Trunk transportation statistical method, device and equipment and storage medium

Abstract

This invention relates to the field of logistics technology and discloses a statistical method for trunk line transportation, comprising: collecting trunk line transportation data; constructing a timeout risk prediction model by inputting influencing factor data and time characteristics into a trained timeout risk prediction model to obtain a timeout risk probability value; calculating the timeout rate by calculating the timeliness compliance rate based on the timeout risk probability value and calculating the predicted timeout rate of the route to generate a risk ranking; generating optimization strategies by automatically matching and generating differentiated dynamic optimization strategies for routes with different risk levels based on the predicted timeout rate and risk ranking; and outputting the strategies by outputting the generated dynamic optimization strategies in the form of specific optimization measures and suggestions. This invention achieves accurate quantitative assessment of transportation timeout risk, can automatically calculate the predicted timeout rate of the route and rank the risks, and generate and output dynamic optimization strategies; effectively improving the timeliness management level and risk response capability of trunk line transportation.

Description

Technical Field

[0001] This invention relates to the field of logistics information technology, and in particular to a method, apparatus, equipment and storage medium for trunk transportation statistics. Background Technology

[0002] In the logistics and transportation sector, trunk line transportation is a crucial link connecting logistics hubs across regions, and its efficiency directly impacts the operational effectiveness of the entire logistics network. Currently, the statistical methods for trunk line transportation qualification rates have the following shortcomings: First, actual transport vehicles include contracted vehicles, trucks, and scheduled trucks, while existing methods only statistically analyze the overall qualification rate without segmenting them by vehicle type, making it difficult to provide differentiated management basis for various vehicle types. Second, existing statistical methods are generally based on fixed time dimensions such as days, weeks, and months, lacking flexible displays of dynamic time dimensions, such as monthly cumulative statistics. This fixed-time statistical method cannot meet the real-time monitoring needs of enterprises regarding transportation status. Finally, existing systems often rank trunk line transportation based on qualification rates, but in actual operation, routes or distribution centers with higher overtime rates often require more focus and improvement. The existing ranking logic for transportation qualification rates fails to reflect this management orientation, leading to a disconnect between statistical results and actual control needs.

[0003] Therefore, it is necessary to invent a statistical method, apparatus, equipment, and storage medium for trunk transportation that can improve trunk transportation statistics, differentiate and display overdue routes or distribution centers that need improvement, and enhance transportation management. Summary of the Invention

[0004] This invention provides a trunk transportation statistics method, apparatus, equipment, and storage medium for improving the statistical methods of trunk transportation, enabling differentiated identification and display of overdue routes or distribution centers that require improvement, and enhancing transportation management.

[0005] The first aspect of this invention provides a trunk transportation statistics method, the trunk transportation statistics method comprising: Collect trunk line transportation data, including operational status data and influencing factor data of trunk line transportation through the logistics transportation system; A timeout risk prediction model is constructed by inputting the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value. Calculate the overtime rate, based on the overtime risk probability value, statistically analyze the timeliness qualification rate according to vehicle type, and calculate the predicted overtime rate of the route to generate a risk ranking; The optimization strategy is generated by automatically matching and generating differentiated dynamic optimization strategies for lines with different risk levels based on the predicted timeout rate and its risk ranking. The output strategy is to output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

[0006] Optionally, in a first implementation of the first aspect of the present invention, the collection of trunk transportation data, which involves collecting operational status data and influencing factor data of trunk transportation through a logistics transportation system, includes: Obtain basic operational data from the database of the logistics and transportation system; Data on influencing factors are collected from external data sources and internal operational records, including external environmental factors and internal operational factors. The basic operational data and the influencing factor data are preprocessed to obtain a multi-source data system.

