Multimodal transport intelligent scheduling and tracking method, device, equipment and storage medium

Abstract

The present invention relates to a multimodal intelligent scheduling and tracking method, device, equipment and storage medium, the method comprising obtaining cargo data, cargo environment data and cargo status data of logistics cargo; performing data analysis on the cargo data to obtain comprehensive transportation data, performing environmental analysis on the cargo environment data to obtain comprehensive environmental data, performing status analysis on the cargo status data to obtain comprehensive status data; performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling plan based on the first path data; performing abnormal prediction on the first path data to obtain abnormal prediction data, and generating a second scheduling plan based on the abnormal prediction data; integrating the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, and optimizing the comprehensive scheduling plan in real time. The present invention can improve response speed and reduce logistics costs.

Description

Technical Field

[0001] The present invention relates to the technical field of multimodal transport, and in particular to a multimodal transport intelligent scheduling and tracking method, device, equipment and storage medium. Background Art

[0002] In the field of multimodal transport, traditional logistics scheduling methods often rely on manual experience, which is incapable of coping with complex transportation changes. Due to the lack of effective data analysis methods and technical support, it is difficult to accurately assess the transportation needs and environmental changes of goods, resulting in poor flexibility of scheduling plans, slow response speed and difficulty in dealing with emergencies. In addition, insufficient monitoring of the status of goods during the logistics process has led to frequent problems such as damage and loss of goods, which has brought a bad experience to customers and increased the operating costs of enterprises. Summary of the invention

[0003] The main purpose of the present invention is to provide a multimodal intelligent scheduling and tracking method, device, equipment and storage medium, which can reduce logistics operation costs and improve customer satisfaction.

[0004] To achieve the above objectives, the present invention provides a multimodal transport intelligent scheduling and tracking method, comprising:

[0005] Obtain cargo data, cargo environment data and cargo status data of logistics cargo;

[0006] Performing data analysis on the cargo data to obtain comprehensive transportation data, performing environmental analysis on the cargo environment data to obtain comprehensive environmental data, and performing status analysis on the cargo status data to obtain comprehensive status data;

[0007] Performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling plan based on the first path data;

[0008] Performing an abnormal prediction on the first route data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data;

[0009] The first scheduling plan and the second scheduling plan are integrated to obtain a comprehensive scheduling plan, tracking data of the logistics goods are obtained based on the comprehensive scheduling plan, and the comprehensive scheduling plan is optimized in real time according to the tracking data to obtain the optimized comprehensive scheduling plan.

[0010] Furthermore, the obtaining of cargo data, cargo environment data and cargo status data of logistics cargo includes:

[0011] The original logistics data is collected by a collection device deployed on the logistics goods, and the original logistics data is screened according to a preset screening rule to obtain logistics screening data;

[0012] Classify and sort the logistics screening data to obtain corresponding cargo screening data, environmental screening data and status screening data;

[0013] Check in sequence whether the cargo screening data, environment screening data and status screening data meet the preset data volume threshold requirements. When any of the cargo screening data, environment screening data and status screening data does not meet the data volume threshold requirements, re-acquire the original logistics data for screening and sorting;

[0014] When the cargo screening data, the environment screening data and the status screening data all meet the data volume threshold requirements, the cargo data, the cargo environment data and the cargo status data are output.

[0015] Further, the data analysis of the cargo data to obtain comprehensive transportation data, the environmental analysis of the cargo environment data to obtain comprehensive environmental data, and the state analysis of the cargo state data to obtain comprehensive state data include:

[0016] Extract key information from the cargo data to obtain basic attributes, transportation requirements and transportation targets, and comprehensively analyze and process the basic attributes, transportation requirements and transportation targets to obtain the comprehensive transportation data;

[0017] Extracting environmental information from the cargo environmental data to obtain environmental data and real-time location data, performing type analysis on the environmental data based on the real-time location data to obtain internal environmental data and external meteorological data of the transportation vehicle, and integrating the real-time location data, the internal environmental data and the external meteorological data to obtain the comprehensive environmental data;

[0018] The state information of the cargo state data is extracted to obtain collision state data and cargo health data, and the collision state data and cargo health data are comprehensively analyzed and processed to obtain the comprehensive state data.

[0019] Further, performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling scheme based on the first path data, includes:

[0020] Reading the comprehensive transportation data and the comprehensive environmental data to obtain the basic attributes, the transportation requirements, the transportation target, the real-time location data, the internal environmental data and the external meteorological data;

[0021] Performing a path analysis based on the transportation target and the real-time location data to obtain first path data, and performing a time prediction on the first path data based on the external meteorological data to obtain a first transportation time;

[0022] Performing time calculation according to the transportation requirements, the basic attributes and the internal environment data to obtain a transportation limit time, and acquiring a corresponding historical limit plan based on the transportation limit time;

[0023] Performing a time analysis on the first transportation time according to the transportation limit time to obtain a first deviation time, determining whether the first deviation time meets a preset time requirement, and when the first deviation time meets the preset time requirement, performing a scheme conversion on the first path data to obtain the first scheduling scheme;

[0024] When the first deviation time does not meet the preset time requirement, the first path data is regenerated based on the transportation target and the real-time location data with reference to the historical limited plan, and the first path data is converted into a plan to obtain the first scheduling plan.

