Civil aviation cargo tracking method

Abstract

The invention discloses a civil aviation cargo tracking method, and relates to the technical field of logistics transportation, and the method comprises the steps: collecting cargo data information, and carrying out the whole-process information monitoring in real time; monitoring data information is obtained, a comprehensive evaluation result is obtained according to the comprehensive evaluation model, the predicted value of the cargo arrival time is dynamically adjusted, and an overall process analysis report is generated; according to the overall process analysis report, obtaining the transportation completion degree and the error time value corresponding to each transportation path and the actual transportation time of each transportation node, and dynamically planning the transportation paths according to an optimization mechanism; through setting cargo transportation whole process information monitoring, transparency and traceability of cargo transportation can be effectively improved. By establishing the comprehensive evaluation model and monitoring and analyzing the change data source, the extended time is obtained and the arrival time is predicted, so that a user can obtain the cargo state information in time, and the effects of information transparency, dynamic adjustment, real-time monitoring and timely feedback are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics and transportation, and in particular to a civil aviation cargo tracking method. Background Art

[0002] In the actual civil aviation cargo process, although users can obtain information such as the cargo's origin, destination, flight number, and estimated arrival time through the shipping bill number, it is often difficult to obtain real-time information on the cargo's actual transportation status. If a delay or other unexpected situation occurs during transportation, users cannot obtain the latest updates on the cargo's progress, resulting in inaccurate arrival times. This lack of transparency forces users to passively wait for notification from relevant personnel to arrange pickup, which not only causes inconvenience to customers but can also lead to financial losses due to delayed information.

[0003] The Chinese invention patent with application number 202110188627.4 provides a cargo tracking method based on the international air logistics APP. This method considers the weather conditions of different other segments in different flight segments and evaluates the arrival time of the cargo based on the weather conditions, so that the cargo arrival time displayed to the user is more in line with the actual situation, making it easier for users to adjust the cargo receiving plan according to the real-time status of the cargo, greatly improving the real-time and transparency of information, and improving the accuracy of cargo tracking.

[0004] However, in existing patented technologies, adjusting the arrival time of the cargo to be tracked based on the location of the current segment and the wind speed and cloud coverage of other segments results in large errors. Estimation based solely on wind speed and cloud cover results in less information source data, making it impossible to achieve accurate evaluation results and reducing user experience. Summary of the Invention

[0005] This application provides a civil aviation cargo tracking method to solve the problem in the existing technology that accurate evaluation cannot be achieved due to insufficient information source data, and realizes the technical effect of comprehensive evaluation of multi-dimensional data and improving the accuracy of evaluation.

[0006] The present application provides a civil aviation cargo tracking method, the method comprising: S100: Collect cargo data information, match aircraft models and arrange transportation plans based on the cargo data information, monitor the entire process in real time, and provide feedback on the monitoring data information; S200: Acquire monitoring data information, obtain comprehensive evaluation results based on the comprehensive evaluation model, dynamically adjust the predicted value of the cargo arrival time, provide feedback to the client, and generate an overall process analysis report; S300: Based on the overall process analysis report, each transport route is numbered, and its starting point, end point, and transfer nodes along the way are recorded. The transport completion degree, error time value, and actual transfer time of each transfer node corresponding to each transport route are obtained, and the transport route is dynamically planned according to the optimization mechanism; S400: Obtain the cargo data information, further refine the classification based on cargo characteristics, set transportation requirements and arrival time sensitivity indicators for each type of cargo, and form a rigid transportation standard; S500: Integrate steps S300 and S400 to select the optimal differentiated transportation route based on the rigid transportation standards.

[0007] Furthermore, the cargo data information refers to the size, type, weight and volume of the cargo; the monitoring data information includes flight information, flight status, waybill information, waybill status, customs status and variable data source; the variable data source includes wind speed, cloud coverage, wind direction, precipitation, visibility, temperature and humidity information.

[0008] Furthermore, the comprehensive evaluation model adopts the long short-term memory network model as the basic model to predict the transportation time in cargo tracking, takes the monitoring data information as input data, outputs the predicted arrival time, and obtains the comprehensive evaluation result.

[0009] Furthermore, dynamically adjusting the predicted value of the cargo arrival time based on the comprehensive evaluation result includes: pre-setting extension time thresholds corresponding to different data, comparing the real-time data of the monitored changing data source with the extension time thresholds respectively, and calculating multiple initial extension times; performing weighted summation on the multiple initial extension times to obtain the total extension time, and then obtaining the predicted arrival time based on the original estimated arrival time and the total extension time.

