Visual network freight platform transportation transaction management system

Abstract

The invention discloses a visual network freight platform transportation transaction management system. The system comprises an order management module, a vehicle scheduling module, a transportation monitoring module, a transaction settlement module and a visual display module. Each module has innovative functions, such as order intelligent classification, vehicle optimization scheduling algorithm to minimize comprehensive cost, real-time monitoring and accurate settlement. The corresponding management method adopts advanced technologies to ensure efficient operation of each link, including block chain recording, intelligent contract settlement and the like. The whole system realizes efficient management, real-time monitoring and convenient visualization of transportation transaction of a freight platform, and improves the efficiency and quality of logistics transportation; according to the visual network freight platform management system, efficient and accurate order management is realized, vehicle scheduling is optimized, the cost is reduced, comprehensive and real-time transportation monitoring is guaranteed to be safe, safe and accurate transaction settlement is realized, convenient and visual display is convenient to make decisions, and the logistics transportation efficiency, quality and user experience are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of freight platform transaction systems, and more specifically, to a visualized network freight platform transportation transaction management system. Background Art

[0002] In today's globalized and rapidly developing e-commerce environment, the scale and complexity of the logistics and transportation industry are constantly increasing. Traditional freight management methods are facing many severe challenges.

[0003] In terms of order management, in the past, orders were mainly recorded and allocated manually, which was inefficient and prone to errors. Due to the lack of an intelligent classification mechanism, it was difficult to accurately match transportation resources according to the characteristics of the goods and transportation requirements, resulting in unreasonable resource allocation. For example, fresh goods may be allocated to vehicles without refrigeration equipment, affecting the quality of goods and transportation efficiency. At the same time, customers and transport parties cannot understand the order status in real time, and information transparency is low, which easily leads to poor communication and misunderstandings.

[0004] In the vehicle dispatching process, traditional methods mostly rely on experience and simple dispatch tables to allocate vehicles, which cannot fully consider dynamic factors such as the real-time location, driving status, and traffic conditions of vehicles. This not only leads to increased transportation costs, such as high vehicle idle rate and fuel waste, but also makes it difficult to ensure the timeliness and efficiency of transportation. Moreover, when faced with complex and changing transportation needs and road conditions, there is a lack of flexible response strategies, and it is impossible to achieve the optimal vehicle dispatching plan.

[0005] In the field of transportation monitoring, traditional monitoring methods are limited, mainly relying on telephone communication and simple positioning equipment, which makes it difficult to grasp the detailed status of vehicles and goods in real time and comprehensively. Abnormal conditions such as key environmental parameters such as temperature and humidity of goods and deviations from the vehicle's driving trajectory cannot be discovered and warned in time, increasing the risk of damage to goods and transportation. In addition, it is difficult to effectively store and analyze historical transportation data, and it is impossible to provide strong data support for subsequent transportation optimization.

[0006] During the transaction settlement process, manual calculation of fees is prone to errors, the settlement cycle is long, and there is a lack of a safe and reliable payment guarantee mechanism. At the same time, it is impossible to quickly generate detailed and accurate transaction reports, which is not conducive to financial auditing and business management.

[0007] In terms of visualization, traditional freight management systems lack intuitive and real-time visualization display functions, making it difficult for managers and relevant personnel to intuitively understand the overall picture of the entire transportation transaction and making it difficult to make efficient decisions and management.

[0008] To sum up, the existing freight platform transportation transaction management method can no longer meet the development needs of the modern logistics industry. An innovative visual network freight platform transportation transaction management system is urgently needed to solve these problems. Summary of the invention

[0009] The present invention proposes a visualized network freight platform transportation transaction management system, which is used to solve the problems mentioned in the above-mentioned prior art.

[0010] In order to achieve the above-mentioned purpose, the present invention adopts the following technical scheme: a visual network freight platform transportation transaction management system, including an order management module, a vehicle scheduling module, a transportation monitoring module, a transaction settlement module and a visual display module;

[0011] The order management module is used to receive, process and allocate transportation orders. It has an intelligent order classification function, which automatically classifies orders according to factors such as cargo type, transportation distance, and timeliness requirements, and allocates them to the most suitable transportation resources. For example, for fresh goods orders, the system will give priority to vehicles with refrigeration equipment and experienced drivers. At the same time, the module supports real-time tracking and status updates of orders, so that both customers and transport parties can check the progress of orders at any time.

[0012] The vehicle dispatch module dispatches vehicles reasonably according to order requirements and real-time vehicle status. By exchanging data with IoT devices installed on vehicles, it obtains information such as vehicle location, driving speed, and load in real time. It uses an optimized dispatch algorithm to minimize the comprehensive transportation cost index. For the goal, ,in Indicates the time cost, represents the fuel cost, represents the travel distance cost, represents the driver labor cost, , , , The weight coefficient is determined based on actual conditions and experience. The most suitable vehicle is assigned to each order. The optimal driving route is planned based on the current location and destination of the vehicle and the traffic condition forecast. The dispatch efficiency evaluation index formula is: ,in represents the scheduling efficiency, It indicates the number of orders that are successfully scheduled according to the optimal solution per unit time. Indicates the time required for scheduling.