[0025] Further, performing an abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data, includes:

[0026] Reading the cargo status data to obtain the collision status data and the cargo health data;

[0027] Based on the collision state data, risk prediction is performed on the first path data to obtain abnormal collision data, wherein the risk prediction process includes performing collision analysis on the collision state data to obtain corresponding historical collision times and historical collision intensities;

[0028] Performing path prediction on the first path data to obtain corresponding path conditions, mapping the historical collision times and historical collision intensities to the path conditions to perform road segment prediction to obtain corresponding road segment collision times and road segment collision intensities, and integrating the road segment collision times and road segment collision intensities;

[0029] Obtaining comprehensive data of the road section, detecting the comprehensive data of the road section according to a preset road section threshold, marking the comprehensive data of the road section exceeding the road section threshold as abnormal data, integrating all the abnormal data, and obtaining abnormal collision data;

[0030] Performing health prediction on the cargo health data according to the abnormal collision data to obtain transportation health;

[0031] Determine whether the transport health meets the preset health threshold requirement, and when the transport health does not meet the preset health threshold requirement, generate the second scheduling plan according to the first path data based on the abnormal collision data and the transport health;

[0032] Among them, the judgment formula for judging whether the transport health meets the preset health threshold requirements includes:

[0033]

[0034] C is the collision state data, is the first path data, For abnormal collision data, is the health threshold, n is the function quantity, is the sequence number of the collision state data involved in the calculation, if means assumption, Indicates other situations; Indicates that the transport health does not meet the preset health threshold requirements. Indicates that the transport health meets the preset health threshold requirements.

[0035] Furthermore, the health prediction of the cargo health data is performed based on the abnormal collision data to obtain the transport health, including:

[0036] Performing data analysis on the abnormal collision data to obtain the corresponding number of collisions on the road section and the collision intensity on the road section, and performing Pearson correlation coefficient calculation on the cargo health data based on the number of collisions on the road section and the collision intensity on the road section to obtain the corresponding road section correlation coefficient;

[0037] Based on the number of road section collisions and the road section collision intensity and according to the road section correlation coefficient, a health prediction is performed on the cargo health data to obtain the transport health.

[0038] Furthermore, the first scheduling plan and the second scheduling plan are integrated to obtain a comprehensive scheduling plan, the tracking data of the logistics goods is obtained based on the comprehensive scheduling plan, and the comprehensive scheduling plan is optimized in real time according to the tracking data to obtain the optimized comprehensive scheduling plan, including:

[0039] Performing scheduling analysis on the first scheduling scheme and the second scheduling scheme respectively to obtain first scheduling information and second scheduling information, generating a third scheduling scheme based on the first scheduling information and the second scheduling information, optimizing the third scheduling scheme according to the first scheduling scheme and the second scheduling scheme to obtain the comprehensive scheduling scheme, and performing time analysis on the comprehensive scheduling scheme to obtain a comprehensive scheduling time;

[0040] Conducting real-time data tracking on the logistics goods after the implementation of the comprehensive scheduling plan, and obtaining the corresponding tracking data;

[0041] Performing deviation analysis on the tracking data according to the comprehensive scheduling time to obtain the corresponding scheduling deviation time;

[0042] The comprehensive scheduling plan is optimized in real time based on the scheduling deviation time to obtain the optimized comprehensive scheduling plan.

[0043] The present invention also provides a multimodal transport intelligent scheduling and tracking device, which is applied to any of the multimodal transport intelligent scheduling and tracking methods mentioned above, comprising:

[0044] A collection module, which is used to obtain cargo data, cargo environment data and cargo status data of logistics cargo;

[0045] An analysis module, the analysis module is used to perform data analysis on the cargo data to obtain comprehensive transportation data, perform environmental analysis on the cargo environment data to obtain comprehensive environmental data, and perform state analysis on the cargo state data to obtain comprehensive state data;

[0046] A calculation module, the calculation module is used to perform path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generate a first scheduling plan based on the first path data;

[0047] A processing module, the processing module is used to perform an abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generate a second scheduling plan according to the abnormal prediction data;

[0048] A control module, wherein the control module is used to integrate the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, obtain the tracking data of the logistics goods based on the comprehensive scheduling plan, and optimize the comprehensive scheduling plan in real time according to the tracking data to obtain the optimized comprehensive scheduling plan.

[0049] The present invention also provides a multimodal transport intelligent dispatching and tracking device, comprising:

[0050] Memory, used to store programs;

[0051] The processor is used to execute the program to implement each step of a multimodal transport intelligent scheduling and tracking method as described in any one of the above.

[0052] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0053] The present invention provides the following beneficial effects:

[0054] By conducting in-depth data analysis on the cargo data, cargo environment data and cargo status data of logistics goods, more comprehensive and accurate transportation demand information can be obtained. The establishment of comprehensive transportation data, comprehensive environmental data and comprehensive status data can help to more accurately evaluate various factors in the transportation process, such as transportation costs, time requirements, environmental changes, etc., so as to formulate more reasonable transportation routes and scheduling plans, significantly improving the efficiency and accuracy of logistics transportation. Secondly, by real-time monitoring of cargo status and combining historical data for abnormal prediction, potential risks and abnormal situations can be identified in advance during transportation. This data-driven abnormal prediction mechanism can not only help logistics companies take measures to avoid losses in the first place, but also dynamically adjust transportation plans to deal with unforeseen situations, greatly improving the stability and reliability of the logistics system. Finally, through the integration of the first scheduling plan and the second scheduling plan and real-time optimization based on tracking data, this method can realize dynamic management and refined control of the logistics process. This not only ensures the execution quality of the transportation plan, but also ensures that various changes can be responded to in a timely manner throughout the logistics chain, thereby reducing logistics operating costs and improving customer satisfaction and service levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a multimodal transport intelligent scheduling and tracking method provided by the present invention;

[0056] Figure 2 It is a structural diagram of a multimodal transport intelligent dispatching and tracking device provided by the present invention;

[0057] Figure 3 It is a structural diagram of a multimodal transport intelligent dispatching and tracking device provided by the present invention.

