.

[1361] 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.

[1362] 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.

[1363] 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.

[1364] [Fourth embodiment]

[1365] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1366] 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.

[1367] 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).

[1368] 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.

[1369] 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.

[1370] 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).

[1371] 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.

[1372] 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.

[1373] 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.

[1374] 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.

[1375] 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.

[1376] 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.

[1377] 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."

[1378] The present invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize a logistics network. This system is implemented as follows.

[1379] System Configuration

[1380] 1. Data Collection Module

[1381] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[1382] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours at each delivery destination, and operational and cost information for trucks, trains, and ships.

[1383] 2. Data Preprocessing Module

[1384] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[1385] 3. AI model training module

[1386] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[1387] Past logistics data is also used in the training to optimize various parameters.

[1388] 4. Real-time data update module

[1389] The device sends the latest traffic and weather information to the server in real time.

[1390] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[1391] 5. Optimization Algorithm Module

[1392] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[1393] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[1394] 6. Notification Module

[1395] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[1396] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[1397] 7. Feedback Collection Module

[1398] The user provides feedback on the actual delivery results and problems to the server via the terminal.

[1399] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes" or "delays occur during certain times of the day."

[1400] 8. AI model retraining module

[1401] The server uses the collected feedback data to retrain the AI ​​model, which continuously improves the model's predictive accuracy and helps with future deliveries.

[1402] Specific examples

[1403] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[1404] 1. Data Collection:

[1405] The server collects weather and traffic information from various APIs. For example, it checks that "traffic congestion is predicted due to heavy rain on Expressway Section A."

[1406] 2. Data Preprocessing:

[1407] The server formats the collected data, imputes missing values, and normalizes it as needed.

[1408] 3. Training the AI ​​model:

[1409] The server trains the AI ​​model using past logistics data and newly collected data.

[1410] 4. Run the optimization algorithm:

[1411] The server uses trained AI models to calculate optimal delivery routes and modes of transport, for example, choosing detours when heavy rain is forecast and even suggesting a combination of rail and truck transport.

[1412] 5. Notice:

[1413] The server notifies the user of the calculation results and instructs the user on the optimal delivery method.

[1414] 6. Feedback:

[1415] Once completed, the user reports the delivery results from their device to the server, which uses the results as data to improve the accuracy of the AI ​​model.

[1416] The above is an embodiment of the logistics network information optimization system based on the present invention. This system utilizes real-time data to constantly maintain an optimal logistics network and achieve efficient delivery.

[1417] The processing flow will be explained below.

[1418] Step 1:

[1419] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[1420] Step 2:

[1421] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[1422] Step 3:

[1423] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[1424] Step 4:

[1425] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[1426] Step 5:

[1427] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[1428] Step 6:

[1429] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[1430] Step 7:

[1431] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[1432] Step 8:

[1433] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[1434] Step 9:

[1435] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[1436] Step 10:

[1437] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[1438] Step 11:

[1439] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[1440] Step 12:

[1441] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[1442] Step 13:

[1443] The server uses the collected feedback data to retrain the AI ​​model, improving its prediction accuracy for future deliveries.

[1444] This is the specific processing flow of the AI-based logistics network information optimization system. By using this system, an optimized logistics network can be maintained at all times, enabling efficient and fast delivery.

[1445] Example 1

[1446] 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."

[1447] In the logistics industry, it is important to appropriately collect information on traffic conditions, weather, delivery destination business hours, and transportation methods, and to select the optimal delivery route and transportation method based on this data. However, it is difficult to reflect this data in real time and operate it efficiently. Furthermore, there is a lack of a mechanism to collect user feedback and continuously improve the model, which means that delivery efficiency and cost optimization cannot be fully achieved.

[1448] 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.

[1449] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation methods, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for receiving real-time data and immediately reflecting it in the AI ​​model, means for proposing an optimal delivery route and transportation method, means for notifying the user of the optimized delivery route and transportation method, means for collecting feedback data from users, and means for retraining the AI ​​model using the feedback data. This allows for traffic conditions, weather, and business hours of delivery destinations to be reflected in real time, making it possible to always select the optimal delivery route and transportation method. Furthermore, the model can be continuously improved using user feedback, thereby achieving logistics efficiency and cost reduction.

[1450] "Traffic information" refers to data related to traffic movement, such as road congestion, traffic jam information, and accident information.

[1451] "Weather information" refers to weather-related data such as weather forecasts, precipitation, wind speed, and temperature.

[1452] "Delivery destination business hours information" refers to data relating to the hours during which the delivery destination facility is open.

[1453] "Data on transportation means" refers to data on transportation means used in logistics, such as the operating status and operating costs of trucks, trains, ships, etc.

[1454] "Preprocessing" refers to the process of normalizing collected data, filling in missing values, and converting it into a format that is easy for an AI model to learn.

[1455] An "artificial intelligence model" is a model that uses machine learning to make predictions and classifications from data.

[1456] "Real-time data" refers to data that is collected immediately to reflect ongoing situations or events.

[1457] The "optimal delivery route" is the most efficient delivery route selected to improve logistics efficiency.

[1458] The "optimal means of transportation" refers to the most efficient and effective transportation method selected to improve logistics efficiency.

[1459] "Users" refer to delivery drivers and logistics managers who use the system to carry out delivery tasks.

[1460] "Feedback Data" refers to data provided by a user to report actual delivery results or problems.

[1461] This invention is a system that collects data on traffic information, weather information, business hours of delivery destinations, and transportation methods, and optimizes a logistics network using an AI model. The system includes a server, a terminal, and a user.

[1462] Hardware and software used

[1463] The server handles data collection, preprocessing, AI model training, real-time updates, optimization algorithm execution, notifications, feedback collection, and AI model retraining. Specific software used is the Python Requests library for data collection, Pandas for data preprocessing, and TensorFlow and PyTorch for AI model training.