[0013] The transportation monitoring module monitors vehicles and goods in real time during transportation. Using satellite positioning technology, sensor technology, etc., it obtains key information such as the vehicle's location, driving trajectory, temperature and humidity of goods in real time. When an abnormal situation occurs, such as the vehicle deviates from the scheduled route or the goods are in abnormal condition, the system will immediately issue an alarm and notify relevant personnel to handle it. At the same time, the module supports the storage and query of historical transportation data for transportation quality analysis and improvement.

[0014] The transaction settlement module is responsible for the settlement of transportation transaction fees. It automatically calculates transportation fees based on the contract terms of the order and the actual transportation situation. It supports multiple payment methods, including online and offline payments, and ensures payment security and accuracy. At the same time, the module will generate detailed transaction reports to facilitate users to conduct financial audits and management. Its settlement accuracy evaluation indicators ,in Indicates the settlement accuracy rate, Indicates the number of transactions whose settlement results are within the preset error range. Indicates the total number of transactions.

[0015] The visualization module displays various data of the platform in the form of intuitive charts, maps, etc., including order distribution, real-time location of vehicles, transportation status statistics, etc. Users can view the operation of the platform anytime and anywhere through computers, mobile phones and other devices, which is convenient for decision-making and management. For example, the driving trajectory and current location of the vehicle can be visualized through the map, which is convenient for dispatchers to monitor and dispatch in real time.

[0016] Preferably, the intelligent order classification function in the order management module is trained and optimized using a multimodal fusion classification model based on deep learning. The accuracy and efficiency of order classification are continuously improved by fusion learning of multimodal information such as cargo image features, text description features, and historical transaction data features.

[0017] Preferably, the optimization scheduling algorithm in the vehicle scheduling module adopts an improved optimization algorithm based on the fusion of ant colony algorithm and particle swarm algorithm. By simulating the foraging behavior of ant colonies and the group intelligent search process of particle swarms, the optimal vehicle scheduling solution is continuously searched to adapt to the complex and changing transportation environment and needs.

[0018] Preferably, the abnormal situation judgment in the transportation monitoring module adopts an intelligent judgment model based on the combination of fuzzy logic and deep learning. Fuzzy logic is used to process uncertain environmental factors and abnormal state boundaries, and deep learning is used to learn a large amount of historical abnormal data to automatically judge abnormal situations in the transportation process and take corresponding treatment measures.

[0019] Preferably, the visualization display module supports dynamic configuration functions for users to customize visualization indicators and data presentation methods according to their preferences and business needs. Users can flexibly select key data indicators of interest and display them through personalized chart styles and interactive methods, which facilitates personalized management and decision-making.

[0020] A method for managing transport transactions on a visual network freight platform comprises the following steps: S1. Order Receiving: Receive the transport order through the order management module, and perform preliminary information entry and verification. Use blockchain-based distributed ledger technology to record key order information to ensure that the order information cannot be tampered with and is traceable.

[0021] S2. Order classification: Use the intelligent order classification function to classify orders and determine the order priority and transportation requirements. Use the automatic classification strategy optimization model based on reinforcement learning, and continuously adjust the classification strategy based on the feedback of the classification results to improve the classification accuracy.

[0022] S3. Vehicle dispatch: According to the order classification results and the real-time status of the vehicle, the vehicle dispatch module is used to dispatch and plan the route of the vehicle. The dynamic energy consumption model of the vehicle and the real-time traffic flow information are considered to optimize the cost calculation and path planning in the dispatch algorithm to ensure the optimality and adaptability of the dispatch scheme.

[0023] S4. Transportation monitoring: During the transportation process, the status of vehicles and goods is monitored in real time through the transportation monitoring module, and abnormal situations are handled in a timely manner. A dynamic monitoring mechanism based on real-time data analysis and prediction models is adopted to predict possible abnormal situations in advance and take preventive measures.

[0024] S5. Transaction Settlement: After the transportation task is completed, the transaction settlement module is used to settle the fees and generate a transaction report. The settlement process is automatically executed using smart contract technology, and the settlement is ensured to be accurate, efficient and secure according to the preset settlement rules and conditions.

[0025] S6. Visualization: Display various data of the platform through the visualization module to facilitate users to manage and make decisions. Adopt immersive visualization based on virtual reality (VR) and augmented reality (AR) technology to provide users with a more intuitive and vivid platform data experience.

[0026] Preferably, in the order receiving step, data encryption technology is used to ensure the security of order information. At the same time, natural language processing technology is used to automatically analyze the text information in the order and extract key information to assist in the rapid entry and classification of the order.

[0027] Preferably, in the vehicle dispatching step, factors such as vehicle endurance and driver working hours are considered to ensure the rationality and feasibility of the dispatching plan. In addition, the dispatching strategy is dynamically adjusted in combination with real-time weather information and road condition forecasts to improve the flexibility and adaptability of the dispatching.