[0058] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0060] The present invention is further described below in conjunction with the accompanying drawings and specific implementation methods.

[0061] Reference Figure 1 As shown, the present invention provides a multimodal transport intelligent scheduling and tracking method, comprising:

[0062] Step S1: Obtain cargo data, cargo environment data and cargo status data of logistics cargo;

[0063] Step S2: performing data analysis on the cargo data to obtain comprehensive transportation data, performing environmental analysis on the cargo environment data to obtain comprehensive environmental data, and performing state analysis on the cargo state data to obtain comprehensive state data;

[0064] Step S3: performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling plan based on the first path data;

[0065] Step S4: performing abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data;

[0066] Step S5: Integrate the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, obtain the tracking data of the logistics goods based on the comprehensive scheduling plan, and optimize the comprehensive scheduling plan in real time according to the tracking data to obtain an optimized comprehensive scheduling plan.

[0067] As shown in the above steps, the detailed steps are as follows:

[0068] Step S1: Obtain cargo data, cargo environment data and cargo status data of logistics cargo;

[0069] Among them, cargo data includes: basic information of each batch of cargo, such as cargo type, size, weight, value, etc. The origin and destination information of the cargo. The latest departure time and the latest arrival time of the cargo.

[0070] Cargo environment data includes: temperature monitoring data, humidity monitoring data, light monitoring data, and vibration monitoring data.

[0071] Cargo status data includes: location data; cargo status data, such as whether the cargo is intact, whether it has been hit, etc.; safety inspection data; event data that records any abnormal events during transportation, such as delays, losses, etc.

[0072] Step S2: Analyze information such as cargo type, size, and weight, and match the appropriate mode of transportation (such as sea, air, and land transportation). Estimate the total transportation cost based on factors such as transportation mode, distance, and time. Consider the origin and destination of the cargo, and combine factors such as cost and time window to plan the transportation route. Integrate the transportation mode, total transportation cost, and transportation route to obtain comprehensive transportation data.

[0073] Analyze the temperature change trend during the transportation of goods to obtain temperature data; analyze the humidity change trend to obtain humidity data; analyze the vibration level that the goods may suffer to obtain seismic intensity data. Integrate temperature data, humidity data and seismic intensity data to obtain comprehensive environmental data.

[0074] Perform status analysis on the cargo status data to obtain comprehensive status data.

[0075] Step S3: Combine the comprehensive transport data and the comprehensive environmental data to form a data set containing all relevant factors.

[0076] Based on the information in the comprehensive transportation data and combined with the information conditions in the comprehensive environmental data, one or more feasible routes are selected.

[0077] Analyze the risks of each route, including factors such as weather conditions, traffic congestion, road maintenance, etc.

[0078] Taking into account the costs and benefits, the route with the highest cost performance is selected as the first path data.

[0079] According to the first path data, the transportation mode adopted in different sections is determined, the required transportation tools and human resources are arranged, the timetable of each key node is set, and the first scheduling plan is generated.

[0080] Step S4: Anomaly prediction is performed on the first route data based on the cargo status data to obtain abnormal prediction data. According to the abnormal prediction data, corresponding response strategies are designed, such as changing the route, increasing the monitoring frequency, etc. According to the new strategy, the allocation of transportation tools and human resources is adjusted, the time nodes are replanned, and the second scheduling plan is generated.

[0081] Step S5:

[0082] Compare the first scheduling solution (based on the initial path analysis) with the second scheduling solution (adjustment after considering the abnormal prediction) to identify the differences between the two solutions. Combine the advantages of the two solutions to develop a comprehensive integrated scheduling solution.

[0083] After implementing the comprehensive scheduling plan, continuously monitor the location and status of the goods, as well as changes in the external environment. Once deviations from the plan are found, take immediate action to correct them and activate the emergency plan if necessary. Collect data during the execution process, continuously adjust and optimize the comprehensive scheduling plan, and form a closed loop of continuous improvement.

[0084] The multimodal intelligent scheduling and tracking method provided by the present invention can obtain more comprehensive and accurate transportation demand information by conducting in-depth data analysis on the cargo data, cargo environment data and cargo status data of the logistics cargo. By establishing comprehensive transportation data, comprehensive environmental data and comprehensive status data, it is helpful to more accurately evaluate various factors in the transportation process, such as transportation cost, time requirements, environmental changes, etc., so as to formulate a more reasonable transportation route and scheduling plan, and significantly improve the efficiency and accuracy of logistics transportation. Secondly, by real-time monitoring of the cargo status and combining historical data for abnormal prediction, potential risks and abnormal situations can be identified in advance during the transportation process. This data-driven abnormal prediction mechanism can not only help logistics companies take measures to avoid losses in the first place, but also dynamically adjust the transportation plan to deal with unforeseen situations, greatly improving the stability and reliability of the logistics system. Finally, through the integrated processing of the first scheduling scheme and the second scheduling scheme and the real-time optimization based on tracking data, the method can realize dynamic management and refined control of the logistics process. This not only ensures the execution quality of the transportation plan, but also ensures that various changes can be responded to in a timely manner throughout the logistics chain, thereby reducing logistics operating costs and improving customer satisfaction and service levels.