[1464] The device is used to send real-time traffic and weather information to a server. For example, a delivery driver's smartphone or tablet sends GPS data and traffic information to the server.

[1465] The user receives suggestions from the system for optimal delivery routes and transportation methods, and then performs the actual delivery. After completing the delivery, the user provides feedback to the server via their terminal.

[1466] Specific examples

[1467] Consider the case of an e-commerce company making a large delivery from the Tokyo metropolitan area to the Kansai region. This company needs to take into account weather forecasts for heavy rain and traffic conditions on expressways based on traffic information.

[1468] The server collects data from traffic information APIs (e.g., Google Maps API) and weather information APIs (e.g., OpenWeatherMap API). The server periodically sends requests to these API endpoints and analyzes the JSON data received as a response. For example, it verifies that "traffic congestion is predicted due to heavy rain on section A of the highway."

[1469] The server preprocesses the collected data using the Pandas library, filling in missing weather information with data from the previous day and normalizing all numerical data to the same scale.

[1470] The server then uses the preprocessed data to train an AI model using TensorFlow or PyTorch. For example, it creates a model that predicts the optimal route for trucks based on past logistics data. The server improves prediction accuracy by training the model using both past data and newly collected data.

[1471] The device then sends the latest traffic and weather information to the server in real time. The delivery driver's smartphone then sends their current location and traffic congestion information to the server, and the server immediately updates the AI ​​model with the received real-time data, updating the forecast.

[1472] The server uses a trained AI model to calculate the optimal delivery route and transportation method, and notifies the user's device. For example, it provides specific instructions such as "If heavy rain is predicted, select a detour route and suggest using both rail and truck."

[1473] After completing the delivery, the user reports the delivery result to the server from their device, which serves as feedback data. The server uses the collected feedback data to retrain the AI ​​model, thereby continuously improving the model's prediction accuracy.

[1474] Prompt Sentence Examples

[1475] "Please suggest the best delivery route to the Kansai region."

[1476] "Please tell me the delivery route in bad weather."

[1477] In this way, the system utilizes real-time data to maintain an optimal logistics network at all times.

[1478] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1479] Step 1:

[1480] Data collection

[1481] The server collects information from traffic information APIs, weather information APIs, customer databases, etc. Specifically, the server periodically sends requests to API endpoints and analyzes the JSON data received as a response.

[1482] Input: Traffic API, Weather API, Data from customer database

[1483] Output: Analyzed traffic, weather, delivery opening hours, and transportation data

[1484] Step 2:

[1485] Data Preprocessing

[1486] The server preprocesses the collected data, for example, by imputing missing data and normalizing numerical data. It uses the Python Pandas library to format the data and impute missing values.

[1487] Input: Parsed data

[1488] Output: Preprocessed data

[1489] Step 3:

[1490] Training an AI model

[1491] The server uses the preprocessed data to train an AI model, specifically by building a neural network using TensorFlow or PyTorch, inputting the data, and optimizing the model.

[1492] Input: Preprocessed data

[1493] Output: A trained AI model

[1494] Step 4:

[1495] Real-time data updates

[1496] The device sends real-time traffic and weather information to the server. For example, a delivery driver's mobile device uses GPS data to send current location and traffic information to the server.

[1497] Input: Real-time traffic and weather information

[1498] Output: Real-time data sent to the server

[1499] Step 5:

[1500] Running the optimization algorithm

[1501] The server uses the latest data to optimize delivery routes and transportation methods, using Python's Scipy library and other optimization libraries to solve complex optimization problems.

[1502] Input: Real-time data and pre-trained AI models

[1503] Output: Optimal delivery route and transportation method suggestions

[1504] Step 6:

[1505] notification

[1506] The server notifies the user's device of the optimal delivery route and transportation method, specifically by sending a pop-up notification or email to the delivery driver or logistics manager.

[1507] Input: Optimal delivery route and transportation suggestions

[1508] Output: User notification

[1509] Step 7:

[1510] Collecting feedback

[1511] Users can report actual delivery results and problems to the server via their devices, specifically by reporting problems using a mobile app or web interface.

[1512] Input: Actual delivery results and issues

[1513] Output: Feedback data sent to the server

[1514] Step 8:

[1515] Retraining AI models

[1516] The server uses the collected feedback data to retrain the AI ​​model, retraining it with new data and comparing it with the previous model to evaluate its accuracy.

[1517] Input: Feedback data

[1518] Output: Retrained AI model

[1519] (Application example 1)

[1520] 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."

[1521] In recent years, the logistics industry has become increasingly difficult to create efficient delivery plans due to a wide variety of delivery destinations and variable factors such as weather and traffic conditions. Conventional methods make it difficult to update information in real time and select optimal delivery routes, resulting in increased delivery costs and environmental impact. To solve these issues, a system is needed that can collect information in real time and instantly calculate and propose optimal delivery routes.

[1522] 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.

[1523] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting information on transportation means, means for normalizing the collected traffic information, weather information, business hours of delivery destinations, and information on transportation means, means for imputing missing values, and converting the collected information on traffic information, weather information, business hours of delivery destinations, and transportation means into a format usable for training an artificial intelligence model, means for training the artificial intelligence model using the preprocessed data, means for receiving real-time traffic information, weather information, business hours of delivery destinations, and information on transportation means and immediately reflecting the information in the artificial intelligence model, means for calculating an optimal delivery route and transportation means using the artificial intelligence model and notifying a user, means for notifying the user of the optimal delivery route and transportation means in real time via the user's smart device, means for collecting behavior related to delivery results and problems from the user, and means for retraining the artificial intelligence model based on the collected behavior data, thereby enabling the selection of efficient and cost-effective delivery routes in a logistics center.

[1524] "Traffic information" refers to all information that affects vehicle movement, such as traffic flow, congestion, and road closure information.