[0028] Preferably, in the transport monitoring step, real-time video monitoring technology is used to achieve visual monitoring of the goods. At the same time, the real-time data of the Internet of Things sensors and artificial intelligence image recognition technology are used to automatically identify the state changes and abnormal conditions of the goods, thereby improving the accuracy and efficiency of monitoring.

[0029] Preferably, in the visualization step, a data dynamic update technology is used to ensure that the displayed data is real-time and accurate. In addition, the user is supported to interact with the visualization interface through voice commands, gesture operations and other interactive methods, thereby improving the user's operational convenience and experience.

[0030] Compared with the prior art, the present invention has the following beneficial effects: 1. Efficient and accurate order management: Through the intelligent order classification function, orders can be automatically and accurately classified according to various factors and matched with the most suitable transportation resources, greatly improving the rationality and efficiency of resource allocation. For example, it ensures that fresh goods can be allocated to suitable vehicles in a timely manner to ensure the quality of goods. At the same time, the real-time tracking and status update functions improve information transparency, making it easier for customers and transport parties to keep track of order progress at any time, reducing communication costs and misunderstandings.

[0031] 2. Optimized vehicle dispatching: By using advanced optimization scheduling algorithms and comprehensively considering various vehicle states and cost factors, the optimal vehicle scheduling solution is achieved. Transportation costs are reduced, such as reducing fuel consumption and driving distance costs through reasonable route planning, improving vehicle utilization, and reducing empty driving rates. In addition, scheduling strategies can be flexibly adjusted according to real-time dynamic factors to adapt to complex and changing transportation environments, ensuring the timeliness and efficiency of transportation.

[0032] 3. Comprehensive and real-time transportation monitoring: With the help of advanced technical means, all-round real-time monitoring of vehicles and goods is achieved. It can timely detect and warn of abnormal situations, such as vehicle deviation from the route and abnormal status of goods, reducing transportation risks and ensuring the safety of goods. At the same time, the storage and analysis function of historical transportation data provides strong data support for the improvement and optimization of transportation quality, which helps to continuously improve the quality of transportation services.

[0033] 4. Safe and accurate transaction settlement: Automatic calculation of transportation costs reduces manual calculation errors and improves settlement accuracy and efficiency. Multiple secure payment methods ensure the safety and reliability of payment, and quickly generated transaction reports facilitate financial audits and business management, improving the standardization and convenience of financial management.

[0034] 5. Intuitive and convenient visual display: Through various visualization methods, such as charts and maps, users can intuitively understand the various data and operation status of the platform. It is convenient for managers to make decisions and management, and improves the efficiency and accuracy of decision-making. At the same time, it supports users to customize visualization content and interaction methods, meeting the personalized needs of different users and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a schematic block diagram of a visualized network freight platform transportation transaction management system proposed by the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0038] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0039] Reference Figure 1 : A visual network freight platform transportation transaction management system, including an order management module, a vehicle scheduling module, a transportation monitoring module, a transaction settlement module and a visual display module; The order management module is used to receive, process and allocate transportation orders. It has an intelligent order classification function, which automatically classifies orders according to factors such as cargo type, transportation distance, and timeliness requirements, and allocates them to the most suitable transportation resources. For example, for fresh goods orders, the system will give priority to vehicles with refrigeration equipment and experienced drivers. At the same time, the module supports real-time tracking and status updates of orders, so that both customers and transport parties can check the progress of orders at any time.

[0040] The vehicle dispatch module dispatches vehicles reasonably according to order requirements and real-time vehicle status. By exchanging data with IoT devices installed on vehicles, it obtains information such as vehicle location, driving speed, and load in real time. It uses an optimized dispatch algorithm to minimize the comprehensive transportation cost index. For the goal, ,in Indicates the time cost, represents the fuel cost, represents the travel distance cost, represents the driver labor cost, , , , The weight coefficient is determined based on actual conditions and experience. The most suitable vehicle is assigned to each order. The optimal driving route is planned based on the current location and destination of the vehicle and the traffic condition forecast. The dispatch efficiency evaluation index formula is: ,in represents the scheduling efficiency, It indicates the number of orders that are successfully scheduled according to the optimal solution per unit time. Indicates the time required for scheduling.

[0041] The transportation monitoring module monitors vehicles and goods in real time during transportation. Using satellite positioning technology, sensor technology, etc., it obtains key information such as the vehicle's location, driving trajectory, temperature and humidity of goods in real time. When an abnormal situation occurs, such as the vehicle deviates from the scheduled route or the goods are in abnormal condition, the system will immediately issue an alarm and notify relevant personnel to handle it. At the same time, the module supports the storage and query of historical transportation data for transportation quality analysis and improvement.

[0042] The transaction settlement module is responsible for the settlement of transportation transaction fees. It automatically calculates transportation fees based on the contract terms of the order and the actual transportation situation. It supports multiple payment methods, including online and offline payments, and ensures payment security and accuracy. At the same time, the module will generate detailed transaction reports to facilitate users to conduct financial audits and management. Its settlement accuracy evaluation indicators , in Indicates the settlement accuracy rate, Indicates the number of transactions whose settlement results are within the preset error range. Indicates the total number of transactions.