[0010] Furthermore, the overall process analysis report includes monitoring data of the entire cargo transportation process, the number of changes in the predicted arrival time and the analysis of the reasons, the original estimated arrival time and the actual arrival time.

[0011] Furthermore, the transport completion degree refers to the proportion of goods transported to the destination within the original estimated arrival time; the transfer node is the transfer location in the transport route, and the actual transfer time of the transfer node is recorded at the same time; the error time value is the time difference between the original estimated arrival time and the actual arrival time.

[0012] Furthermore, the optimization mechanism is based on the transport completion degree, the error time value and the actual transit time, and is based on a genetic algorithm dynamic programming to form a plurality of transport routes.

[0013] Furthermore, in step S500, it also includes: obtaining a single logistics order, obtaining an acceptable error time value, and marking the maximum acceptable error time value among all orders in the current batch as the acceptable error time value; using a particle swarm optimization algorithm to comprehensively optimize the transportation routes of all orders with the goal of minimizing the overall error time value.

[0014] Furthermore, the acceptable error time value refers to setting the original predicted arrival time as a time range, and the difference in the time range is the acceptable error time value.

[0015] Furthermore, the error-tolerant time value is used as an optimization constraint condition for the particle swarm optimization algorithm. The specific steps of comprehensive optimization using the particle swarm optimization algorithm are as follows: randomly generate a group of particles, each particle represents a transportation path plan; calculate the fitness function value for each particle and evaluate its quality; compare the fitness of the current particle with its historical optimal value and update the individual optimal position; compare the fitness of all particles and update the global optimal position; adjust the speed and position of each particle according to the fitness function value and the update rule; determine whether the maximum number of iterations has been reached. If the termination condition is met, output the global optimal position as the optimized transportation path plan.

[0016] One or more technical solutions provided in this application have at least the following technical effects or advantages: By setting up information monitoring for the entire cargo transportation process, the transparency and traceability of cargo transportation can be effectively improved; by establishing a comprehensive evaluation model, the changing data source is monitored and analyzed, the extension time is obtained and the arrival time is predicted, ensuring that users can obtain cargo status information in a timely manner, achieving information transparency, dynamic adjustment, real-time monitoring, and timely feedback. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a schematic diagram of the overall process of a civil aviation cargo tracking method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0018] To facilitate understanding of the present invention, the present application will be described more comprehensively below with reference to the relevant drawings; the drawings show preferred embodiments of the present invention, but the present invention can be implemented in many different forms and is not limited to the embodiments described herein; on the contrary, the purpose of providing these embodiments is to enable a more thorough and comprehensive understanding of the disclosed content of the present invention.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains; the terms used herein in the specification of the present invention are for the purpose of describing specific embodiments only and are not intended to limit the present invention; the term "and / or" used herein includes any and all combinations of one or more of the associated listed items.

[0020] Example 1: Figure 1 As shown, a civil aviation cargo tracking method includes: S100: Collect cargo data information, match aircraft models and arrange transportation plans based on the cargo data information, monitor the entire process in real time, and provide feedback on the monitoring data information.

[0021] In some embodiments, the cargo data information refers to detailed records of cargo size, type, weight, volume, and other information when the cargo is put into storage. Aircraft matching is performed based on the cargo data information. Based on the size and type of the cargo and the collected aircraft information, the most suitable aircraft model is selected for transportation based on historical experience and historical data. Based on the aircraft matching results, the cargo transportation plan is arranged to ensure that the cargo can be transported to the destination on time and safely.

[0022] In some embodiments, the monitoring data information includes flight information, flight status, waybill information, waybill status, customs status, and change data source; the flight information is based on actual flight attributes and business rules, and the correspondence between the preset plan dictionary and the flight data return field is, for example: If the waybill has (actual flight departure time), it means it is scheduled, and the word "scheduled" is added in the upper right corner of the flight information, indicating that the flight has not yet taken off; If the waybill has (actual flight departure time), it means the flight is in progress, and the word "in flight" is added to the upper right corner of the flight information, indicating that the flight has taken off; If the waybill has (actual landing time of the flight), it means that the flight has landed, and the word "landed" is added in the upper right corner of the flight information, indicating that the flight has landed.