[1525] "Weather information" refers to all information related to weather conditions, such as rain, snow, wind speed, and temperature.

[1526] "Delivery destination business hours information" is information about the hours during which packages can be received.

[1527] "Information about transportation means" refers to information about the operation status and costs of transportation means such as trucks, trains, and ships.

[1528] An "artificial intelligence model" is a machine learning algorithm trained to predict optimal delivery routes and modes of transportation based on data.

[1529] "Real-time data" refers to information that is currently in progress or has recently been updated.

[1530] An "optimal delivery route" is a cargo movement route calculated to minimize cost, time, and environmental impact.

[1531] "Transportation" refers to the means by which cargo is transported to its destination, such as road, rail, or ship.

[1532] "Users" are logistics managers and delivery drivers who use this system to determine delivery routes and transportation methods.

[1533] A "smart device" is a portable electronic device with internet connectivity, such as a smartphone or tablet.

[1534] "Delivery results" refers to information such as the results of the actual delivery and any problems encountered.

[1535] "Behavioral data" is information based on user actions and behavior, and is used to retrain artificial intelligence models.

[1536] The present invention is a system for optimizing delivery routes within a logistics center. This system collects real-time traffic information, weather information, delivery destination business hours, and information on transportation methods, and trains an artificial intelligence model based on this data to propose optimal delivery routes. Specific embodiments are as follows.

[1537] Hardware and software used

[1538] server:

[1539] AWS EC2 instances: Used for data collection, preprocessing, and training the AI ​​model.

[1540] MySQL: Used to store and access data.

[1541] Device:

[1542] Smartphones and tablets: Used as operating devices for logistics drivers and managers.

[1543] Google Maps API: Used to collect traffic information.

[1544] OpenWeatherMap API: Used to collect weather information.

[1545] software:

[1546] TensorFlow: Used to train and optimize artificial intelligence models.

[1547] Data collection and preprocessing

[1548] The server collects real-time traffic information using the Google Maps API, weather information using the OpenWeatherMap API, business hours information for delivery destinations obtained from the customer database, and information on transportation modes collected from various operation statuses and costs. This collected data is normalized and missing values ​​are imputed.

[1549] Training and optimizing artificial intelligence models

[1550] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow. By also using past logistics data, a more accurate predictive model is built. This trained model instantly reflects real-time data and calculates the optimal delivery route and transportation method.

[1551] Notifications and Feedback

[1552] The optimal delivery route and transportation suggestions are sent to the user in real time via the device. For example, a smartphone may display instructions such as, "Section A of the highway is congested, so please select a route that combines rail and truck." Feedback on delivery results and problems is also collected via the device, and the server uses this information to retrain the AI ​​model, continuously improving prediction accuracy.

[1553] Examples of concrete examples and prompts

[1554] As a concrete example, suppose the weather information is "rain" and the traffic information is "highway section A is congested." Based on this information, the system will suggest a detour route.

[1555] Example prompt sentence:

[1556] "If it's raining and there's traffic on Highway A, please suggest the best delivery route."

[1557] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1558] Program processing steps

[1559] Step 1: Collect data

[1560] The server collects traffic information using the Google Maps API, weather information using the OpenWeatherMap API, and business hours of delivery destinations from the customer database, as well as various operational status and cost information.

[1561] Input: Traffic information obtained from API, weather information, opening hours information from customer database, operation status and cost information.

[1562] Output: Raw data summarizing the acquired data.

[1563] Specific operation: Sends requests to each API and receives response data in JSON format. Similarly, queries and retrieves business hours information from the database.

[1564] Step 2: Preprocessing the data

[1565] The server normalizes the collected raw data, imputes missing values, and converts the data format into a format that can be used by machine learning models.

[1566] Input: The raw data collected.

[1567] Output: Preprocessed data.

[1568] Specific operation: Uses standardization logic to convert traffic, weather, and business hours information into a unified format. Imputes missing values ​​with the mean or median.

[1569] Step 3: Training the AI ​​model

[1570] The server uses the preprocessed data to train an artificial intelligence model using TensorFlow, along with historical logistics data.

[1571] Input: Preprocessed data, historical logistics data.

[1572] Output: A trained artificial intelligence model.

[1573] What it does: It feeds data to TensorFlow and runs a training loop using the backpropagation algorithm, selects optimal hyperparameters, and evaluates the model's accuracy.

[1574] Step 4: Update real-time data

[1575] The server receives real-time traffic and weather information, as well as delivery destination business hours, and reflects this information in a trained artificial intelligence model.

[1576] Input: Real-time traffic, weather, and business hours information.

[1577] Output: An updated artificial intelligence model.

[1578] Specific operation: The acquired real-time data is added to the model and reflected in the model calculations. Parameters are fine-tuned as necessary.

[1579] Step 5: Optimization calculation

[1580] The server uses the updated artificial intelligence model to calculate the optimal delivery route and means of transportation.

[1581] Input: Updated artificial intelligence model, real-time data.

[1582] Output: Optimal delivery route and mode of transport.

[1583] Specific operation: Performs inference processing on the model to select the optimal route and transportation method. Formats the results in JSON format or similar.

[1584] Step 6: Notification

[1585] The server notifies the user's smart device of the optimal delivery route and transportation suggestions.

[1586] Input: Optimal delivery route and mode of transport.

[1587] Output: Notification message displayed on the user's terminal.

[1588] Specific operation: A push notification is sent to the smart device, displaying a message such as "Section A of the expressway is congested, so please choose a route that combines rail and truck traffic."

[1589] Step 7: Gather feedback

[1590] The user sends feedback regarding delivery results and problems to the server via the terminal.

[1591] Input: Feedback data from users.

[1592] Output: Feedback data stored on the server.

[1593] Specific operation: Feedback data collected from user terminals is sent to the server and stored in a database.