[0007] Optionally, in a second implementation of the first aspect of the present invention, the step of constructing a timeout risk prediction model, which involves inputting the influencing factor data and time characteristics into a trained timeout risk prediction model to obtain a timeout risk probability value, includes: The timeout risk prediction model is constructed using the XGBoost algorithm; The vehicle type, weather conditions, road congestion index, historical overtime rate, driver experience, cargo type, and time characteristics in the influencing factor data are input into the overtime risk prediction model. The timeout risk prediction model outputs the timeout risk probability value.

[0008] Optionally, in a third implementation of the first aspect of the present invention, the calculation of the timeout rate, based on the timeout risk probability value, statistically calculating the timeliness qualification rate according to vehicle type, and calculating the predicted timeout rate of the route to generate a risk ranking, includes: The timeout risk probability value is used as the predicted pass rate of the corresponding line in the future preset period. Calculate the predicted timeout rate for each line, wherein the predicted timeout rate and the predicted pass rate are complementary. Based on the calculated predicted timeout rate, the lines are sorted in descending order from high to low to generate a risk ranking. Calculate the overall timeliness pass rate for the vehicle category based on the predicted pass rate of the routes included in the vehicle.

[0009] Optionally, in a fourth implementation of the first aspect of the present invention, the optimization strategy generation, based on the predicted timeout rate and its risk ranking, automatically matches and generates differentiated dynamic optimization strategies for lines with different risk levels, including: Preset a first risk threshold and a second risk threshold; The lines with a predicted timeout rate greater than the first risk threshold are identified as high-risk lines, and a first type of optimization strategy is generated for the high-risk lines. The lines whose predicted timeout rate is greater than the second risk threshold and less than or equal to the first risk threshold are identified as medium-risk lines, and a second type of optimization strategy is generated for the medium-risk lines. Lines with a predicted timeout rate less than or equal to the second risk threshold are identified as low-risk lines, and a third type of optimization strategy is generated for the low-risk lines.

[0010] Optionally, in a fifth implementation of the first aspect of the present invention, the output strategy outputs the generated dynamic optimization strategy in the form of specific optimization measures and suggestions, including: For high-risk lines, output specific scheduling instructions corresponding to the first type of optimization strategy; For lines with medium risk levels, output monitoring and coordination instructions corresponding to the second type of optimization strategy; For low-risk lines, output status confirmation information corresponding to the third type of optimization strategy; The scheduling instructions, the monitoring and coordination instructions, and the status confirmation information are pushed and displayed through a visual interface or system interface; The dispatching instructions include the names of specific road sections to be avoided, recommended alternative transportation routes, and estimated time savings; the monitoring and coordination instructions include key road sections requiring enhanced monitoring, service stations along the route requiring coordination, and resource information.

[0011] Optionally, in a sixth implementation of the first aspect of the present invention, the trunk transport statistics method further includes: Data updates and model iterations are performed based on the actual transportation results after the execution of the dynamic optimization strategy. Feedback data is collected and used to update the parameters and retrain the timeout risk prediction model.

[0012] A second aspect of the present invention provides a trunk line transportation statistics device, comprising: The trunk transportation data acquisition module is used to collect operational status data and influencing factor data of trunk transportation through the logistics transportation system; The module for collecting trunk line transportation data includes: The acquisition unit is used to acquire basic operational data from the database of the logistics and transportation system; The data acquisition unit collects influencing factor data from external data sources and internal operational records, including external environmental factors and internal operational factors. The preprocessing unit preprocesses the basic operational data and the influencing factor data to obtain a multi-source data system.

[0013] A timeout risk prediction model module is constructed to input the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value; The module for constructing the timeout risk prediction model includes: The construction unit is used to construct the timeout risk prediction model using the XGBoost algorithm; The input unit takes the vehicle type, weather conditions, road congestion index, historical overtime rate, driver experience, cargo type, and time characteristics from the influencing factor data as input features and inputs them into the overtime risk prediction model. The prediction unit outputs the timeout risk probability value through the timeout risk prediction model.