[0043] The visualization module displays various data of the platform in the form of intuitive charts, maps, etc., including order distribution, real-time location of vehicles, transportation status statistics, etc. Users can view the operation of the platform anytime and anywhere through computers, mobile phones and other devices, which is convenient for decision-making and management. For example, the driving trajectory and current location of the vehicle can be visualized through the map, which is convenient for dispatchers to monitor and dispatch in real time.

[0044] The intelligent order classification function in the order management module of the present invention is highly intelligent and accurate.

[0045] In terms of building a multimodal fusion classification model based on deep learning, the system is equipped with advanced image recognition technology for the extraction and learning of cargo image features. When customers upload pictures of goods, the system uses a deep convolutional neural network to analyze the images. This network structure can automatically learn various features in the image. For example, for boxed goods with regular shapes, the network can identify their size, packaging type and other features; for fresh goods with irregular shapes, the network can identify their approximate type, freshness and other features. The system can also conduct in-depth analysis of the color information in the image, such as judging whether the goods belong to the category of perishable goods by color features.

[0046] For the processing of text description features, the system uses the word vector model in natural language processing technology. The text description information in the order is converted into a digital vector form that can be understood by the computer. For example, when the order text mentions key descriptive words such as "fragile items" and "expedited delivery", the system can accurately extract the semantic features of these words and include them in the consideration of the classification model. At the same time, through training on a large amount of text data, the system can understand the semantic associations between different words. For example, "cold chain transportation" is often associated with goods that need to be kept at low temperatures. The system can better understand the needs of the order based on this semantic relationship.

[0047] In terms of utilizing the characteristics of historical transaction data, the system will collect and organize a large amount of past order transaction data, including order type, transportation time, customer satisfaction and other information. By analyzing these data, the system can discover some hidden patterns and rules. For example, certain types of customers often order a certain type of goods in a specific time period. The system can assist in the classification of current orders based on these historical rules. Or by analyzing the transportation costs and efficiency of different types of orders in historical data, the classification decision of current orders can be optimized to better allocate transportation resources.

[0048] In the process of fusion learning of multimodal information, the system adopts a specially designed fusion architecture. The features of the cargo image, text description, and historical transaction data are respectively extracted and encoded through different processing channels. Then, a fusion layer is used to merge and interact the features of these different modalities. For example, through weighted fusion, different features are assigned corresponding weights according to their importance, and they are combined into a comprehensive feature vector. This comprehensive feature vector contains information from multiple aspects and can more comprehensively reflect the essential characteristics of the order.

[0049] During the training and optimization process, the system uses a large amount of labeled real order data as training samples. By continuously adjusting the parameters of the deep learning model, the model can better adapt to various types of order classification tasks. For example, in each round of training, the model will classify and predict the training samples based on the current parameters, and then compare the prediction results with the real classification labels to calculate the error. Based on this error, the system will use the back propagation algorithm to update the parameters of the model so that the model can be more accurate in the next prediction. At the same time, the system will regularly introduce new order data for incremental learning, and continuously update the model's knowledge and capabilities to adapt to the changing market demand and goods types, thereby continuously improving the accuracy and efficiency of order classification.

[0050] The optimized dispatching algorithm in the vehicle dispatching module of the present invention is innovative and efficient.

[0051] In terms of integrating the ant colony algorithm, the system compares the transportation network to the foraging path environment of the ant colony. Each vehicle to be dispatched is regarded as an ant, and the starting and ending points of the transportation task and the key nodes along the way (such as logistics transfer stations, etc.) are analogous to the path nodes between the food source and the ant nest. Ants release a pheromone in the process of looking for food, and the concentration of the pheromone gradually accumulates along the ant's walking path. In vehicle scheduling, the system initializes the pheromone concentration on each path based on historical transportation data and real-time traffic information. When a vehicle completes a transportation task, it is equivalent to an ant finding food and returning to the nest. The system will update the pheromone concentration on the path based on the completion of this transportation task, such as transportation time, fuel consumption and other indicators. The pheromone concentration on those paths with high transportation efficiency will increase, attracting more vehicles to choose this path. For example, in a city's logistics distribution network, if a road has smooth traffic, fast vehicle speeds, and a short time to complete the transportation task within a specific time period, then the pheromone concentration on the path will increase accordingly. In this way, subsequent vehicles are more likely to choose this path when dispatched, thus achieving a process similar to that of ant colonies finding the optimal path through pheromone guidance.