[0085] In one embodiment, obtaining cargo data, cargo environment data, and cargo status data of logistics cargo includes:

[0086] The original logistics data is collected by the collection equipment deployed on the logistics goods, and the original logistics data is screened according to the preset screening rules to obtain the logistics screening data;

[0087] Classify and sort the logistics screening data to obtain corresponding cargo screening data, environmental screening data and status screening data;

[0088] Check in sequence whether the cargo screening data, environment screening data and status screening data meet the preset data volume threshold requirements. When any of the cargo screening data, environment screening data and status screening data does not meet the data volume threshold requirements, re-acquire the original logistics data for screening and sorting;

[0089] When the cargo screening data, environment screening data and status screening data all meet the data volume threshold requirements, the cargo data, cargo environment data and cargo status data are output.

[0090] This embodiment uses preset screening rules to screen the original logistics data and remove invalid or redundant data, thereby improving the data quality of subsequent processing. Setting the data volume threshold requirement can ensure that the amount of data collected is sufficient to support further analysis needs and avoid inaccurate analysis results due to insufficient data volume. Although reacquiring data when the data volume does not meet the threshold requirement increases the process of acquiring data, it also avoids invalid analysis due to insufficient data volume, thereby reducing the waste of computing resources and manpower.

[0091] In one embodiment, data analysis is performed on cargo data to obtain comprehensive transportation data, environmental analysis is performed on cargo environmental data to obtain comprehensive environmental data, and status analysis is performed on cargo status data to obtain comprehensive status data, including:

[0092] Key information is extracted from cargo data to obtain basic attributes (such as cargo type, size, weight, packaging method), transportation requirements (such as temperature control, humidity control, safety requirements) and transportation goals (final destination of cargo, expected arrival time). The basic attributes, transportation requirements and transportation goals are comprehensively analyzed and processed to obtain comprehensive transportation data.

[0093] Environmental information is extracted from the cargo environmental data to obtain environmental data (such as temperature, humidity, and light) and real-time location data. Based on the real-time location data, type analysis is performed on the environmental data to obtain the internal environmental data and external meteorological data of the means of transport. The real-time location data, internal environmental data, and external meteorological data are integrated to obtain comprehensive environmental data.

[0094] The cargo status data is subjected to status information extraction to obtain collision status data (such as the number of collisions and the intensity of collisions) and cargo health data (such as temperature changes, humidity changes, and whether the cargo is damaged). The collision status data and cargo health data are comprehensively analyzed and processed to obtain comprehensive status data.

[0095] This embodiment can more accurately plan transportation plans and improve transportation efficiency by extracting the basic properties, transportation requirements and transportation targets of the goods and performing comprehensive analysis and processing. By real-time monitoring of environmental data, it is possible to ensure that the goods are transported in a suitable environment and improve transportation conditions. By analyzing the internal environmental data of the transportation vehicle and the external meteorological data, it is possible to prevent damage to the goods due to environmental factors. By real-time monitoring of the goods status data, it is possible to promptly detect abnormal conditions of the goods during transportation. By analyzing the collision status data and the goods health data, it is possible to prevent the loss of goods due to collisions or environmental factors.

[0096] In one embodiment, performing path analysis based on the integrated transportation data and the integrated environmental data to obtain first path data, and generating a first scheduling solution based on the first path data includes:

[0097] The comprehensive transportation data and comprehensive environmental data are read to obtain basic attributes, transportation requirements, transportation targets, real-time location data, internal environmental data and external meteorological data.

[0098] Based on the transportation target and real-time location data, a path planning algorithm (such as Dijkstra algorithm, A* algorithm, etc.) is used to determine the optimal path to obtain the first path data.

[0099] The first path data is time-predicted according to external meteorological data to obtain a first transportation time.

[0100] The time is calculated according to the transportation requirements, basic attributes and internal environment data to obtain the transportation limit time, and the corresponding historical limit plan is obtained based on the transportation limit time.

[0101] The first transportation time is analyzed according to the transportation limit time to obtain a first deviation time, and it is determined whether the first deviation time meets the preset time requirement. When the first deviation time meets the preset time requirement, the first path data is converted to obtain a first scheduling plan.

[0102] When the first deviation time does not meet the preset time requirement, the first path data is regenerated based on the transportation target and the real-time location data with reference to the historical limited plan, and the first path data is converted into a plan to obtain a first scheduling plan.

[0103] This embodiment uses real-time location data and transportation targets to perform path analysis, and can select the optimal path to reduce transportation time and cost. Using external meteorological data for time prediction can more accurately estimate the arrival time and reduce time delays caused by unforeseen factors. Considering transportation requirements and internal environmental data, ensure that specific conditions (such as temperature control) are met during transportation to ensure the safety and integrity of the goods. When the actual transportation time does not meet expectations, the plan can be quickly adjusted by referring to historical data, which improves the flexibility and adaptability of the system. By optimizing the path and accurately predicting the time, unnecessary waiting and resource waste can be reduced, thereby reducing the overall operating cost.