[1594] Step 8: Retraining the AI ​​model

[1595] The server retrains the artificial intelligence model based on the collected feedback data.

[1596] Input: Feedback data.

[1597] Output: A retrained artificial intelligence model.

[1598] Specific operation: The training process is run again using the feedback data to improve the accuracy of the model.

[1599] These steps enable the logistics center to select efficient and cost-effective delivery routes and transportation methods.

[1600] 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.

[1601] This invention is a system that collects data on traffic information, weather information, delivery destination business hours, and transportation methods, and uses an AI model to optimize the logistics network. Furthermore, by combining it with an emotion engine that recognizes user emotions, it aims to improve the user experience. This system is implemented as follows.

[1602] System Configuration

[1603] 1. Data Collection Module

[1604] The server collects the necessary data from traffic information APIs, weather information APIs, customer databases, etc.

[1605] Specifically, it collects information such as nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and operational and cost information for trucks, trains, and ships.

[1606] 2. Data Preprocessing Module

[1607] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[1608] 3. AI model training module

[1609] The server uses the pre-processed data to train an AI model, which is then able to predict optimal transportation routes and modes.

[1610] Past logistics data is also used in the training to optimize various parameters.

[1611] 4. Real-time data update module

[1612] The device sends the latest traffic and weather information to the server in real time.

[1613] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions to the latest version.

[1614] 5. Optimization Algorithm Module

[1615] The server uses the latest data to optimize delivery routes and transportation methods, taking into account multiple criteria including cost, time, and environmental impact.

[1616] For example, it is possible to set whether to prioritize "cost reduction" or "shortest time."

[1617] 6. Emotion Engine Module

[1618] The server analyzes the user's feedback data and recognizes their emotions, which are then used to retrain the AI ​​model and adjust the optimization results presented.

[1619] The emotion engine extracts and analyzes emotions from users' text and voice feedback and classifies them into categories such as "satisfied," "dissatisfied," and "abnormal."

[1620] 7. Notification Module

[1621] The server notifies the user's (delivery driver or logistics manager's) terminal of the optimal delivery route and transportation method suggestions.

[1622] A specific example is instructions such as "Use rail for deliveries from Tokyo to Osaka Prefecture, and trucks for deliveries within Osaka Prefecture."

[1623] 8. Feedback Collection Module

[1624] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[1625] For example, they report specific problems such as "traffic congestion is likely to occur on certain routes," "delays occurred at certain times," or "customers were dissatisfied with the service."

[1626] 9. AI model retraining module

[1627] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continually improves the model's predictive accuracy and aids in future deliveries.

[1628] Specific examples

[1629] Consider an e-commerce company making a large volume of deliveries from the Tokyo metropolitan area to the Kansai region. The company needs to consider weather forecasts for heavy rain and traffic conditions on expressways based on traffic information. Feedback and sentiment data collected from drivers are also taken into consideration.

[1630] 1. Data Collection:

[1631] The server obtains current road conditions from the traffic information API and obtains heavy rain forecast information from the weather forecast API.

[1632] The server obtains the delivery destination's business hours information from the customer database.

[1633] 2. Data Preprocessing:

[1634] The server formats and normalizes the collected data and imputes missing values.

[1635] 3. Training the AI ​​model:

[1636] The server trains an AI model based on the pre-processed data to predict the optimal delivery route and transportation method.

[1637] 4. Run the optimization algorithm:

[1638] The server optimizes delivery routes and transportation methods based on the latest data. For example, if heavy rain is predicted to cause congestion, it will choose a detour route and suggest using both rail and truck.

[1639] 5. Notice:

[1640] The server notifies the user of the calculation results and suggests the optimal delivery method.

[1641] 6. Feedback and Emotion Recognition:

[1642] Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[1643] 7. Retraining the AI ​​model:

[1644] The server uses the feedback and sentiment data to retrain the AI ​​model and improve its prediction accuracy.

[1645] This system utilizes real-time data and sentiment data to maintain a constantly optimized logistics network, which leads to efficient and fast delivery and contributes to an improved user experience.

[1646] The processing flow will be explained below.

[1647] Step 1:

[1648] The server sends a request to the traffic information API to obtain the latest traffic data nationwide, allowing users to understand real-time road conditions such as congestion and road closures.

[1649] Step 2:

[1650] The server references the weather information API to obtain weather forecasts for the entire country, paying particular attention to important weather events such as heavy rain and typhoons. This information is necessary for selecting transportation methods and routes.

[1651] Step 3:

[1652] The server retrieves the latest business hours information for each delivery destination from the customer database, allowing the server to determine when deliveries are possible.

[1653] Step 4:

[1654] The server collects various data about transportation modes (cost, time, environmental impact, etc.) This data relates to various transportation modes such as trucks, trains, ships, etc.

[1655] Step 5:

[1656] The server consolidates all collected data and performs preprocessing, normalizing the data, filling in missing values, and structuring it to convert it into a format that is easy for the AI ​​model to learn.

[1657] Step 6:

[1658] The server uses the pre-processed data to train an AI model, which is capable of predicting optimal delivery routes and modes of transportation based on historical logistics data.

[1659] Step 7:

[1660] The device sends the latest traffic and weather information to the server in real time, ensuring that the latest information is always reflected.

[1661] Step 8:

[1662] The server immediately reflects the received real-time data in the AI ​​model and updates the predictions, allowing optimization based on the latest conditions.

[1663] Step 9:

[1664] The server optimizes delivery routes and transportation methods based on the latest data, using multiple criteria to consider cost, time, and environmental impact.

[1665] Step 10:

[1666] The server notifies the user (delivery driver or logistics manager) of the calculation results. For example, it issues specific instructions such as "Use trains for deliveries from Tokyo to Osaka, and trucks for deliveries within Osaka."

[1667] Step 11:

[1668] After the delivery is completed, the user sends feedback to the server using the terminal, reporting specific information such as the delivery time and any problems.

