A parcel logistics multimodal transport collaborative scheduling method based on big data

Abstract

This invention discloses a big data-based multimodal transport collaborative scheduling method for parcel logistics, relating to the field of big data technology. It includes triggering dynamic corrections of transportation efficiency coefficients, cost fluctuation coefficients, and service risk coefficients when an information monitoring terminal detects an anomaly. When the absolute value of the difference between the updated evaluation index and the original evaluation index exceeds a preset threshold, the scheduling decision terminal re-executes the plan generation process to generate an emergency plan. This invention uses a built-in evaluation model to dynamically allocate weights based on customer-selected scheduling modes such as cost priority, time priority, and safety priority, outputting evaluation indices. It combines this with a genetic algorithm to generate transport mode combinations and performs time-coordination and equipment matching verification, achieving multi-objective collaborative optimization. This method can flexibly adapt to different customer needs, achieving a balance between transportation efficiency, cost, and safety, and improving the efficiency of multimodal transport resource allocation.

Description

Technical Field

[0001] This invention relates to the field of big data technology, and in particular to a collaborative scheduling method for multimodal transport of parcels based on big data. Background Technology

[0002] With the rapid development of global economic integration and e-commerce, the logistics industry is facing unprecedented opportunities and challenges. Consumers' demands for logistics services are becoming increasingly diversified, expanding from traditional timeliness and security to multi-dimensional requirements such as cost transparency and green, low-carbon practices. At the same time, the complexity of supply chains and the breadth of logistics networks continue to expand. Parcel transportation involves multiple stages, including collection, sorting, transportation, warehousing, and distribution, urgently requiring efficient resource integration through multimodal transport such as rail, road, air, and water transport. However, the collaborative scheduling of multimodal transport involves the real-time processing of massive amounts of heterogeneous data, dynamic resource allocation, and multi-objective optimization, which traditional logistics management models can no longer meet. Against this backdrop, the application of technologies such as big data and artificial intelligence has become a key driving force for the intelligent upgrading of the logistics industry. How to utilize these technologies to achieve efficient collaborative scheduling of multimodal transport has become a focus of industry attention.

[0003] Currently, the logistics sector has made some progress in multimodal transport scheduling. For example, some companies use GPS positioning and IoT technology to achieve real-time monitoring of transport vehicles or optimize route planning using historical data analysis. Academic research has also proposed various scheduling models, such as static resource allocation methods based on linear programming and time window optimization strategies using heuristic algorithms. However, existing technologies still have significant limitations. First, data collection and analysis capabilities are insufficient; most systems rely on data from a single source (such as vehicle status) and lack comprehensive collection and fusion of data from the entire supply chain, including package characteristics, environmental parameters, and equipment compatibility. Second, existing scheduling models are mostly static or semi-dynamic, unable to respond in real-time to emergencies such as traffic congestion and sudden weather changes, leading to significant fluctuations in transport efficiency. Furthermore, the dynamic trade-off mechanism for multiple objectives such as cost, timeliness, and risk during resource allocation is imperfect, often relying on fixed weights and failing to meet personalized customer needs. For example, while some studies have proposed genetic algorithms that can generate transport combination schemes, they do not incorporate carbon emission constraints and lack refined design for verifying equipment matching and time coordination.

[0004] However, existing technologies still face many pressing problems: First, low transportation efficiency and resource utilization. Due to the isolated data of various modes of transport in multimodal transport and the lack of real-time coordination mechanisms, low vehicle loading rates, poor transshipment connections, and widespread resource waste occur. For example, road transport dominates short-distance delivery, but the cost advantages of rail or water transport on long-distance trunk lines are not fully utilized. Second, insufficient dynamic balance between cost control and risk management. There is a lack of quantitative models for the impact of fuel price fluctuations, package damage rates, and environmental factors such as temperature and humidity on transportation costs and service risks. Existing methods mostly rely on empirical values ​​or fixed coefficients, making accurate prediction and dynamic adjustment difficult. Third, weak anomaly response capabilities. When encountering traffic congestion, equipment failure, or sudden weather changes, traditional systems often rely on manual intervention, resulting in delayed responses and low efficiency in generating emergency plans, easily leading to customer defaults or cargo losses. Fourth, green logistics requirements have not been effectively incorporated into the decision-making system. Although low-carbon transportation has become an industry trend, existing scheduling models rarely use carbon emissions as a hard constraint, resulting in insufficient environmental friendliness of the solutions.

[0005] Therefore, it is essential to invent a big data-based multimodal transport collaborative scheduling method for parcel logistics to solve the above problems. Summary of the Invention

[0006] The purpose of this invention is to provide a big data-based multimodal transport collaborative scheduling method for parcel logistics to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution: a big data-based multimodal transport collaborative scheduling method for parcel logistics, comprising a parcel data acquisition terminal, an environmental data acquisition terminal, a loading equipment data acquisition terminal, a scheduling decision terminal, an information monitoring terminal, a logistics terminal, and a multimodal transport resource pool, comprising the following steps:

[0008] S1. The parcel data collection terminal, environmental data collection terminal, and loading equipment data collection terminal collect data from the entire chain of parcels from receipt, sorting, transportation, warehousing to delivery, to obtain parcel datasets, environmental datasets, and loading equipment datasets.

[0009] S2. The logistics terminal processes and analyzes the parcel dataset, environmental dataset, and loading equipment dataset to obtain the transportation efficiency coefficient, cost fluctuation coefficient, and service risk coefficient.

[0010] S3, the logistics terminal imports the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient into the built-in evaluation model, dynamically allocates the weight of the evaluation model according to the scheduling mode selected by the customer, and outputs the evaluation index.