[0023] The flight status is based on the actual flight attributes and business rules until a complete flight status progress is generated. For example, if the flight status has an actual take-off time, the corresponding actual take-off and previous icons are lit, their corresponding colors are changed, and the take-off time is displayed; if the flight status has an actual landing time, the corresponding flight landing and previous icons are lit, their corresponding colors are changed, and the landing time is displayed.

[0024] The waybill information is based on the actual waybill attributes and business rules, and the correspondence between the special cargo dictionary and the waybill data return fields is preset, for example: If there is (200) on the waybill, it means dangerous goods, and if there is a “dangerous” character before the waybill, it means that this waybill is a dangerous goods waybill; If there is (300) on the waybill, it means cold chain, and if there is a word like “Cold” before the waybill, it means that this waybill is a cold chain waybill.

[0025] The waybill status is based on the actual waybill attributes and business rules until a complete waybill status progress is generated, for example: If there is a freight station collection time in the waybill status, the corresponding freight station collection icon will light up and change its corresponding color and display the collection time; If there is a flight departure time in the waybill status, the corresponding flight departure icon will light up and change its color to show the flight departure time; If there is a flight landing time in the waybill status, the corresponding flight landing icon will light up and change its color to show the flight landing time; If there is an arrival notification time in the waybill status, the corresponding arrival notification icon will light up and change its color and display the arrival notification time; If there is a customer pickup time in the waybill status, the corresponding customer pickup icon will be lit and its corresponding color will change, and the customer pickup time will be displayed.

[0026] The customs status is generated based on the actual waybill attributes and business rules to generate a complete customs status progress, for example: If there is a take-off time in the waybill status, the corresponding customs take-off and all icons before the take-off status will be lit up and their corresponding colors will change to show the take-off time; If a landing time is available in the waybill status, the corresponding customs landing and all icons before the landing status will light up and change their colors to display the landing time. Based on the cargo data, the aircraft model is matched and the transportation plan is arranged. The entire process is monitored in real time and the monitoring data is fed back.

[0027] In some embodiments, the variable data source includes but is not limited to wind speed, cloud coverage, wind direction, precipitation, visibility, temperature and humidity information. The variable data source refers to uncertain data information that changes in real time. Based on the variable data source, the current shipping status can be accurately judged, and then based on the variable data source, it can be judged whether it will affect the original transportation plan. If an impact occurs, the size and specific scope of the impact are further judged, the extension time of the impact is judged, and the data change information is promptly fed back to the user end.

[0028] In some embodiments, full-process information monitoring refers to providing users with tracking information on the entire process of goods from warehousing to delivery through the app, including location, estimated time of arrival, flight information, waybill status, and customs status. This allows for real-time updates of flight, waybill, and customs status to ensure transparent and accurate information. Furthermore, an exception monitoring mechanism is established to automatically trigger alarms for abnormal situations such as delays and loss, and to instantly notify users through the app. Users can also customize notification preferences to ensure timely communication of important information.

[0029] S200: Acquire monitoring data information, and obtain comprehensive evaluation results based on the comprehensive evaluation model, dynamically adjust the predicted value of the cargo arrival time, and provide feedback to the client to generate an overall process analysis report.

[0030] In some embodiments, the comprehensive evaluation model uses a long short-term memory network model as a base model to predict transportation time in cargo tracking, uses monitoring data information as input, outputs a predicted arrival time, and obtains a comprehensive evaluation result. Dynamically adjusting the predicted value of cargo arrival time based on the comprehensive evaluation result specifically includes: presetting extension time thresholds corresponding to different data, wherein the extension time thresholds are pre-set based on historical data and experience, comparing the real-time data of the monitored variable data source with the extension time thresholds, and calculating multiple initial extension times. For example, when the wind speed exceeds a certain threshold, the transportation time is extended by a fixed time for each unit increase in wind speed; when the cloud cover exceeds a certain threshold, the transportation time is also extended by a fixed time for each unit increase in cloud cover; the same method is used to calculate the remaining variable data factors to obtain corresponding initial extension times; the multiple initial extension times are weighted and summed to obtain a total extension time, and the total extension time is adjusted according to the results of the comprehensive evaluation model to reflect the comprehensive impact of weather changes on transportation time. The predicted arrival time is obtained based on the original estimated arrival time and the total extended time. The original estimated arrival time is the estimated arrival time when the goods are first transported. The total extended time is generated based on the influence of the changed data. The sum of the original estimated arrival time and the total extended time is used as the new predicted arrival time.

[0031] In some embodiments, the overall process analysis report includes monitoring data of the entire cargo transportation process, the number of changes in the predicted arrival time and the reason analysis, the original estimated arrival time and the actual arrival time.