[0014] The timeout rate calculation module is used to calculate the timeliness qualification rate according to the vehicle type based on the timeout risk probability value, and calculate the predicted timeout rate of the route to generate a risk ranking. The timeout rate calculation module includes: The timeout risk probability value is used as the predicted pass rate of the corresponding line in the future preset period. The first calculation unit is used to calculate the prediction timeout rate for each line, wherein the prediction timeout rate and the prediction pass rate are complementary. The sorting unit sorts the lines in descending order from high to low based on the calculated predicted timeout rate, generating a risk ranking. The second calculation unit calculates the overall timeliness pass rate of the vehicle category based on the predicted pass rate of the routes included in the vehicle.

[0015] The optimization strategy generation module is used to automatically match and generate differentiated dynamic optimization strategies for lines with different risk levels based on the predicted timeout rate and its risk ranking. The optimization strategy generation module includes: The preset unit is used to preset the first risk threshold and the second risk threshold; The determination unit identifies routes with a prediction timeout rate greater than the first risk threshold as high-risk routes and generates a first type of optimization strategy for the high-risk routes; identifies routes with a prediction timeout rate greater than the second risk threshold and less than or equal to the first risk threshold as medium-risk routes and generates a second type of optimization strategy for the medium-risk routes; and identifies routes with a prediction timeout rate less than or equal to the second risk threshold as low-risk routes and generates a third type of optimization strategy for the low-risk routes.

[0016] The output strategy module is used to output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

[0017] The output strategy module includes: The output unit is used to output specific scheduling instructions corresponding to the first type of optimization strategy for high-risk lines; to output monitoring and coordination instructions corresponding to the second type of optimization strategy for medium-risk lines; and to output status confirmation information corresponding to the third type of optimization strategy for low-risk lines. The push unit is used to push and display the scheduling instructions, the monitoring and coordination instructions, and the status confirmation information through a visual interface or system interface; The dispatching instructions include the names of specific road sections to be avoided, recommended alternative transportation routes, and estimated time savings; the monitoring and coordination instructions include key road sections requiring enhanced monitoring, service stations along the route requiring coordination, and resource information.

[0018] A third aspect of the present invention provides a trunk transportation statistics device, comprising a memory and at least one processor, wherein the memory stores computer-readable instructions; The at least one processor invokes the computer-readable instructions in the memory to perform the various steps of the trunk transport statistics method as described above.

[0019] A fourth aspect of the present invention provides a computer-readable storage medium storing computer-readable instructions, which, when executed by a processor, implement the various steps of the trunk transportation statistics method described above.

[0020] This invention achieves accurate quantitative assessment of transportation delay risks by automatically collecting trunk transportation data and constructing a predictive model, thus improving the statistical methods of trunk transportation. It can automatically calculate the predicted delay rate of routes and rank them by risk, differentiate them, and display the delay routes or distribution centers that need improvement. Furthermore, it generates and outputs targeted dynamic optimization strategies for routes with different risk levels. This forms a complete closed loop of data collection, risk prediction, and strategy generation, which can effectively improve the timeliness management level and risk response capability of trunk transportation. Attached Figure Description

[0021] Figure 1 This is a first flowchart of the trunk transportation statistics method provided in an embodiment of the present invention; Figure 2 This is a second flowchart of the trunk transportation statistics method provided in an embodiment of the present invention; Figure 3This is a third flowchart of the trunk transportation statistics method provided in the embodiments of the present invention; Figure 4 This is a fourth flowchart of the trunk transportation statistics method provided in the embodiments of the present invention; Figure 5 The fifth flowchart of the trunk transportation statistics method provided in the embodiments of the present invention; Figure 6 The sixth flowchart of the trunk transportation statistics method provided in the embodiments of the present invention; Figure 7 This is a schematic diagram of the structure of the trunk transportation statistics device provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of the trunk transportation statistics device provided in an embodiment of the present invention. Detailed Implementation