[0104] In one embodiment, an abnormal prediction is performed on the first path data according to the cargo status data to obtain abnormal prediction data, and a second scheduling plan is generated according to the abnormal prediction data, including:

[0105] Read the cargo status data to obtain collision status data and cargo health data;

[0106] Based on the collision state data, risk prediction is performed on the first path data to obtain abnormal collision data, wherein the risk prediction process includes performing collision analysis on the collision state data to obtain corresponding historical collision times and historical collision intensities.

[0107] The first path data (i.e., the original transportation route) is predicted to obtain the corresponding path conditions (such as traffic congestion, road construction, etc.), and the historical collision times and historical collision intensities are mapped to the path conditions to perform section prediction to obtain the corresponding section collision times and section collision intensities.

[0108] The number of road section collisions and the road section collision intensity are integrated and processed to obtain the comprehensive data of each road section. The comprehensive data of the road section is tested according to the preset road section threshold, and the comprehensive data of the road section exceeding the road section threshold is marked as abnormal data. All abnormal data are integrated to obtain abnormal collision data.

[0109] The health of the cargo is predicted based on the abnormal collision data to obtain the transport health.

[0110] Determine whether the transport health meets the preset health threshold requirements. When the transport health does not meet the preset health threshold requirements, analyze the abnormal collision data, identify which sections cause the health of the goods to decline, re-plan the second path data, avoid the sections that cause the health to decline, and generate a second scheduling plan, including a new transport route and transport time adjustment.

[0111] Among them, the judgment formula for judging whether the transport health meets the preset health threshold requirements includes:

[0112]

[0113] C is the collision status data, is the first path data, is abnormal collision data, is the health threshold, n is the function quantity, is the sequence number of the collision state data involved in the calculation, if means assumption, Indicates other situations; Indicates that the transport health does not meet the preset health threshold requirements. Indicates that the transport health meets the preset health threshold requirements.

[0114] This embodiment can promptly detect the risk of collision that may occur during transportation through real-time monitoring and analysis of cargo status data, so as to take preventive measures and reduce the probability of cargo damage. Through risk prediction based on collision status data, high-risk sections can be identified in advance, and the transportation route can be adjusted accordingly, and a safer alternative route can be selected to avoid potential problems. Guarantee the quality of goods: Health prediction ensures that the goods remain in good condition throughout the transportation process, which is especially important for perishable or sensitive goods. By avoiding unnecessary collisions and losses, additional costs caused by cargo damage, such as insurance claims, re-shipment and other expenses, are reduced. Regular inspections and ensuring that the health of the goods meets the predetermined standards will help improve customer trust and satisfaction with the service and maintain the company's brand image.

[0115] In one embodiment, health prediction is performed on the cargo health data according to the abnormal collision data to obtain the transport health, including:

[0116] Data analysis is performed on the abnormal collision data to obtain the corresponding number of road section collisions and the road section collision intensity, and the Pearson correlation coefficient of the cargo health data is calculated based on the number of road section collisions and the road section collision intensity, including calculating the number Pearson correlation coefficient between the number of road section collisions and the cargo health data, calculating the intensity Pearson correlation coefficient between the road section collision intensity and the cargo health data, and integrating the number Pearson correlation coefficient and the intensity Pearson correlation coefficient to obtain the road section correlation coefficient.

[0117] Based on domain knowledge and actual needs, a series of rules are predefined to describe the relationship between the number of road section collisions, the intensity of road section collisions and the health of cargo.

[0118] For example, if the number of collisions on a road segment exceeds a certain threshold, the road segment is considered to have a negative impact on the cargo health.

[0119] According to the defined rules, the impact of each road segment on the health of the cargo is evaluated.

[0120] For example, if the number of collisions on a road segment is above a threshold and the Pearson correlation coefficient shows a strong negative correlation, the road segment is considered likely to cause a decrease in cargo health.

[0121] Based on the number of road section collisions, road section collision intensity and road section correlation coefficient, combined with the defined rules, health prediction is performed to obtain the health prediction results of each road section.

[0122] For example, if a road segment has a high number of collisions and the correlation coefficient shows a strong negative correlation, it is predicted that the road segment may result in a decrease in cargo health.

[0123] According to the prediction results of each section, an overall health index is calculated, for example, by a weighted average algorithm. Finally, the transportation health of the entire transportation process is calculated.

[0124] This embodiment can improve the accuracy of predictions by defining clear rules to describe the relationship between the number of road section collisions, the intensity of road section collisions and the health of goods, because these rules are based on domain knowledge and experience. There is no need to build complex prediction models, which simplifies the prediction process and makes the prediction results more intuitive and easy to understand. The rule-oriented method can make predictions based on new data more quickly, which helps logistics companies to respond quickly and take measures when encountering emergencies. The rules can be adjusted according to the actual results, and the prediction results can be gradually optimized to ensure that the prediction method is continuously improved as the logistics environment changes.