[1669] Step 12:

[1670] The server collects and stores the feedback data in a database, which is used to retrain the AI ​​model.

[1671] Step 13:

[1672] The server uses the collected feedback data to retrain the AI ​​model, which improves the model's prediction accuracy and helps with future deliveries.

[1673] Step 14:

[1674] The server operates an emotion engine based on the user's feedback data. The emotion engine analyzes the user's emotions from text and voice data and classifies them into emotions such as "satisfied," "dissatisfied," and "abnormal."

[1675] Step 15:

[1676] The server retrains the AI ​​model based on the results of the emotion analysis, enabling optimization based on user emotions.

[1677] Step 16:

[1678] The server adjusts the optimal delivery route and transportation proposals based on the analysis results of the emotion engine. For example, if the user expresses dissatisfaction, further improvements will be identified and reflected in the next optimization.

[1679] Example 2

[1680] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1681] In logistics networks, it is important to select efficient delivery routes and transportation methods. However, conventional systems lack the means to integrate and optimize data related to traffic information, weather information, delivery destination business hours, and transportation methods. As a result, costs and delays are likely to increase. In addition, re-optimization is not performed taking user feedback and emotions into account, making it difficult to improve customer satisfaction.

[1682] 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.

[1683] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training a machine learning model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the machine learning model, means for optimizing delivery routes and transportation means based on the latest data, means for proposing optimal delivery routes and transportation means, means for collecting user feedback data and performing sentiment analysis, and means for retraining the machine learning model using the feedback data and sentiment data. This makes it possible to maintain a constantly optimized logistics network by utilizing real-time data and user feedback, thereby enabling efficient and fast delivery and improved customer satisfaction.

[1684] "Traffic information" refers to data including road congestion status, traffic volume, accident information, and so on.

[1685] "Weather information" is data including current weather conditions, forecasts, temperature, probability of precipitation, etc.

[1686] "Delivery destination business hours information" is data indicating the hours during which each delivery destination is open.

[1687] "Transportation data" refers to data that includes information on the operation status, costs, and available transportation means such as trucks, trains, and ships.

[1688] "Means for training machine learning models using preprocessed data" refers to a mechanism for formatting raw data and training a model using a machine learning algorithm.

[1689] "Means of receiving real-time data and immediately reflecting it in the machine learning model" refers to a mechanism that receives the latest information in real time and updates the predictions of the machine learning model based on this information.

[1690] "Means for optimizing delivery routes and transportation methods based on the latest data" refers to an algorithm that uses newly collected data to determine the most efficient delivery routes and transportation methods.

[1691] "Means for proposing optimal delivery routes and transportation methods" is a function that presents the calculated optimization results to the user.

[1692] The "means for collecting user feedback data and performing emotion analysis" is a technology for collecting feedback from users and analyzing the emotions contained therein.

[1693] "Means for retraining machine learning models using feedback data and emotion data" refers to a mechanism for retraining machine learning models to improve their accuracy using collected feedback and emotion data.

[1694] This system optimizes logistics networks by collecting data on traffic, weather, delivery destination business hours, and transportation methods, and utilizes machine learning models. Furthermore, it combines an emotion engine that recognizes user emotions to improve the user experience.

[1695] System Configuration and Operation

[1696] Data collection

[1697] The server retrieves traffic information from the Google Maps API, weather information from the OpenWeatherMap API, and delivery location business hours information from a customer database (e.g., MySQL database), thereby comprehensively collecting data on transportation modes.

[1698] Data Preprocessing

[1699] The server uses the Python Pandas library to format and normalize the collected data, and imputes missing values ​​using the fillna function.

[1700] AI model training

[1701] The server uses the preprocessed data to train a machine learning model using libraries like TensorFlow and PyTorch, and also uses historical logistics data to set optimal parameters for the model.

[1702] Real-time data updates

[1703] The device sends the latest traffic and weather information to the server in real time using the MQTT protocol. The server then immediately applies the received real-time data to the machine learning model, providing the latest prediction results.

[1704] Delivery route and transportation optimization

[1705] The server uses the latest data to optimize delivery routes and transportation methods, using combinatorial optimization algorithms (e.g., genetic algorithms) that take into account multiple criteria, including cost, time, and environmental impact.

[1706] Information Notification

[1707] The server notifies the user's device of the calculated optimal delivery route and transportation suggestions, for example, by using a push notification API to send the optimization results to the mobile device.

[1708] Feedback and Emotion Recognition

[1709] The user provides feedback on delivery results and problems to the server via the terminal. This feedback includes emotional data and is analyzed by the emotion engine. The feedback is entered in text format using the terminal's feedback form.

[1710] AI model retraining

[1711] The server uses the collected feedback and sentiment data to retrain the machine learning model, which improves the model's predictive accuracy and allows for the continuous maintenance of an optimal logistics network.

[1712] Specific examples

[1713] When an e-commerce company makes a large delivery from the Tokyo metropolitan area to the Kansai region, it must take into account forecasts of heavy rain and traffic congestion on highways, as well as feedback and sentiment data collected from drivers.

[1714] Data collection: The server obtains current road conditions from the traffic information API, heavy rain forecast information from the weather forecast API, and business hours information for delivery destinations from the customer database.

[1715] Data preprocessing: The server formats and normalizes the collected data and imputes missing values.

[1716] Training the AI ​​model: The server trains the AI ​​model based on the pre-processed data to predict the optimal delivery route and transportation method.

[1717] Execution of optimization algorithm: The server proposes the best delivery route and transportation method based on the latest data.

[1718] Notification: The server notifies the user of the calculation results and suggests the optimal delivery method.

[1719] Feedback and emotion recognition: Users report delivery results and emotions from their devices, and the server collects and analyzes the data.