[0022] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 The first embodiment of a trunk line transportation statistics method according to the present invention includes: S101. Collect trunk line transportation data, and collect the operation status data and influencing factor data of trunk line transportation through the logistics transportation system; S102. Construct a timeout risk prediction model by inputting the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value. S103. Calculate the overtime rate. Based on the overtime risk probability value, calculate the timeliness qualification rate according to the vehicle type, and calculate the predicted overtime rate of the route to generate a risk ranking. S104. Optimization strategy generation: Based on the predicted timeout rate and its risk ranking, automatically match and generate differentiated dynamic optimization strategies for lines with different risk levels. S105. Output strategy: Output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

[0024] This invention, through the automatic collection of trunk transportation data and the construction of a predictive model, achieves accurate quantitative assessment of transportation timeout risks and improves the statistical methods of trunk transportation. It can automatically calculate the predicted timeout rate of routes and rank them by risk, differentiate them, and display the timeout routes or distribution centers that need improvement. Furthermore, it generates and outputs targeted dynamic optimization strategies for routes with different risk levels. This forms a complete closed loop of data collection, risk prediction, and strategy generation, which can effectively improve the timeliness management level and risk response capability of trunk transportation.

[0025] Please see Figure 2 The second embodiment of the trunk transportation statistical method in this invention involves collecting trunk transportation data, which includes collecting operational status data and influencing factor data of trunk transportation through the logistics transportation system. S201. Obtain basic operational data from the database of the logistics and transportation system; S202. Collect influencing factor data from external data sources and internal operational records, wherein the influencing factor data includes external environmental factors and internal operational factors; S203. Preprocess the basic operating data and the influencing factor data to obtain a multi-source data system.

[0026] This invention, through the integration of internal databases, external data sources, and internal operational records within a logistics and transportation system, constructs a comprehensive data system covering basic operational status, external environment, and internal operational factors. This method ensures the multi-source nature and integrity of the data, providing a comprehensive and accurate data foundation for subsequent risk prediction models. Simultaneously, the preprocessing steps standardize the data format and improve data quality, thereby guaranteeing the reliability and effectiveness of the overall analysis process.

[0027] Please see Figure 3 A third embodiment of a trunk line transportation statistical method according to the present invention includes constructing a timeout risk prediction model by inputting the influencing factor data and time characteristics into a trained timeout risk prediction model to obtain a timeout risk probability value, comprising: S301. The timeout risk prediction model is constructed using the XGBoost algorithm; S302. Input the vehicle type, weather conditions, road congestion index, historical overtime rate, driver experience, cargo type and time characteristics from the influencing factor data into the overtime risk prediction model. S303. Output the timeout risk probability value through the timeout risk prediction model.

[0028] This invention employs the high-performance XGBoost algorithm and selects multiple key factors as model inputs, including vehicle type, weather conditions, road congestion, historical performance, driver experience, cargo attributes, and time characteristics. This design enables the model to deeply explore complex nonlinear relationships, thereby achieving accurate and quantitative assessment of trunk line transportation timeout risks. This embodiment improves the accuracy and scientific rigor of risk prediction, providing core decision-making basis for subsequent statistical analysis, risk ranking, and strategy optimization.

[0029] Please see Figure 4 The fourth embodiment of a trunk line transportation statistical method in this invention includes calculating the overtime rate, which involves calculating the timeliness compliance rate based on the overtime risk probability value, categorizing the vehicles by type, and calculating the predicted overtime rate of the route to generate a risk ranking. S401. The timeout risk probability value is used as the predicted pass rate of the corresponding line in the future preset time period; S402. Calculate the predicted timeout rate for each line, wherein the predicted timeout rate and the predicted pass rate are complementary. S403. Based on the calculated predicted timeout rate, sort the lines in descending order from high to low to generate a risk ranking; S404. Calculate the overall timeliness pass rate of the vehicle category based on the predicted pass rate of the routes included in the vehicle.