[0032] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: This application can effectively improve the transparency and traceability of cargo transportation by setting up information monitoring for the entire cargo transportation process; by establishing a comprehensive evaluation model, monitoring and analyzing the changing data source, obtaining the extension time and predicting the arrival time, ensuring that users can obtain cargo status information in a timely manner, and achieving the effects of information transparency, dynamic adjustment, real-time monitoring, and timely feedback.

[0033] Example 2: In Example 1, by setting up information monitoring of the entire cargo transportation process and establishing a comprehensive evaluation model, the cargo transportation status is obtained in real time. This example makes further improvements on the above basis.

[0034] Continue to refer Figure 1 , the method further includes: S300: numbering each transport route according to the overall process analysis report, recording its starting point, end point and transfer nodes along the way, obtaining the transport completion degree, error time value and actual transfer time of each transfer node corresponding to each transport route, and dynamically planning the transport route according to the optimization mechanism; S400: Obtain the cargo data information, further refine the classification based on cargo characteristics, set transportation requirements and arrival time sensitivity indicators for each type of cargo, and form a rigid transportation standard; S500: Integrate steps S300 and S400 to select the optimal differentiated transportation route based on the rigid transportation standards.

[0035] The transport completion rate refers to the proportion of goods transported to the destination within the original estimated arrival time, indicating that there were no delays during the transport process and the transport task was completed within the predetermined time standard; the transfer node is the transfer location in the transport route, and the actual transfer time of the transfer node is recorded at the same time. The transfer location here includes but is not limited to different flights and different customs, all situations involving cargo transfer, which should be marked as transfer nodes and the actual transfer time should be recorded. The actual transfer time refers to the actual usage time from the transfer node to the next transfer node after handing over the cargo data; the error time value is the time difference between the original estimated arrival time and the actual arrival time, which is used to evaluate the punctuality of the transport route.

[0036] In some embodiments, the optimization mechanism is based on the degree of transport completion, error time value and actual transit time, and is based on a genetic algorithm dynamic programming to form several transport routes. Further refined classification according to cargo characteristics refers to further refining cargo data information, such as the fragility, shelf life, value, etc. of the cargo, setting transportation requirements and arrival time sensitivity indicators for the cargo. The transportation requirements and arrival time sensitivity are both the actual and mandatory transportation requirements and time limits for cargo transportation by users, forming a rigid transportation standard, and selecting the optimal differentiated transportation route based on the rigid transportation standard. The differentiated transportation route is to achieve the maximum degree of transport completion and the shortest error time value under the premise of meeting the rigid transportation standard. By setting several optional optimal transportation routes, and then matching them with the rigid transportation standards after the refined classification of the cargo, the final differentiated transportation route is formed.

[0037] Specifically, a genetic algorithm is a search algorithm that simulates natural selection and heredity. It seeks the optimal solution by simulating the biological evolutionary process. In route planning, a genetic algorithm can gradually optimize the optimal transportation route through operations such as selection, crossover, and mutation. The specific steps for dynamically planning the optimal transportation route using a genetic algorithm are as follows: Each transportation route is encoded as an individual, and each individual is represented using a specific encoding method, such as binary or decimal. In route planning, each individual is represented as a path sequence, with each element in the sequence representing a node (such as a flight, customs, etc.). A set of initial paths is randomly generated as the initial population, and the population size is determined based on the problem scale and actual conditions. A fitness function is defined to evaluate the quality of each path, taking into account multiple factors such as path length, transportation time, and transportation cost. For each individual in the population, its fitness value is calculated. The higher the fitness value, the better the path; a tournament selection strategy is used to select individuals with higher fitness from the population as parents to generate the next generation of individuals for subsequent crossover and mutation operations; a multi-point crossover method is used to exchange some gene fragments of the parent individuals to generate new individuals, and a certain number of offspring individuals are generated through crossover operations as part of the next generation population; a smaller mutation probability is set to simulate gene mutations in the process of biological evolution. For each individual in the offspring population, some of its gene fragments are randomly changed with the mutation probability to generate new individuals; the parent population and the offspring population are merged to form a new generation population. According to the fitness value, the individual with the highest fitness is selected from the new generation population as the optimal solution; a maximum number of iterations is set. If the maximum number of iterations is reached, the algorithm is terminated and the optimal solution is output; otherwise, the iteration continues.