[1720] Retraining the AI ​​model: The server uses the feedback and sentiment data to retrain the AI ​​model to improve prediction accuracy.

[1721] Example prompt sentence:

[1722] "Generate Python code to develop a logistics network optimization system based on traffic and weather information. The system will use real-time data to suggest optimal delivery routes and analyze user feedback and sentiment data to retrain the AI ​​model."

[1723] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1724] Program processing flow

[1725] Step 1:

[1726] The server collects traffic information from the Google Maps API. Specifically, it sends an HTTP request to the Google Maps API and receives current road condition data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the obtained traffic information data.

[1727] Step 2:

[1728] The server collects weather information from the OpenWeatherMap API. Specifically, it sends an HTTP request to the OpenWeatherMap API and receives weather forecast data in JSON format. The input is the API request parameters (e.g., location information, time), and the output is the retrieved weather information data.

[1729] Step 3:

[1730] The server retrieves the delivery destination's business hours information from the customer database. Specifically, it executes a MySQL query to extract the required business hours information from the database. The input is the SQL query, and the output is the retrieved business hours data.

[1731] Step 4:

[1732] The server formats and normalizes the collected traffic, weather, and business hours information. Specifically, it uses Python's Pandas library to create a data frame, standardize the data, and impute missing values. The input is raw data, and the output is formatted and normalized data.

[1733] Step 5:

[1734] The server trains a machine learning model using the reshaped and normalized data. Specifically, it uses the TensorFlow library to build a neural network model and optimizes the model's parameters through backpropagation. The input is the preprocessed data, and the output is the trained model.

[1735] Step 6:

[1736] The terminal sends the latest traffic and weather information to the server in real time. Specifically, the terminal continuously transmits real-time data using the MQTT protocol. The input is the real-time data, and the output is the updated server database.

[1737] Step 7:

[1738] The server updates the machine learning model based on the latest real-time data to optimize delivery routes and transportation methods. Specifically, it runs a combinatorial optimization algorithm using the latest data to generate an optimal logistics plan. The input is the latest real-time data and the existing model, and the output is a proposal for an optimized delivery route and transportation method.

[1739] Step 8:

[1740] The server notifies the user's device of the optimal delivery route and transportation method proposal. Specifically, it uses a push notification API to send the proposal to the user. The input is the optimized logistics plan, and the output is a notification sent to the user's device.

[1741] Step 9:

[1742] The user provides feedback on delivery results and problems to the server via the terminal. Specifically, the user enters the feedback in text format using the terminal's feedback form and sends it to the server. The input is the user's feedback data, and the output is the feedback data saved on the server.

[1743] Step 10:

[1744] The server retrains the machine learning model using the feedback data and the emotion data. Specifically, the server performs retraining using a dataset containing the collected feedback and emotion data. The input is the feedback and emotion data, and the output is the retrained model.

[1745] (Application example 2)

[1746] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1747] In modern logistics systems, obtaining real-time traffic and weather information is a given, and proposing optimal delivery routes is also important. However, in addition to these, flexible responses that take into account user emotional feedback are also required. There is a lack of systems that can make such fine adjustments, making it difficult to build efficient logistics networks.

[1748] 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.

[1749] In this invention, the server includes means for collecting traffic information, means for collecting weather information, means for collecting business hours of delivery destinations, means for collecting data on transportation means, means for training an AI model using preprocessed data, means for receiving real-time data and immediately reflecting the data in the AI ​​model, means for proposing optimal delivery routes and transportation means, means for collecting user emotional feedback using an emotion recognition function, and means for sending notifications to users, thereby enabling optimization of a logistics network that effectively incorporates real-time data and emotional feedback.

[1750] "Means for collecting traffic information" refers to a device or system that has the function of collecting data on road conditions, such as traffic conditions and congestion information.

[1751] A "means for collecting weather information" is a device or system that has the function of collecting data related to local weather, such as weather conditions and weather forecasts.

[1752] The "means for collecting business hours information of delivery destinations" refers to a device or system that has the function of collecting data related to business hours, such as opening and closing times of delivery destinations.

[1753] "Means for collecting data on transportation means" refers to devices or systems that have the function of collecting operational status and cost information on various transportation means, such as trucks, trains, and ships.

[1754] A "means for training an AI model using preprocessed data" is a device or system that has the function of normalizing collected data, filling in missing values, and then processing the data to train an AI model.

[1755] "Means for receiving real-time data and immediately reflecting it in an artificial intelligence model" refers to a device or system that has the function of receiving the latest data obtained in real time and immediately applying that data to an artificial intelligence model.

[1756] A "means for proposing optimal delivery routes and transportation means" is a device or system that has the function of calculating and proposing efficient and optimal delivery routes and transportation means using a trained artificial intelligence model.

[1757] The "means for collecting user emotional feedback using an emotion recognition function" refers to a device or system that has the technology to analyze text or voice feedback from a user and recognize their emotional state.

[1758] The "means for sending notifications to the user" refers to a device or system that has the function of sending emails or app notifications to notify the user of the calculation results or suggestions.

[1759] A "means for retraining an AI model based on emotional feedback" is a device or system that has the function of retraining an AI model to improve its predictive ability using emotional data collected from users.

[1760] The present invention is a system for optimizing logistics networks. The system collects data on traffic, weather, delivery destination business hours, and transportation methods, and uses the preprocessed data to train an artificial intelligence model (AI model). The method is detailed below.

[1761] System Configuration

[1762] 1. Data Collection Module

[1763] The server collects necessary data from traffic information APIs, weather information APIs, customer databases, etc. Specifically, it collects nationwide traffic conditions, weather forecasts, business hours of each delivery destination, and transportation operation status and cost information.

[1764] 2. Data Preprocessing Module

[1765] The server preprocesses the collected data, normalizing it, filling in missing values, and converting it into a format that is easy for the AI ​​model to learn.