[0052] At the same time, the advantages of the particle swarm algorithm are combined. Each vehicle is regarded as a particle in the particle swarm. Each particle has two key attributes: position and speed. The position represents the current location of the vehicle and the assigned transportation task, and the speed represents the adjustment and change speed of the vehicle scheduling plan. The particles in the particle swarm search for the optimal scheduling plan by constantly updating their own positions and speeds. During the update process, each particle will refer to two key factors: one is its own historical optimal position, that is, the best transportation plan for the vehicle in the past scheduling process; the other is the global optimal position of the entire particle swarm, that is, the best scheduling plan in the entire vehicle scheduling system. For example, when a vehicle receives a new transportation task in a certain area, the system will calculate the next task point and the best driving path of the vehicle based on the current location of the vehicle, the remaining transportation capacity, and the status of other surrounding vehicles, combined with the update rules of the particle swarm algorithm. If at a certain moment, the system finds that a batch of urgent goods needs to be transported and there are multiple vehicles available for dispatch, the particle swarm algorithm will quickly calculate the best scheduling plan for each vehicle, so that the transportation task of this batch of goods can be completed in the shortest time, while minimizing the impact on other ongoing transportation tasks.

[0053] By simulating the foraging behavior of ant colonies and the swarm intelligence search process of particle swarms, the system can continuously search for the optimal vehicle scheduling solution in complex and changing transportation environments and demands. For example, during peak traffic hours, when road congestion is severe, the system will adjust the vehicle's driving path based on real-time traffic information and use the dynamic update mechanism of pheromones in the ant colony algorithm to guide vehicles to choose relatively unobstructed roads. At the same time, the particle swarm algorithm will reasonably allocate transportation tasks based on the global state of the entire vehicle scheduling system to ensure that each vehicle can perform tasks at the most suitable time and place. If there are sudden weather changes, such as heavy rain that makes some roads impassable, the system will quickly use the fusion advantages of the two algorithms to re-plan the vehicle scheduling solution and guide vehicles to safe and efficient transportation routes to maximize transportation needs and improve transportation efficiency.

[0054] The transportation monitoring module of the present invention has a unique and efficient intelligent judgment model in judging abnormal situations.

[0055] First, the part based on fuzzy logic plays a key role in dealing with uncertain environmental factors and abnormal state boundaries. For fuzzy concepts in environmental factors, such as "light rain", "moderate rain" and "heavy rain" in weather conditions, there is no absolutely clear boundary between them. Fuzzy logic can handle them according to a series of preset fuzzy rules and membership functions. The system will define fuzzy sets corresponding to different rainfall ranges, and calculate the membership of each fuzzy set based on the real-time monitored rainfall data. For example, when the rain sensor detects that the current rainfall is in a range that is difficult to clearly define as "moderate rain" or "heavy rain", the fuzzy logic system will comprehensively consider other relevant factors, such as wind speed, temperature, etc., and their mutual relationship. If in this case, the wind speed is also high and the temperature is low, then the system may judge that this environmental combination may have a greater impact on the transportation process and classify it as a state that needs to be paid special attention to. The fuzzy processing of abnormal state boundaries is also based on a similar principle. For example, it may be normal for the temperature of the goods to fluctuate within a certain range, but when it approaches a certain critical value, it is difficult to clearly determine whether it is in an abnormal state. At this time, fuzzy logic will comprehensively evaluate whether the current state is close to the abnormal boundary based on the temperature change trend in similar situations in historical data and other relevant factors, such as the type of goods and transportation time, and give a fuzzy judgment result, providing an important reference for subsequent accurate judgment.

[0056] At the same time, deep learning performs well in learning a large amount of historical abnormal data. The system collects and organizes various abnormal situation data that occurred in the past transportation process, including cases such as vehicle failure, cargo damage, route deviation, etc., and pre-processes and annotates these data. Then, these annotated data are trained using deep neural network models, such as convolutional neural networks or recurrent neural networks. By constantly adjusting the weights and parameters of the network, the deep learning model can automatically learn the characteristic patterns of abnormal situations. For example, for the judgment of vehicle failure, the deep learning model can identify the patterns of potential fault signals such as abnormal engine vibration and frequent triggering of the brake system by analyzing the time series characteristics of vehicle sensor data. When similar characteristic patterns are monitored in real time during actual transportation, the model can quickly determine possible abnormal situations.

[0057] When the system automatically determines an abnormal situation during transportation, it will immediately take appropriate measures. If it is a vehicle failure, the system will automatically send a request for help to a nearby maintenance station and provide detailed information such as the location of the vehicle and the type of failure so that maintenance personnel can respond quickly. For abnormal cargo conditions, such as too high or too low temperature, the system will automatically adjust the temperature control equipment of the transport vehicle, or notify the driver to take appropriate emergency measures, such as checking whether the cargo packaging is damaged. If it is a route deviation, the system will immediately send an alarm to the driver and re-plan the optimal driving route to ensure that the transportation task can return to normal as soon as possible. At the same time, the system will also record the detailed information of the abnormal situation for subsequent data analysis and improvement, and continuously improve the accuracy and efficiency of abnormal situation judgment and handling.

[0058] The visual display module in the present invention has high flexibility and personalized customization capabilities, and can greatly meet the diverse needs of users.