[0030] This invention directly quantifies the timeout risk probability value output by the model into the predicted timeout rate of the route, and generates a clear risk ranking based on this, transforming the abstract risk assessment into an intuitive and comparable management view. Furthermore, this method not only focuses on route risk but also considers the comprehensive timeliness compliance rate statistically calculated by vehicle category.

[0031] Please see Figure 5 The fifth embodiment of a trunk line transportation statistics method in this invention includes the generation of optimization strategies. Based on the predicted timeout rate and its risk ranking, differentiated dynamic optimization strategies are automatically matched and generated for routes with different risk levels, including: S501, Preset the first risk threshold and the second risk threshold; S502. The lines with a predicted timeout rate greater than the first risk threshold are identified as high-risk lines, and a first type of optimization strategy is generated for the high-risk lines. S503. Determine the lines whose predicted timeout rate is greater than the second risk threshold and less than or equal to the first risk threshold as medium-risk lines, and generate a second type of optimization strategy for the medium-risk lines. S504. Determine the lines whose predicted timeout rate is less than or equal to the second risk threshold as low-risk lines, and generate a third type of optimization strategy for the low-risk lines.

[0032] This invention automatically classifies railway lines into high, medium, and low risk levels by pre-setting specific risk thresholds, and automatically generates differentiated optimization strategies for each level. This method closely integrates prediction results with actual operation and management, achieving an automated closed loop from risk identification to response strategies. It ensures that limited management resources are prioritized for high-risk lines, implementing strong intervention measures, while adopting matching optimization or maintenance strategies for medium- and low-risk lines, thereby significantly improving the accuracy, efficiency, and intelligence of risk management.

[0033] Please see Figure 6 In a sixth embodiment of a trunk transportation statistics method of the present invention, the output strategy outputs the generated dynamic optimization strategy in the form of specific optimization measures and suggestions, including: S601. For high-risk lines, output specific scheduling instructions corresponding to the first type of optimization strategy; S602. For medium-risk lines, output monitoring and coordination instructions corresponding to the second type of optimization strategy; S603. For low-risk lines, output status confirmation information corresponding to the third type of optimization strategy; S604. The scheduling instruction, the monitoring and coordination instruction, and the status confirmation information are pushed and displayed through a visual interface or system interface; The dispatching instructions include the names of specific road sections to be avoided, recommended alternative transportation routes, and estimated time savings; the monitoring and coordination instructions include key road sections requiring enhanced monitoring, service stations along the route requiring coordination, and resource information.

[0034] In this embodiment of the invention, differentiated and structured information, ranging from specific scheduling instructions to monitoring and coordination instructions and status confirmation information, is output according to different risk levels. The information is clear and operable. Pushing this information through a visual interface or system interface ensures that the strategy can directly and efficiently reach relevant management personnel and operating systems.

[0035] In some embodiments, the trunk transport statistics method further includes: Data updates and model iterations are performed based on the actual transportation results after the execution of the dynamic optimization strategy. Feedback data is collected and used to update the parameters and retrain the timeout risk prediction model.

[0036] The embodiments of the present invention effectively improve the dynamic adaptability and long-term prediction accuracy of the model, ensuring that the entire trunk transportation statistics and risk management system can continue to evolve over time, maintaining its effectiveness and advancement.

[0037] The trunk line transportation statistics method in the embodiments of the present invention has been described above. The apparatus in the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 7 The implementation methods of the trunk line transportation statistics device in this invention include: The trunk transportation data acquisition module 701 is used to collect trunk transportation operation status data and influencing factor data through the logistics transportation system; In some embodiments, the trunk transportation data acquisition module 701 includes: The acquisition unit 7011 is used to acquire basic operational data from the database of the logistics and transportation system. The data acquisition unit 7012 collects influencing factor data from external data sources and internal operational records, including external environmental factors and internal operational factors. The preprocessing unit 7013 preprocesses the basic operating data and the influencing factor data to obtain a multi-source data system.