[0125] In one embodiment, the first scheduling plan and the second scheduling plan are integrated to obtain a comprehensive scheduling plan, tracking data of logistics goods is obtained based on the comprehensive scheduling plan, and the comprehensive scheduling plan is optimized in real time according to the tracking data to obtain an optimized comprehensive scheduling plan, including:

[0126] Performing scheduling analysis on the first scheduling scheme and the second scheduling scheme respectively to obtain first scheduling information and second scheduling information, generating a third scheduling scheme based on the first scheduling information and the second scheduling information, optimizing the third scheduling scheme according to the first scheduling scheme and the second scheduling scheme to obtain a comprehensive scheduling scheme, and performing time analysis on the comprehensive scheduling scheme to obtain a comprehensive scheduling time;

[0127] Carry out real-time data tracking of logistics goods after the implementation of the comprehensive scheduling plan, and obtain the corresponding tracking data;

[0128] Perform deviation analysis on tracking data based on comprehensive dispatch time to obtain corresponding dispatch deviation time;

[0129] The comprehensive scheduling plan is optimized in real time based on the scheduling deviation time to obtain an optimized comprehensive scheduling plan.

[0130] This embodiment can allocate resources more effectively and reduce unnecessary waiting time and transportation costs by integrating and optimizing multiple scheduling schemes, thereby improving the overall scheduling efficiency. The real-time optimization mechanism can quickly respond to changes in the external environment, such as changes in traffic conditions, fluctuations in order demand, etc., enhancing the adaptability and flexibility of the system. Accurate tracking data and timely scheduling adjustments can ensure that goods are delivered on time, reduce delays, and thus improve customer satisfaction. Through comprehensive consideration and optimization of different scheduling schemes, duplication of work and ineffective transportation can be avoided, effectively reducing costs. The comprehensive scheduling scheme can better coordinate various resources, such as vehicles, personnel, and warehouse space, to ensure the effective use of resources.

[0131] Reference Figure 2 As shown, the present invention also provides a multimodal transport intelligent scheduling and tracking device, which is applied to any of the above multimodal transport intelligent scheduling and tracking methods, including:

[0132] A collection module, which is used to obtain cargo data, cargo environment data and cargo status data of logistics cargo;

[0133] The analysis module is used to perform data analysis on the cargo data to obtain comprehensive transportation data, perform environmental analysis on the cargo environment data to obtain comprehensive environmental data, and perform status analysis on the cargo status data to obtain comprehensive status data;

[0134] A calculation module, the calculation module is used to perform path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generate a first scheduling plan based on the first path data;

[0135] A processing module, the processing module is used to perform an abnormal prediction on the first path data according to the cargo status data, obtain abnormal prediction data, and generate a second scheduling plan according to the abnormal prediction data;

[0136] The control module is used to integrate the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, obtain the tracking data of the logistics goods based on the comprehensive scheduling plan, and optimize the comprehensive scheduling plan in real time according to the tracking data to obtain an optimized comprehensive scheduling plan.

[0137] The multimodal intelligent scheduling and tracking device provided by the present invention can obtain more comprehensive and accurate transportation demand information by conducting in-depth data analysis on the cargo data, cargo environment data and cargo status data of the logistics cargo. By establishing comprehensive transportation data, comprehensive environmental data and comprehensive status data, it is helpful to more accurately evaluate various factors in the transportation process, such as transportation cost, time requirements, environmental changes, etc., so as to formulate a more reasonable transportation route and scheduling plan, and significantly improve the efficiency and accuracy of logistics transportation. Secondly, by real-time monitoring of the cargo status and combining historical data for abnormal prediction, potential risks and abnormal situations can be identified in advance during the transportation process. This data-driven abnormal prediction mechanism can not only help logistics companies take measures to avoid losses in the first place, but also dynamically adjust the transportation plan to deal with unforeseen situations, greatly improving the stability and reliability of the logistics system. Finally, through the integrated processing of the first scheduling scheme and the second scheduling scheme and the real-time optimization based on tracking data, the method can realize dynamic management and refined control of the logistics process. This not only ensures the execution quality of the transportation plan, but also ensures that various changes can be responded to in a timely manner throughout the logistics chain, thereby reducing logistics operating costs and improving customer satisfaction and service levels.

[0138] Reference Figure 3 As shown, the present invention also provides a multimodal transport intelligent scheduling and tracking device, comprising:

[0139] Memory, used to store programs;

[0140] The processor is used to execute the program to implement each step of any one of the multimodal transport intelligent scheduling and tracking methods described above.

[0141] In this embodiment, the processor and the memory may be connected via a bus or other means. The memory may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a read-only memory, a flash memory, a hard disk, or a solid-state drive. The processor may be a general-purpose processor, such as a central processing unit, a digital signal processor, an application-specific integrated circuit, or one or more integrated circuits configured to implement the embodiments of the present invention.

[0142] The present invention also provides a storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute any of the above methods.