[0059] In terms of supporting user-defined visualization indicators, the system provides an intuitive and easy-to-operate indicator selection interface. After logging into the system, users can enter the visualization indicator setting area. Here are listed all the displayable data indicator options covered by the system, including but not limited to the number of orders, real-time vehicle location distribution, cargo transportation status statistics, transportation cost details, etc. Users can easily check the key data indicators they want to focus on according to their business concerns and preferences. For example, the operation managers of logistics companies may pay more attention to the completion rate of orders and the utilization rate of vehicles. They can accurately select these indicators from many indicators for key display. At the same time, users can also sort and group the selected indicators to better organize and view the data. For some special business scenarios, users can even create unique composite indicators by customizing formulas. For example, users can define a "comprehensive index of transportation efficiency" according to their needs. The index can be composed of multiple basic indicators such as transportation time, cargo loading and unloading time, and vehicle driving speed through certain mathematical operations.

[0060] In terms of the dynamic configuration function of data presentation, the system provides a variety of chart styles for users to choose from. Users can display key data indicators in various forms such as bar charts, line charts, pie charts, and scatter charts according to the characteristics of the data and their own preferences. For example, to display the trend of order quantity changes in different time periods, users can choose a line chart to clearly see the fluctuation of order quantity over time; and for displaying the order distribution ratio in different regions, a pie chart is a good choice. In addition, users can also personalize the color, font, axis label and other details of the chart to make it more in line with their visual habits and business needs. In terms of interaction methods, users can not only operate the visual interface through traditional mouse clicks and drags, but also choose a more convenient interaction method according to their habits. For example, users can switch different data display pages through voice commands. Simply say "view vehicle location" and "display transportation cost report" and other commands, and the system will respond quickly and display the corresponding content. At the same time, for devices that support touch screens, users can also use gestures, such as pinching to adjust the size of the chart, sliding to switch different data views, etc. This personalized configuration function enables users to create an exclusive visual management interface based on their needs and work scenarios, greatly facilitating users' personalized management and decision-making.

[0061] A method for managing transport transactions on a visual network freight platform comprises the following steps: S1. Order Receiving: Receive the transport order through the order management module, and perform preliminary information entry and verification. Use blockchain-based distributed ledger technology to record key order information to ensure that the order information cannot be tampered with and is traceable.

[0062] S2. Order classification: Use the intelligent order classification function to classify orders and determine the order priority and transportation requirements. Use the automatic classification strategy optimization model based on reinforcement learning, and continuously adjust the classification strategy based on the feedback of the classification results to improve the classification accuracy.

[0063] S3. Vehicle dispatch: According to the order classification results and the real-time status of the vehicle, the vehicle dispatch module is used to dispatch and plan the route of the vehicle. The dynamic energy consumption model of the vehicle and the real-time traffic flow information are considered to optimize the cost calculation and path planning in the dispatch algorithm to ensure the optimality and adaptability of the dispatch scheme.

[0064] S4. Transportation monitoring: During the transportation process, the status of vehicles and goods is monitored in real time through the transportation monitoring module, and abnormal situations are handled in a timely manner. A dynamic monitoring mechanism based on real-time data analysis and prediction models is adopted to predict possible abnormal situations in advance and take preventive measures.

[0065] S5. Transaction Settlement: After the transportation task is completed, the transaction settlement module is used to settle the fees and generate a transaction report. The settlement process is automatically executed using smart contract technology, and the settlement is ensured to be accurate, efficient and secure according to the preset settlement rules and conditions.

[0066] S6. Visualization: Display various data of the platform through the visualization module to facilitate users to manage and make decisions. Adopt immersive visualization based on virtual reality (VR) and augmented reality (AR) technology to provide users with a more intuitive and vivid platform data experience.

[0067] In the present invention, in the order receiving step, great attention is paid to the security of order information, and advanced data encryption technology is adopted. When the customer submits the order information, the system will immediately start the encryption program, and use powerful encryption algorithms such as Advanced Encryption Standard (AES) to encrypt all key data in the order, including the customer's name, contact information, delivery address, and detailed description of the goods. In this way, even if the data is maliciously intercepted during the data transmission process, the attacker cannot decrypt the content, thereby ensuring the confidentiality and integrity of the order information.

[0068] At the same time, the system cleverly uses natural language processing technology to deeply process the text information in the order. First, the system will use word segmentation technology to split the order text into independent words, and then use part-of-speech tagging technology to mark the part of speech of each word, such as noun, verb, adjective, etc. Next, the named entity recognition technology is used to automatically identify the key entity information in the order text, such as customer name, product name, place of shipment and place of receipt, and other specific named entities. For some common expressions and industry terms, the system can accurately understand their meaning after being trained with a large amount of data. For example, when the order mentions expressions such as "ship as soon as possible" and "expedited delivery", the system can automatically recognize that this is an order with high timeliness requirements. Through these automatic analysis and extraction of key information, the rapid entry of orders is greatly assisted. In the entry stage, the system can automatically fill in the corresponding form fields based on the extracted key information, reducing the workload and error rate of manual input. In terms of classification, based on the extracted key information such as the type of goods and timeliness requirements, combined with pre-set classification rules and algorithms, orders can be quickly and accurately classified into corresponding categories, such as fresh food, general goods, expedited orders, etc., providing an efficient foundation for subsequent order processing processes.