[0038] This invention, through the integration of internal databases, external data sources, and internal operational records within a logistics and transportation system, constructs a comprehensive data system covering basic operational status, external environment, and internal operational factors. This method ensures the multi-source nature and integrity of the data, providing a comprehensive and accurate data foundation for subsequent risk prediction models. Simultaneously, the preprocessing steps standardize the data format and improve data quality, thereby guaranteeing the reliability and effectiveness of the overall analysis process.

[0039] A timeout risk prediction model module 702 is used to input the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value; In some embodiments, the module 702 for constructing the timeout risk prediction model includes: Construction unit 7021 is used to construct the timeout risk prediction model using the XGBoost algorithm; Input unit 7022 inputs vehicle type, weather conditions, road congestion index, historical overtime rate, driver experience, cargo type and time characteristics from the influencing factor data into the overtime risk prediction model; The prediction unit 7023 outputs the timeout risk probability value through the timeout risk prediction model.

[0040] This invention employs the high-performance XGBoost algorithm and selects multiple key factors as model inputs, including vehicle type, weather conditions, road congestion, historical performance, driver experience, cargo attributes, and time characteristics. This design enables the model to deeply explore complex nonlinear relationships, thereby achieving accurate and quantitative assessment of trunk line transportation timeout risks. This embodiment improves the accuracy and scientific rigor of risk prediction, providing core decision-making basis for subsequent statistical analysis, risk ranking, and strategy optimization.

[0041] The timeout rate calculation module 703 is used to calculate the timeliness qualification rate according to the vehicle type based on the timeout risk probability value, and calculate the predicted timeout rate of the route to generate a risk ranking. In some embodiments, the timeout rate calculation module 703 includes: The timeout risk probability value is used as the predicted pass rate of the corresponding line in the future preset period. The first calculation unit 7031 is used to calculate the predicted timeout rate for each line, wherein the predicted timeout rate and the predicted pass rate are complementary. The sorting unit 7032 sorts the lines in descending order from high to low based on the calculated predicted timeout rate to generate a risk ranking. The second calculation unit 7033 calculates the comprehensive timeliness qualification rate of the vehicle category based on the predicted qualification rate of the route included in the vehicle.

[0042] This invention directly quantifies the timeout risk probability value output by the model into the predicted timeout rate of the route, and generates a clear risk ranking based on this, transforming the abstract risk assessment into an intuitive and comparable management view. Furthermore, this method not only focuses on route risk but also considers the comprehensive timeliness compliance rate statistically calculated by vehicle category.

[0043] The optimization strategy generation module 704 is used to automatically match and generate differentiated dynamic optimization strategies for lines with different risk levels based on the predicted timeout rate and its risk ranking. In some embodiments, the optimization strategy generation module 704 includes: The preset unit 7041 is used to preset the first risk threshold and the second risk threshold; The determination unit 7042 determines lines with a prediction timeout rate greater than the first risk threshold as high-risk lines and generates a first type of optimization strategy for the high-risk lines; determines lines with a prediction timeout rate greater than the second risk threshold and less than or equal to the first risk threshold as medium-risk lines and generates a second type of optimization strategy for the medium-risk lines; and determines lines with a prediction timeout rate less than or equal to the second risk threshold as low-risk lines and generates a third type of optimization strategy for the low-risk lines.

[0044] This invention automatically classifies railway lines into high, medium, and low risk levels by pre-setting specific risk thresholds, and automatically generates differentiated optimization strategies for each level. This method closely integrates prediction results with actual operation and management, achieving an automated closed loop from risk identification to response strategies. It ensures that limited management resources are prioritized for high-risk lines, implementing strong intervention measures, while adopting matching optimization or maintenance strategies for medium- and low-risk lines, thereby significantly improving the accuracy, efficiency, and intelligence of risk management.