[0143] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and conciseness of description, the specific working process of the system and each module described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0144] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A multimodal transport intelligent scheduling and tracking method, It is characterized in that include: Obtain cargo data, cargo environment data and cargo status data of logistics cargo; Performing data analysis on the cargo data to obtain comprehensive transportation data, performing environmental analysis on the cargo environment data to obtain comprehensive environmental data, and performing status analysis on the cargo status data to obtain comprehensive status data; Performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling plan based on the first path data; Performing an abnormal prediction on the first route data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data; Integrate the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, obtain tracking data of the logistics goods based on the comprehensive scheduling plan, and optimize the comprehensive scheduling plan in real time according to the tracking data to obtain an optimized comprehensive scheduling plan; The performing of data analysis on the cargo data to obtain comprehensive transportation data, performing of environmental analysis on the cargo environment data to obtain comprehensive environmental data, and performing of state analysis on the cargo state data to obtain comprehensive state data include: Extract key information from the cargo data to obtain basic attributes, transportation requirements and transportation targets, and comprehensively analyze and process the basic attributes, transportation requirements and transportation targets to obtain the comprehensive transportation data; Extracting environmental information from the cargo environmental data to obtain environmental data and real-time location data, performing type analysis on the environmental data based on the real-time location data to obtain internal environmental data and external meteorological data of the transportation vehicle, and integrating the real-time location data, the internal environmental data and the external meteorological data to obtain the comprehensive environmental data; Extracting status information from the cargo status data to obtain collision status data and cargo health data, and comprehensively analyzing and processing the collision status data and cargo health data to obtain the comprehensive status data; The performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling scheme based on the first path data, includes: Reading the comprehensive transportation data and the comprehensive environmental data to obtain the basic attributes, the transportation requirements, the transportation target, the real-time location data, the internal environmental data and the external meteorological data; Performing a path analysis based on the transportation target and the real-time location data to obtain first path data, and performing a time prediction on the first path data based on the external meteorological data to obtain a first transportation time; Performing time calculation according to the transportation requirements, the basic attributes and the internal environment data to obtain a transportation limit time, and acquiring a corresponding historical limit plan based on the transportation limit time; Performing a time analysis on the first transportation time according to the transportation limit time to obtain a first deviation time, determining whether the first deviation time meets a preset time requirement, and when the first deviation time meets the preset time requirement, performing a scheme conversion on the first path data to obtain the first scheduling scheme; When the first deviation time does not meet the preset time requirement, regenerate the first path data based on the transportation target and the real-time location data with reference to the historical limited plan, and perform plan conversion on the first path data to obtain the first scheduling plan; The step of performing an abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data includes: Reading the cargo status data to obtain the collision status data and the cargo health data; Based on the collision state data, risk prediction is performed on the first path data to obtain abnormal collision data, wherein the risk prediction process includes performing collision analysis on the collision state data to obtain corresponding historical collision times and historical collision intensities; Performing path prediction on the first path data to obtain corresponding path conditions, mapping the historical collision times and historical collision intensities to the path conditions to perform road segment prediction to obtain corresponding road segment collision times and road segment collision intensities, and integrating the road segment collision times and road segment collision intensities; Obtaining comprehensive data of the road section, detecting the comprehensive data of the road section according to a preset road section threshold, marking the comprehensive data of the road section exceeding the road section threshold as abnormal data, integrating all the abnormal data, and obtaining abnormal collision data; Performing health prediction on the cargo health data according to the abnormal collision data to obtain transportation health; Determine whether the transport health meets the preset health threshold requirement, and when the transport health does not meet the preset health threshold requirement, generate the second scheduling plan according to the first path data based on the abnormal collision data and the transport health; Among them, the judgment formula for judging whether the transport health meets the preset health threshold requirements includes: ， C is the collision state data, is the first path data, For abnormal collision data, is the health threshold, n is the function quantity, is the sequence number of the collision state data involved in the calculation, if means assumption, Indicates other situations; Indicates that the transport health does not meet the preset health threshold requirements. Indicates that the transport health meets the preset health threshold requirements.

2. The multimodal transport intelligent scheduling and tracking method according to claim 1, It is characterized in that The obtaining of cargo data, cargo environment data and cargo status data of logistics cargo includes: The original logistics data is collected by a collection device deployed on the logistics goods, and the original logistics data is screened according to a preset screening rule to obtain logistics screening data; Classify and sort the logistics screening data to obtain corresponding cargo screening data, environmental screening data and status screening data; Check in sequence whether the cargo screening data, environment screening data and status screening data meet the preset data volume threshold requirements. When any of the cargo screening data, environment screening data and status screening data does not meet the data volume threshold requirements, re-acquire the original logistics data for screening and sorting; When the cargo screening data, the environment screening data and the status screening data all meet the data volume threshold requirements, the cargo data, the cargo environment data and the cargo status data are output.

3. The multimodal transport intelligent scheduling and tracking method according to claim 1, It is characterized in that The health prediction of the cargo health data based on the abnormal collision data to obtain the transport health includes: Performing data analysis on the abnormal collision data to obtain the corresponding number of collisions on the road section and the collision intensity on the road section, and performing Pearson correlation coefficient calculation on the cargo health data based on the number of collisions on the road section and the collision intensity on the road section to obtain the corresponding road section correlation coefficient; Based on the number of road section collisions and the road section collision intensity and according to the road section correlation coefficient, a health prediction is performed on the cargo health data to obtain the transport health.

4. The multimodal transport intelligent scheduling and tracking method according to claim 1, It is characterized in that The first scheduling plan and the second scheduling plan are integrated to obtain a comprehensive scheduling plan, tracking data of the logistics goods are obtained based on the comprehensive scheduling plan, and the comprehensive scheduling plan is optimized in real time according to the tracking data to obtain the optimized comprehensive scheduling plan, including: Performing scheduling analysis on the first scheduling scheme and the second scheduling scheme respectively to obtain first scheduling information and second scheduling information, generating a third scheduling scheme based on the first scheduling information and the second scheduling information, optimizing the third scheduling scheme according to the first scheduling scheme and the second scheduling scheme to obtain the comprehensive scheduling scheme, and performing time analysis on the comprehensive scheduling scheme to obtain a comprehensive scheduling time; Conducting real-time data tracking on the logistics goods after the implementation of the comprehensive scheduling plan, and obtaining the corresponding tracking data; Performing deviation analysis on the tracking data according to the comprehensive scheduling time to obtain the corresponding scheduling deviation time; The comprehensive scheduling plan is optimized in real time based on the scheduling deviation time to obtain the optimized comprehensive scheduling plan.