[0069] In the present invention, in the vehicle dispatching step, the key factor of the vehicle's endurance is fully and comprehensively considered. The system will monitor the remaining power or fuel of the vehicle in real time, and accurately calculate the distance that the vehicle can still travel under different road conditions according to the different models of the vehicle, energy consumption characteristics and current load conditions. For example, for electric trucks, the aging degree of the battery, the current charging status and the trend of power consumption changes during driving will be comprehensively considered to ensure that the dispatched vehicles have sufficient endurance to complete the assigned transportation tasks and avoid stagnation due to insufficient power. At the same time, the driver's working hours are also closely monitored. The driver's cumulative working hours, rest intervals and current working status are recorded in detail, and relevant labor laws and safety regulations are strictly observed. The driver's work tasks are reasonably arranged to avoid driver fatigue driving and ensure the safety of the transportation process. By comprehensively considering these factors, the rationality and feasibility of the dispatching plan can be effectively ensured.

[0070] In addition, the system innovatively combines real-time weather information and road condition forecasts to dynamically adjust the dispatching strategy. The system will continuously obtain the latest weather data from professional meteorological service platforms, including weather conditions such as rainfall, snowfall, heavy fog, and strong winds, and their changing trends. For sections that may be affected by bad weather, predictions and assessments are made in advance. At the same time, advanced traffic big data analysis technology and intelligent road condition prediction models are used to obtain real-time information on road congestion, construction information, and accident probability. When encountering sudden traffic congestion, bad weather causing road conditions to deteriorate, or other situations that affect transportation, the system can respond quickly and dynamically adjust the vehicle dispatching strategy. For example, re-planning the driving route to avoid congested sections or areas severely affected by bad weather; or according to the actual situation of the driver and the vehicle, reasonably adjusting the allocation of transportation tasks, improving the flexibility and adaptability of dispatching, and ensuring that the transportation tasks can be completed efficiently and smoothly.

[0071] In the present invention, advanced real-time video monitoring technology is innovatively used in the transportation monitoring step. By installing high-definition cameras at key locations such as transport vehicles and cargo storage areas, real-time images of the cargo can be continuously transmitted back to the monitoring center. This makes the monitoring personnel seem to be next to the cargo and can clearly observe every detail and state change of the cargo. Whether it is the adjustment of the placement of the cargo during transportation or the slight shaking caused by the external environment, it can be clearly seen through real-time video monitoring technology, truly realizing all-round visual monitoring of the cargo.

[0072] At the same time, make full use of the real-time data of IoT sensors and advanced artificial intelligence image recognition technology. IoT sensors can accurately capture key data such as temperature, humidity, pressure, etc. of goods, and transmit these data back in real time. And artificial intelligence image recognition technology is like a keen guardian, which can intelligently analyze the real-time video surveillance screen. When the packaging of the goods shows signs of damage, the shape of the goods changes, or the color of the goods is abnormal, artificial intelligence image recognition technology can quickly identify these state changes and abnormal conditions and immediately issue an alarm. In this way, not only the accuracy of monitoring is greatly improved, and those small changes and potential risks that are easily overlooked can be accurately discovered, but also the efficiency of monitoring is greatly improved, the time and energy consumption of manual one-by-one inspection is reduced, and transportation monitoring becomes more intelligent, efficient and reliable.

[0073] In the present invention, advanced data dynamic update technology is carefully used in the visualization step. This technology can efficiently connect and synchronize data with various data collection sources in real time, ensuring that the data displayed to the user is always up to date and accurate at any time. Whether it is the real-time status change of the order, the dynamic location information of the vehicle, or the fluctuation of the key parameters of the goods during transportation, they can all be reflected instantly in the visualization interface.

[0074] Moreover, the system considerately supports users to interact with the visual interface through a variety of convenient interactive methods. Users can not only use clear and fluent voice commands to control the interface switching, data filtering, and function calling, but also use natural and fluent gestures such as sliding, zooming, and clicking to easily browse detailed information, switch different display perspectives, and make personalized settings in the visual interface. This greatly improves the convenience of users in the operation process, allowing users to have a more comfortable and pleasant experience in the process of using the system, as if they are having a smooth and intelligent conversation with the system.