[0045] The output strategy module 705 is used to output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

[0046] In some embodiments, the output strategy module 705 includes: The output unit 7051 is used to output specific scheduling instructions corresponding to the first type of optimization strategy for high-risk lines; to output monitoring and coordination instructions corresponding to the second type of optimization strategy for medium-risk lines; and to output status confirmation information corresponding to the third type of optimization strategy for low-risk lines. The push unit 7052 is used to push and display the scheduling instructions, the monitoring and coordination instructions and the status confirmation information through a visual interface or system interface; The dispatching instructions include the names of specific road sections to be avoided, recommended alternative transportation routes, and estimated time savings; the monitoring and coordination instructions include key road sections requiring enhanced monitoring, service stations along the route requiring coordination, and resource information.

[0047] This invention, through the automatic collection of trunk transportation data and the construction of a predictive model, achieves accurate quantitative assessment of transportation timeout risks and improves the statistical methods of trunk transportation. It can automatically calculate the predicted timeout rate of routes and rank them by risk, differentiate them, and display the timeout routes or distribution centers that need improvement. Furthermore, it generates and outputs targeted dynamic optimization strategies for routes with different risk levels. This forms a complete closed loop of data collection, risk prediction, and strategy generation, which can effectively improve the timeliness management level and risk response capability of trunk transportation.

[0048] Figure 7 The structure of the trunk transportation statistics device shown does not constitute a limitation on the trunk transportation statistics device, and can implement the steps of the trunk transportation statistics methods provided in the above-described method embodiments.

[0049] above Figure 7 The trunk transportation statistics device in this embodiment of the invention will be described in detail from the perspective of modular functional entities. The trunk transportation statistics device in this embodiment of the invention will be described in detail from the perspective of hardware processing.

[0050] Figure 8 This is a schematic diagram of the structure of a trunk transportation statistics device provided in an embodiment of the present invention. The device 800 can vary considerably depending on its configuration or performance, and may include one or more central processing units (CPUs) 810 (e.g., one or more processors) and a memory 820, and one or more storage media 830 (e.g., one or more mass storage devices) for storing application programs 833 or data 832. The memory 820 and storage media 830 can be temporary or persistent storage. The program stored in the storage media 830 may include one or more modules (not shown), each module including a series of instruction operations on the device 800. Furthermore, the processor 810 may be configured to communicate with the storage media 830 and execute the series of instruction operations stored in the storage media on the device 800.

[0051] Device 800 may also include one or more power supplies 840, one or more wired or wireless network interfaces 850, one or more input / output interfaces 860, and / or one or more operating systems 831, such as Windows Server, Mac OS X, Unix, Linux, FreeBSD, etc.

[0052] This invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the trunk transportation statistics method.

[0053] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the system, device, or unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0054] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0055] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A statistical method for trunk line transportation, characterized in that, The trunk line transportation statistical method includes: Collect trunk line transportation data, including operational status data and influencing factor data of trunk line transportation through the logistics transportation system; A timeout risk prediction model is constructed by inputting the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value. Calculate the overtime rate, based on the overtime risk probability value, statistically analyze the timeliness qualification rate according to vehicle type, and calculate the predicted overtime rate of the route to generate a risk ranking; The optimization strategy is generated by automatically matching and generating differentiated dynamic optimization strategies for lines with different risk levels based on the predicted timeout rate and its risk ranking. The output strategy is to output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

2. The trunk line transportation statistical method according to claim 1, characterized in that, The collection of trunk line transportation data involves gathering operational status data and influencing factor data for trunk line transportation through the logistics transportation system, including: Obtain basic operational data from the database of the logistics and transportation system; Data on influencing factors are collected from external data sources and internal operational records, including external environmental factors and internal operational factors. The basic operational data and the influencing factor data are preprocessed to obtain a multi-source data system.

3. The trunk line transportation statistical method according to claim 2, characterized in that, The construction of the timeout risk prediction model involves inputting the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value, including: The timeout risk prediction model is constructed using the XGBoost algorithm; The vehicle type, weather conditions, road congestion index, historical overtime rate, driver experience, cargo type, and time characteristics in the influencing factor data are input into the overtime risk prediction model. The timeout risk prediction model outputs the timeout risk probability value.