[0038] Based on the first embodiment, this embodiment evaluates and analyzes the historical flight planning paths and transfer nodes and replans them to further shorten the error time value. In combination with the refined classification of goods, the optimal differentiated transportation path is selected to improve transportation efficiency and reduce extension time.

[0039] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: This application optimizes transportation route selection and improves transportation efficiency through evaluation and analysis of transportation routes and transfer nodes; combines the refined classification of goods to select the most appropriate differentiated transportation routes and plans, minimizing extended time and transportation costs; improves the punctuality and reliability of cargo transportation, and enhances user satisfaction and user experience.

[0040] Embodiment 3: This embodiment makes further improvements based on the above embodiment.

[0041] In the above embodiment, the transportation routes are replanned and the goods are finely classified to form the optimal differentiated transportation routes. However, in actual applications, due to the multi-party uncertainties of the changing data sources, it will still cause the problem of extended time for multiple transportation routes. This embodiment makes further improvements on the above basis.

[0042] In step S500, it also includes: obtaining a single logistics order, obtaining an acceptable error time value, marking the maximum acceptable error time value among all orders in the current batch as the acceptable error time value; using the particle swarm optimization algorithm to comprehensively optimize the transportation routes of all orders with the goal of minimizing the overall error time value.

[0043] In some embodiments, an acceptable time error value is determined for each logistics order as a constraint for subsequent optimization. An initial range of acceptable time error values is set based on the rigid transportation standards of each order (such as arrival time sensitivity, cargo characteristics, etc.). Taking into account the customer's tolerance for transportation time and the historical transportation delays of this type of cargo, the initial range is adjusted to obtain the final acceptable time error value. The acceptable time error value refers to setting the original predicted arrival time as the time range, and the difference in the time range is the acceptable time error value. Among all orders in the current batch, the maximum acceptable time error value is found and marked as the acceptable time error value. As an important constraint for the overall optimization, the acceptable time error values of all orders are traversed to find the maximum value, i.e., the time error value. This value will be used as an important parameter in the particle swarm optimization algorithm to limit the optimization range of the overall transportation time.

[0044] In some embodiments, the error-tolerant time value is used as an optimization constraint of a particle swarm optimization algorithm. The specific steps for comprehensive optimization using the particle swarm optimization algorithm are as follows: randomly generate a group of particles, each particle represents a transportation path plan; calculate the fitness function value for each particle and evaluate its quality; compare the fitness of the current particle with its historical optimal value and update the individual optimal position; compare the fitness of all particles and update the global optimal position; adjust the speed and position of each particle according to the fitness function value and the update rule; determine whether the maximum number of iterations has been reached. If the termination condition is met, output the global optimal position as the optimized transportation path plan.

[0045] Specifically, particle swarm optimization is an optimization algorithm based on swarm intelligence. It imitates the foraging behavior of bird flocks and finds the optimal solution through information sharing and collaboration between particles. Each particle represents a possible transportation route plan. A group of particles is randomly generated, and each particle contains the transportation route information of all orders (starting point, end point, transit nodes, etc.). The fitness function is used to evaluate the pros and cons of each transportation route plan, taking into account multiple factors such as the overall error time value, transportation cost, path length, etc. The fitness function is defined as the weighted sum of these factors. The overall acceptable error time value is used as the main component of the fitness function, and the weight is set. To reflect its importance, the particle's speed and position are updated based on the fitness function value. The speed update formula considers the current speed, the difference between the individual optimal position and the global optimal position, and the inertia weight. The position update formula adjusts the particle's position based on the updated speed. In each iteration, each particle's fitness function value is compared with its historical optimal value to update the individual optimal position. Simultaneously, the fitness function values of all particles are compared to update the global optimal position. A maximum number of iterations or a convergence threshold for the fitness function value is set as the termination condition. When the termination condition is met, the global optimal position is output as the optimized transportation route plan. In the particle swarm optimization algorithm described above, the input data includes basic information about all orders (starting point, end point, cargo characteristics, etc.); hard transportation standards (arrival time sensitivity, tolerance time), transshipment node information (including transshipment time, transshipment cost, etc.); and particle swarm optimization algorithm parameters (such as the number of particles, number of iterations, inertia weight, etc.). The output data is the optimized transportation route plan, including each route's starting point, end point, transshipment nodes along the way, and estimated arrival time; as well as the optimization results for optimization metrics such as overall tolerance time and transportation cost.