[0075] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A visual network freight platform transportation transaction management system, characterized in that: It includes order management module, vehicle dispatch module, transportation monitoring module, transaction settlement module and visual display module; Order management module: used to receive, process and allocate transport orders. It has intelligent order classification function, automatically classifies orders according to cargo type, transportation distance and timeliness requirements, and allocates them to the most suitable transport resources. Specifically, for fresh goods orders, the system will give priority to vehicles with refrigeration equipment. This module supports real-time tracking and status updates of orders. Vehicle dispatch module: dispatches vehicles according to order requirements and real-time vehicle status, obtains vehicle location, driving speed, and load information in real time through data interaction with IoT devices installed on vehicles, and uses optimized dispatching algorithms to minimize the comprehensive transportation cost index. As the target, the calculation formula is: ,in Indicates the time cost, represents the fuel cost, represents the travel distance cost, represents the driver labor cost, , , , is the weight coefficient, and a vehicle is assigned to each order. The optimal driving route is planned based on the current location and destination of the vehicle and the traffic condition forecast. The dispatch efficiency evaluation index formula is: ,in represents the scheduling efficiency, It indicates the number of orders that are successfully scheduled according to the optimal solution per unit time. Indicates the time required for scheduling; The transportation monitoring module monitors vehicles and goods in real time during transportation. It uses satellite positioning technology and sensor technology to obtain the vehicle's location, driving trajectory, and the temperature and humidity information of the goods in real time. When the vehicle deviates from the scheduled route or the goods are in abnormal condition, the system will issue an alarm. This module supports the storage and query of historical transportation data. Transaction settlement module: used for the settlement of transportation transaction fees. It automatically calculates the transportation fees based on the contract terms of the order and the actual transportation situation. It supports online and offline payments. The module will generate transaction reports. The calculation formula for the settlement accuracy evaluation index is: ,in Indicates the settlement accuracy rate, Indicates the number of transactions whose settlement results are within the preset error range. Indicates the total number of transactions; Visual display module: displays various data of the platform in the form of charts and maps. The display content includes order distribution, real-time location of vehicles, transportation status statistics, and visualizes the vehicle's driving trajectory and current location through maps.

2. The visual network freight platform transportation transaction management system according to claim 1 is characterized in that: The intelligent order classification function in the order management module is trained and optimized using a multimodal fusion classification model based on deep learning, and improves the accuracy and efficiency of order classification by fusing multimodal information such as cargo image features, text description features, and historical transaction data features.

3. The visual network freight platform transportation transaction management system according to claim 1 is characterized in that: The optimization scheduling algorithm in the vehicle scheduling module adopts an improved optimization algorithm based on the fusion of ant colony algorithm and particle swarm algorithm, and searches for the optimal vehicle scheduling solution by simulating the foraging behavior of ant colonies and the group intelligent search process of particle swarms.

4. The visual network freight platform transportation transaction management system according to claim 1 is characterized in that: The abnormal situation judgment in the transportation monitoring module adopts an intelligent judgment model based on the combination of fuzzy logic and deep learning. It processes abnormal environmental factors and abnormal state boundaries through fuzzy logic, and uses deep learning to learn historical abnormal data to automatically judge abnormal situations in the transportation process.

5. The visual network freight platform transportation transaction management system according to claim 1 is characterized in that: The visualization display module supports dynamic configuration of visualization indicators and data presentation methods based on users’ preferences and business needs. Users can flexibly select key data indicators of interest and display them through personalized chart styles and interactive methods, which facilitates personalized management and decision-making.

6. A method for managing a transport transaction management system of a visual network freight platform, used to implement the transport transaction management system of a visual network freight platform according to any one of claims 1 to 5, characterized in that: The following steps are involved: S1. Order receiving: Receive the transport order through the order management module, perform preliminary information entry and verification, and use blockchain-based distributed ledger technology to record key order information; S2. Order classification: Use the intelligent order classification function to classify orders, use the automatic classification strategy based on reinforcement learning to optimize the model, and adjust the classification strategy based on the feedback of the classification results; S3, vehicle dispatching: according to the order classification results and the real-time status of the vehicle, the vehicle dispatching module is used to dispatch and plan the route of the vehicle, taking into account the dynamic energy consumption model of the vehicle and the real-time traffic flow information, which is used to optimize the cost calculation and route planning in the dispatching algorithm; S4. Transportation monitoring: During the transportation process, the status of vehicles and goods is monitored in real time through the transportation monitoring module, abnormal situations are handled in a timely manner, and a dynamic monitoring mechanism based on real-time data analysis and prediction models is adopted to predict possible abnormal situations in advance; S5. Transaction Settlement: After the transportation task is completed, the fee settlement is carried out through the transaction settlement module, and a transaction report is generated, and the settlement process is automatically executed using smart contract technology; S6. Visual display: Display the platform data through a visual display module, using a visual display method based on virtual reality and augmented reality technology;.

7. The method for managing transportation transactions on a visual network freight platform according to claim 6 is characterized in that: In the order receiving step, data encryption technology is used to ensure the security of order information, and natural language processing technology is used to automatically analyze the text information in the order and extract key information to assist in the rapid entry and classification of orders.

8. The method for managing transport transactions on a visual network freight platform according to claim 6, characterized in that: In the vehicle dispatching step, the vehicle's endurance and the driver's working hours are taken into consideration, and the dispatching strategy is adjusted dynamically in combination with real-time weather information and road condition forecasts.

9. The method for managing transportation transactions on a visual network freight platform according to claim 6, characterized in that: In the transportation monitoring step, real-time video monitoring technology is used to achieve visual monitoring of goods, and real-time data from IoT sensors and artificial intelligence image recognition technology are used to automatically identify changes in the status of goods and abnormal conditions.

10. The method for managing transportation transactions on a visualized network freight platform according to claim 6, characterized in that: In the visualization step, dynamic data update technology is used to ensure that the displayed data is real-time and accurate, and supports users to interact with the visualization interface through voice commands and gesture operations.

Images