4. The trunk line transportation statistical method according to claim 3, characterized in that, The calculation of the timeout rate, based on the timeout risk probability value, statistically analyzes the timeliness compliance rate according to vehicle type, and calculates the predicted timeout rate of the route to generate a risk ranking, including: The timeout risk probability value is used as the predicted pass rate of the corresponding line in the future preset period. Calculate the predicted timeout rate for each line, wherein the predicted timeout rate and the predicted pass rate are complementary. Based on the calculated predicted timeout rate, the lines are sorted in descending order from high to low to generate a risk ranking. Calculate the overall timeliness pass rate for the vehicle category based on the predicted pass rate of the routes included in the vehicle.

5. The trunk line transportation statistical method according to claim 4, characterized in that, The optimization strategy generation, based on the predicted timeout rate and its risk ranking, automatically matches and generates differentiated dynamic optimization strategies for lines with different risk levels, including: Preset a first risk threshold and a second risk threshold; The lines with a predicted timeout rate greater than the first risk threshold are identified as high-risk lines, and a first type of optimization strategy is generated for the high-risk lines. The lines whose predicted timeout rate is greater than the second risk threshold and less than or equal to the first risk threshold are identified as medium-risk lines, and a second type of optimization strategy is generated for the medium-risk lines. Lines with a predicted timeout rate less than or equal to the second risk threshold are identified as low-risk lines, and a third type of optimization strategy is generated for the low-risk lines.

6. The trunk line transportation statistical method according to claim 5, characterized in that, The output strategy outputs the generated dynamic optimization strategy in the form of specific optimization measures and suggestions, including: For high-risk lines, output specific scheduling instructions corresponding to the first type of optimization strategy; For lines with medium risk levels, output monitoring and coordination instructions corresponding to the second type of optimization strategy; For low-risk lines, output status confirmation information corresponding to the third type of optimization strategy; The scheduling instructions, the monitoring and coordination instructions, and the status confirmation information are pushed and displayed through a visual interface or system interface; The dispatching instructions include the names of specific road sections to be avoided, recommended alternative transportation routes, and estimated time savings; the monitoring and coordination instructions include key road sections requiring enhanced monitoring, service stations along the route requiring coordination, and resource information.

7. The trunk line transportation statistical method according to claim 5, characterized in that, The trunk transport statistical method also includes: Data updates and model iterations are performed based on the actual transportation results after the execution of the dynamic optimization strategy. Feedback data is collected and used to update the parameters and retrain the timeout risk prediction model.

8. A trunk line transportation statistics device, characterized in that, include: The trunk transportation data acquisition module is used to collect operational status data and influencing factor data of trunk transportation through the logistics transportation system; A timeout risk prediction model module is constructed to input the influencing factor data and time characteristics into the trained timeout risk prediction model to obtain the timeout risk probability value; The timeout rate calculation module is used to calculate the timeliness qualification rate according to the vehicle type based on the timeout risk probability value, and calculate the predicted timeout rate of the route to generate a risk ranking. The optimization strategy generation module is used to automatically match and generate differentiated dynamic optimization strategies for lines with different risk levels based on the predicted timeout rate and its risk ranking. The output strategy module is used to output the generated dynamic optimization strategy in the form of specific optimization measures and suggestions.

9. A trunk line transportation statistics device, characterized in that, It includes a memory and at least one processor, wherein the memory stores computer-readable instructions; The at least one processor invokes the computer-readable instructions in the memory to perform the various steps of the trunk transport statistics method as described in any one of claims 1-7.

10. A computer-readable storage medium storing computer-readable instructions thereon, characterized in that, When the computer-readable instructions are executed by a processor, they implement the various steps of the trunk transport statistics method as described in any one of claims 1-7.

Images