[0046] The technical solutions in the above embodiments of the present application have at least the following technical effects or advantages: This application can more effectively utilize transportation resources and reduce unnecessary transfer and waiting time through refined classification and differentiated transportation route planning, thereby improving overall transportation efficiency; introducing the error-tolerant time value as an optimization constraint, continuously updating the individual optimal position and the global optimal position, and achieving the effect of maximizing overall transportation efficiency.

[0047] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Various modifications and variations are readily apparent to those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A civil aviation cargo tracking method, characterized in that: The method comprises: S100: Collect cargo data information, match aircraft models and arrange transportation plans based on the cargo data information, monitor the entire process in real time, and provide feedback on the monitoring data information; S200: Acquire monitoring data information, obtain comprehensive evaluation results based on the comprehensive evaluation model, dynamically adjust the predicted value of the cargo arrival time, provide feedback to the client, and generate an overall process analysis report; S300: Based on the overall process analysis report, each transport route is numbered, and its starting point, end point, and transfer nodes along the way are recorded. The transport completion degree, error time value, and actual transfer time of each transfer node corresponding to each transport route are obtained, and the transport route is dynamically planned according to the optimization mechanism; S400: Obtain the cargo data information, further refine the classification based on cargo characteristics, set transportation requirements and arrival time sensitivity indicators for each type of cargo, and form a rigid transportation standard; S500: Integrate steps S300 and S400 to select the optimal differentiated transportation route based on the rigid transportation standards.

2. A civil aviation cargo tracking method according to claim 1, characterized in that: The cargo data information refers to the size, type, weight and volume of the cargo; the monitoring data information includes flight information, flight status, waybill information, waybill status, customs status and variable data source; the variable data source includes wind speed, cloud coverage, wind direction, precipitation, visibility, temperature and humidity information.

3. A civil aviation cargo tracking method according to claim 1, characterized in that: The comprehensive evaluation model adopts the long short-term memory network model as the basic model to predict the transportation time in cargo tracking, takes monitoring data information as input data, outputs the predicted arrival time, and obtains a comprehensive evaluation result.

4. A civil aviation cargo tracking method according to claim 1, characterized in that: Dynamically adjusting the predicted value of the cargo arrival time according to the comprehensive evaluation result includes: presetting extension time thresholds corresponding to different data, comparing the real-time data of the monitored variable data source with the extension time thresholds respectively, and calculating multiple initial extension times; performing weighted summation on the multiple initial extension times to obtain the total extension time, and then obtaining the predicted arrival time based on the original estimated arrival time and the total extension time.

5. A civil aviation cargo tracking method according to claim 1, characterized in that: The overall process analysis report includes monitoring data of the entire cargo transportation process, the number of changes in the predicted arrival time and the analysis of the reasons, the original estimated arrival time and the actual arrival time.

6. A civil aviation cargo tracking method according to claim 1, characterized in that: The transport completion rate refers to the proportion of goods transported to the destination within the original estimated arrival time; the transfer node is the transfer location in the transport route, and the actual transfer time of the transfer node is recorded at the same time; the error time value is the time difference between the original estimated arrival time and the actual arrival time.

7. A civil aviation cargo tracking method according to claim 1, characterized in that: The optimization mechanism is based on the transport completion degree, error time value and actual transit time, and composes several transport routes based on genetic algorithm dynamic programming.

8. A civil aviation cargo tracking method according to claim 1, characterized in that: In step S500, it also includes: obtaining a single logistics order, obtaining an acceptable error time value, marking the maximum acceptable error time value among all orders in the current batch as the acceptable error time value; using the particle swarm optimization algorithm to comprehensively optimize the transportation routes of all orders with the goal of minimizing the overall error time value.

9. A civil aviation cargo tracking method according to claim 8, characterized in that: The acceptable error time value refers to setting the original predicted arrival time as a time range, and the difference in the time range is the acceptable error time value.

10. A civil aviation cargo tracking method according to claim 8, characterized in that: The error-tolerant time value is used as an optimization constraint of the particle swarm optimization algorithm. The specific steps of comprehensive optimization using the particle swarm optimization algorithm are as follows: randomly generate a group of particles, each particle represents a transportation path plan; calculate the fitness function value for each particle and evaluate its quality; compare the fitness of the current particle with its historical optimal value and update the individual optimal position; compare the fitness of all particles and update the global optimal position; adjust the speed and position of each particle according to the fitness function value and the update rule; determine whether the maximum number of iterations has been reached. If the termination condition is met, output the global optimal position as the optimized transportation path plan.

Images