5. An intelligent multimodal transport dispatching and tracking device, applied to any one of the multimodal transport intelligent dispatching and tracking methods of claims 1-4 above, It is characterized in that include: A collection module, which is used to obtain cargo data, cargo environment data and cargo status data of logistics cargo; An analysis module, the analysis module is used to perform data analysis on the cargo data to obtain comprehensive transportation data, perform environmental analysis on the cargo environment data to obtain comprehensive environmental data, and perform state analysis on the cargo state data to obtain comprehensive state data; A calculation module, the calculation module is used to perform path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generate a first scheduling plan based on the first path data; A processing module, the processing module is used to perform an abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generate a second scheduling plan according to the abnormal prediction data; A control module, the control module is used to integrate the first scheduling plan and the second scheduling plan to obtain a comprehensive scheduling plan, obtain the tracking data of the logistics goods based on the comprehensive scheduling plan, and optimize the comprehensive scheduling plan in real time according to the tracking data to obtain the optimized comprehensive scheduling plan; The performing of data analysis on the cargo data to obtain comprehensive transportation data, performing of environmental analysis on the cargo environment data to obtain comprehensive environmental data, and performing of state analysis on the cargo state data to obtain comprehensive state data include: Extract key information from the cargo data to obtain basic attributes, transportation requirements and transportation targets, and comprehensively analyze and process the basic attributes, transportation requirements and transportation targets to obtain the comprehensive transportation data; Extracting environmental information from the cargo environmental data to obtain environmental data and real-time location data, performing type analysis on the environmental data based on the real-time location data to obtain internal environmental data and external meteorological data of the transportation vehicle, and integrating the real-time location data, the internal environmental data and the external meteorological data to obtain the comprehensive environmental data; Extracting status information from the cargo status data to obtain collision status data and cargo health data, and comprehensively analyzing and processing the collision status data and cargo health data to obtain the comprehensive status data; The performing path analysis based on the comprehensive transportation data and the comprehensive environmental data to obtain first path data, and generating a first scheduling scheme based on the first path data, includes: Reading the comprehensive transportation data and the comprehensive environmental data to obtain the basic attributes, the transportation requirements, the transportation target, the real-time location data, the internal environmental data and the external meteorological data; Performing a path analysis based on the transportation target and the real-time location data to obtain first path data, and performing a time prediction on the first path data based on the external meteorological data to obtain a first transportation time; Performing time calculation according to the transportation requirements, the basic attributes and the internal environment data to obtain a transportation limit time, and acquiring a corresponding historical limit plan based on the transportation limit time; Performing a time analysis on the first transportation time according to the transportation limit time to obtain a first deviation time, determining whether the first deviation time meets a preset time requirement, and when the first deviation time meets the preset time requirement, performing a scheme conversion on the first path data to obtain the first scheduling scheme; When the first deviation time does not meet the preset time requirement, regenerate the first path data based on the transportation target and the real-time location data with reference to the historical limited plan, and perform plan conversion on the first path data to obtain the first scheduling plan; The step of performing an abnormal prediction on the first path data according to the cargo status data to obtain abnormal prediction data, and generating a second scheduling plan according to the abnormal prediction data includes: Reading the cargo status data to obtain the collision status data and the cargo health data; Based on the collision state data, risk prediction is performed on the first path data to obtain abnormal collision data, wherein the risk prediction process includes performing collision analysis on the collision state data to obtain corresponding historical collision times and historical collision intensities; Performing path prediction on the first path data to obtain corresponding path conditions, mapping the historical collision times and historical collision intensities to the path conditions to perform road segment prediction to obtain corresponding road segment collision times and road segment collision intensities, and integrating the road segment collision times and road segment collision intensities; Obtaining comprehensive data of the road section, detecting the comprehensive data of the road section according to a preset road section threshold, marking the comprehensive data of the road section exceeding the road section threshold as abnormal data, integrating all the abnormal data, and obtaining abnormal collision data; Performing health prediction on the cargo health data according to the abnormal collision data to obtain transportation health; Determine whether the transport health meets the preset health threshold requirement, and when the transport health does not meet the preset health threshold requirement, generate the second scheduling plan according to the first path data based on the abnormal collision data and the transport health; Among them, the judgment formula for judging whether the transport health meets the preset health threshold requirements includes: ， C is the collision state data, is the first path data, For abnormal collision data, is the health threshold, n is the function quantity, is the sequence number of the collision state data involved in the calculation, if means assumption, Indicates other situations; Indicates that the transport health does not meet the preset health threshold requirements. Indicates that the transport health meets the preset health threshold requirements.

6. An intelligent multimodal transport dispatching and tracking device, It is characterized in that include: Memory, used to store programs; A processor is used to execute the program to implement each step of a multimodal transport intelligent scheduling and tracking method as described in any one of claims 1 to 4.

7. A storage medium, It is characterized in that Computer instructions are stored, and the computer instructions are used to make a computer execute the method according to any one of claims 1 to 4.

Images