[1766] 3. AI model training module

[1767] The server uses the preprocessed data to train an AI model, using a deep learning framework such as TensorFlow or Keras.

[1768] 4. Real-time data update module

[1769] The device sends the latest traffic and weather information to the server in real time, and the server immediately reflects the received real-time data in the AI ​​model.

[1770] 5. Optimization Algorithm Module

[1771] The server uses the latest data to optimize delivery routes and transportation methods, implementing optimization algorithms using Python and R, with cost, time, and environmental impact as criteria.

[1772] 6. Emotion Engine Module

[1773] The server analyzes the user's feedback data and recognizes their emotions. It uses a natural language processing library such as TextBlob to extract emotions from the user's text feedback and classify them as "Satisfied," "Dissatisfied," or "Abnormal."

[1774] 7. Notification Module

[1775] The server then notifies the user (delivery driver or logistics manager) of the optimal delivery route and transportation method proposal via email via the SMTP server.

[1776] 8. Feedback Collection Module

[1777] The user provides feedback to the server via the terminal about the actual delivery results and problems, including the user's emotional reaction to the delivery.

[1778] 9. AI model retraining module

[1779] The server uses the collected feedback and sentiment data to retrain the AI ​​model, which continuously improves its prediction accuracy for future deliveries.

[1780] Specific examples

[1781] For example, when making a large delivery from the Tokyo metropolitan area to the Kansai region, the server obtains current road conditions through a traffic information API and heavy rain forecast information from a weather information API. The collected data is preprocessed using Pandas and Sklearn. An AI model (built using TensorFlow and Keras) is then trained based on the preprocessed data. Real-time data updates are received using Flask and reflected in the model. The trained model calculates the optimal delivery route and transportation method using optimization algorithms using Python and R, and notifies the user via a notification module. User feedback and sentiment data are analyzed using TextBlob, and the AI ​​model is retrained.

[1782] Prompt Sentence Examples

[1783] "Please suggest the best delivery route and transportation method based on current traffic and weather information. Also, please take into account the user's emotional feedback on the delivery results to retrain your AI model."

[1784] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1785] Step 1:

[1786] Data collection

[1787] The server collects data from a traffic information API, a weather information API, and a customer database. Specifically, it uses the API to obtain road congestion information, weather forecasts, opening hours for each delivery location, and the operation status and cost information of various transportation modes. The inputs are API requests and database queries, and the output is a set of selected data.

[1788] Step 2:

[1789] Data Preprocessing

[1790] The server uses the Pandas library to reshape and normalize the collected data and impute missing values, for example, imputing the mean or median for missing data points and min-max scaling for numerical data. The input is the raw data collected in the previous step, and the output is the preprocessed dataset.

[1791] Step 3:

[1792] Training an AI model

[1793] The server trains an AI model using the preprocessed data using the TensorFlow and Keras libraries. Specifically, it splits the dataset into training data and validation data, and generates and trains the model using a deep learning algorithm. The input is the preprocessed dataset, and the output is the trained AI model.

[1794] Step 4:

[1795] Real-time data updates

[1796] The device obtains the latest traffic and weather information in real time and sends it to the server. The server immediately updates the AI ​​model based on the received real-time data. The input is new information obtained in real time, and the output is an AI model that reflects the latest data.

[1797] Step 5:

[1798] Running the optimization algorithm

[1799] The server uses a trained AI model to calculate and propose optimal delivery routes and transportation methods. The algorithm uses Python and R to evaluate cost, time, and environmental impact. The input is the latest AI model and a preprocessed dataset, and the output is the optimal delivery plan and transportation method.

[1800] Step 6:

[1801] Collecting emotional feedback

[1802] The user reports feedback and emotional data about the delivery results to the server via their terminal. Specifically, text and voice data are input as feedback. The input is the feedback data from the user, and the output is emotional data that has been classified and stored by the server.

[1803] Step 7:

[1804] Emotion data analysis and notification

[1805] The server analyzes the user's emotional feedback using natural language processing libraries such as TextBlob and classifies it into emotional categories. Based on the analysis results, an optimized delivery route and transportation method are notified. The input is the user's feedback data, and the output is a next optimization proposal including the emotional data.

[1806] Step 8:

[1807] Retraining AI models

[1808] The server uses the collected feedback and emotion data to retrain the AI ​​model, which continuously improves the model's prediction accuracy and helps with the next delivery plan. The input is the feedback and emotion data, and the output is an updated AI model.

[1809] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1810] 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.

[1811] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1812] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1813] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1814] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1815] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1816] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1817] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1818] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1819] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1820] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1821] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1822] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1823] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1824] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1825] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1826] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1827] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1828] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1829] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1830] The following is further disclosed regarding the above embodiment.

[1831] Below is a draft of the patent claims for a logistics network information optimization system using AI.

[1832] (Claim 1)

[1833] a means for collecting traffic information;

[1834] a means for collecting weather information;

[1835] A means for collecting delivery destination business hours information;

[1836] a means of collecting data relating to transportation means;

[1837] means for training an artificial intelligence model using the preprocessed data; and

[1838] A means of receiving real-time data and immediately reflecting it in the artificial intelligence model;

[1839] A system that includes a means to suggest optimal delivery routes and transportation methods.

[1840] (Claim 2)

[1841] a means for calculating an optimal delivery route from the preprocessed data;

[1842] A means for selecting an optimal transportation mode from the preprocessed data;

[1843] a means of assessing environmental impacts from preprocessed data; and

[1844] 10. The system of claim 1, further comprising means for estimating shipping costs from the preprocessed data.

[1845] (Claim 3)

[1846] a means for collecting feedback data from users;

[1847] 10. The system of claim 1, further comprising means for using the feedback data to retrain the artificial intelligence model.

[1848] "Example 1"

[1849] (Claim 1)

[1850] a means for collecting traffic information;

[1851] a means for collecting weather information;

[1852] A means for collecting delivery destination business hours information;

[1853] a means of collecting data relating to transportation means;

[1854] a means for pre-processing the collected data;

[1855] means for training an artificial intelligence model using the preprocessed data; and

[1856] A means of receiving real-time data and immediately reflecting it in the artificial intelligence model;

[1857] A means of proposing optimal delivery routes and transportation methods;

[1858] a means for informing the user of the optimized delivery route and transportation means;

[1859] a means for collecting feedback data from users;

[1860] A system including a means for retraining an artificial intelligence model using feedback data.

[1861] (Claim 2)

[1862] a means for calculating an optimal delivery route from the preprocessed data;

[1863] A means for selecting an optimal transportation mode from the preprocessed data;

[1864] a means of assessing environmental impacts from preprocessed data; and

[1865] 10. The system of claim 1, further comprising means for estimating shipping costs from the preprocessed data.

[1866] (Claim 3)

[1867] a means for collecting feedback data from users;

[1868] 10. The system of claim 1, further comprising means for using the feedback data to retrain the artificial intelligence model.

[1869] "Application Example 1"

[1870] (Claim 1)

[1871] a means for collecting traffic information;

[1872] a means for collecting weather information;

[1873] A means for collecting delivery destination business hours information;

[1874] a means of collecting information regarding the means of transportation;

[1875] A means for normalizing the collected traffic information, weather information, delivery destination business hours information, and transportation information, imputing missing values, and converting the information into a format that can be used to train an artificial intelligence model; and

[1876] means for training an artificial intelligence model using the preprocessed data; and

[1877] A means for receiving real-time traffic information, weather information, delivery destination business hours information, and transportation information and immediately reflecting the information in the artificial intelligence model;

[1878] a means for calculating optimal delivery routes and modes of transport using an artificial intelligence model and notifying the user;

[1879] A means of notifying users of the optimal delivery route and transportation method in real time via their smart devices,

[1880] A means for collecting behavioral information from users regarding delivery results and problems;

[1881] a means for retraining the artificial intelligence model based on the collected behavioral data; and

[1882] A system including:

[1883] (Claim 2)

[1884] a means for calculating an optimal delivery route from the preprocessed data;

[1885] A means for selecting an optimal transportation mode from the preprocessed data;

[1886] a means of assessing environmental impacts from preprocessed data; and

[1887] 10. The system of claim 1, further comprising means for estimating shipping costs from the preprocessed data.

[1888] (Claim 3)

[1889] a means for collecting feedback data from users;

[1890] 10. The system of claim 1, further comprising means for using the feedback data to retrain the artificial intelligence model.

[1891] "Example 2: Combining Emotion Engines"

[1892] (Claim 1)

[1893] a means for collecting traffic information;

[1894] a means for collecting weather information;

[1895] A means for collecting delivery destination business hours information;

[1896] a means of collecting data relating to transportation means;

[1897] a means for training a machine learning model using the preprocessed data; and

[1898] A means to receive real-time data and immediately reflect it in machine learning models,

[1899] A means to optimize delivery routes and transportation methods based on the latest data,

[1900] A means of proposing optimal delivery routes and transportation methods;

[1901] means for collecting user feedback data and performing sentiment analysis;

[1902] The system includes a means for retraining a machine learning model using the feedback data and sentiment data.

[1903] (Claim 2)

[1904] a means for calculating an optimal delivery route from the preprocessed data;

[1905] A means for selecting an optimal transportation mode from the preprocessed data;

[1906] a means of assessing environmental impacts from preprocessed data; and

[1907] 10. The system of claim 1, further comprising means for estimating shipping costs from the preprocessed data.

[1908] (Claim 3)

[1909] means for collecting and analyzing user emotion data;

[1910] 10. The system of claim 1, further comprising means for using the feedback data and the emotion data to retrain the machine learning model.

[1911] "Application example 2 when combining emotion engines"

[1912] (Claim 1)

[1913] a means for collecting traffic information;

[1914] a means for collecting weather information;

[1915] A means for collecting delivery destination business hours information;

[1916] a means of collecting data relating to transportation means;

[1917] means for training an artificial intelligence model using the preprocessed data; and

[1918] A means of receiving real-time data and immediately reflecting it in the artificial intelligence model;

[1919] A means of proposing optimal delivery routes and transportation methods;

[1920] means for collecting user emotional feedback using emotion recognition;

[1921] A system including a means for sending notifications to a user.

[1922] (Claim 2)

[1923] a means for calculating an optimal delivery route from the preprocessed data;

[1924] A means for selecting an optimal transportation mode from the preprocessed data;

[1925] a means of assessing environmental impacts from preprocessed data; and

[1926] a means for estimating shipping costs from the preprocessed data;

[1927] 10. The system of claim 1, further comprising means for retraining the artificial intelligence model based on the emotional feedback.

[1928] (Claim 3)

[1929] a means for collecting feedback data from users;

[1930] a means for using the feedback data to retrain an artificial intelligence model; and

[1931] 10. The system of claim 1, further comprising means for adjusting the optimization result using the emotion recognition result. [Explanation of symbols]

[1932] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for collecting traffic information; a means for collecting weather information; A means for collecting delivery destination business hours information; a means of collecting data relating to transportation means; means for training an artificial intelligence model using the preprocessed data; and A means of receiving real-time data and immediately reflecting it in the artificial intelligence model; A system that includes a means to suggest optimal delivery routes and transportation methods.

2. a means for calculating an optimal delivery route from the preprocessed data; A means for selecting an optimal transportation mode from the preprocessed data; a means of assessing environmental impacts from preprocessed data; and The system of claim 1 further comprising means for estimating shipping costs from the preprocessed data.

3. a means for collecting feedback data from users; 10. The system of claim 1, further comprising means for using the feedback data to retrain the artificial intelligence model.

Images