[0011] S4. The scheduling decision terminal calls the multimodal transport resource pool to obtain real-time available resources for railway, highway, aviation and water transport. It generates all possible combinations of transport modes through a genetic algorithm, calculates the evaluation index of each combination and sorts them in descending order, then selects the top five as candidate schemes, and then performs time connection verification and equipment matching verification. Finally, it selects the scheme with the highest evaluation index and carbon emissions lower than the industry average from the feasible candidate schemes.

[0012] S5. When the information monitoring terminal detects an abnormal situation, it triggers dynamic correction of the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient. When the absolute value of the difference between the updated evaluation index and the original evaluation index exceeds the preset threshold, the dispatch decision terminal re-executes the plan generation process to generate an emergency plan.

[0013] Preferably, the package dataset includes: package weight, package volume, actual package density, package required equipment code, package status, customer-specified time window start point, time window length, historical lowest transportation cost for similar packages, package damage rate, complaint rate, historical on-time delivery rate, and historical cargo integrity rate; the environment dataset includes: weather status, weather level, environmental parameter safety thresholds, origin congestion coefficient, destination congestion coefficient, high-risk congested road segment collection, road segment identifiers in the transportation route, and environmental parameters, including: ambient temperature, ambient humidity, and ambient wind force; the loading equipment dataset includes: available equipment type code, maximum value of equipment type code, maximum load capacity of logistics nodes, maximum allowable density of transportation vehicles, optimal loading volume of transportation vehicles, maximum volume of logistics nodes, equipment failure status, and historical average delay time.

[0014] Preferably, the transportation efficiency coefficient is specifically:

[0015] ,

[0016] in, The transportation mode adaptability coefficient is as follows: Where k is the mode of transport, Type(k) is the binary identifier of the mode of transport, and λ k These are the basic efficiency parameters for each mode of transportation; The weather impact coefficient is as follows: Where t represents the weather state, Weather(t) represents the weather level, and μ t The weather influence is weighted; ε is the equipment compatibility coefficient, specifically... Where E is the available device type code, E req For the package requirement equipment coding, E max The maximum value for device type encoding; η is the global scaling factor, specifically... , where e is the natural constant and Z is the evaluation index; Where ω1, ω2, ω3, and ω4 are weighting coefficients, ω1, ω2, ω3, and ω4 ∈ [0, 1], and ω1 + ω2 + ω + ω4 = 1; f1 is the weight utilization factor, specifically:

[0017] ,

[0018] Where D is the actual density of the package, specifically... W0 is the package weight, V0 is the package volume, and W max D is the maximum load-bearing capacity of the logistics node. lim f1 is the maximum allowable density for transportation vehicles; f2 is the volume utilization factor, specifically:

[0019] ,

[0020] Among them, V opt V is the optimal loading volume of the transport vehicle. max Let f be the maximum volume of the logistics node, e be the natural constant, and f3 be the time efficiency factor, specifically:

[0021] ,

[0022] Among them, T min The shortest time required to complete the transportation task under ideal transportation conditions, where △T is the historical average delay time, and T is the shortest time required to complete the transportation task. w Specify the start point of the time window for the customer, T win T is the length of the time window. p T is the actual transportation time predicted based on historical data. s f4 represents the actual start time of transportation; f4 is the congestion impact factor, specifically:

[0023] ,

[0024] Among them, F avg The overall congestion coefficient is as follows: , of which F s F represents the congestion coefficient at the origin. d R represents the destination congestion coefficient; m represents the total number of road segments in the transportation route. j Let I(R) be the identifier of the j-th road segment in the transportation route, Ω be the set of high-risk congestion road segments, and I(R) be the identifier of the j-th road segment in the transportation route. j ∈Ω) is an indicator function, specifically , is used to determine whether the j-th road segment belongs to the set of high-risk congested road segments Ω.

[0025] Preferably, the cost fluctuation coefficient is specifically:

[0026] ,

[0027] Where n is the number of possible combinations of transportation modes, c i Let be the unit weight cost of the i-th mode of transportation. Let p be the estimated transport distance for the i-th mode of transport. i Let be the damage rate of the package for the i-th transportation method. The lowest transportation cost for similar packages in history is represented by θ, where θ is the fuel price fluctuation coefficient.

[0028] Preferably, the service risk coefficient is as follows:

[0029] ,

[0030] Among them, O tr For historical on-time delivery rate, I cr For the historical package integrity rate, η time The time sensitivity coefficient is, specifically... , among which, T remain For the remaining transportation time, T plan For planned transportation time; η env This is the environmental risk buffer coefficient, specifically... X i Let X be the actual data for the i-th environment. i，max The safety thresholds for each environmental parameter; Q sec For safety compliance scoring, Q cus The customer complaint rate is scored, specifically as follows: Where, complaint rate = number of complaints ÷ number of orders, with the number of orders in tens of thousands; m is the number of modes in the transportation mode combination, R risk，k Let be the specific risk index of the k-th mode of transportation, n be the total number of environmental parameters, and δ1, δ2, δ3 and δ4 be weighting coefficients, where δ1, δ2, δ3 and δ4 ∈ [0, 1] and δ1 + δ2 + δ3 + δ4 = 1.

[0031] Preferably, the evaluation model is as follows:

[0032] ,

[0033] Where k1 is the timeliness weight coefficient, k2 is the cost weight coefficient, k3 is the safety weight coefficient, k1, k2 and k3 ∈ [0, 1], and k1+k2+k3=1, K is the transportation efficiency coefficient, C is the cost fluctuation coefficient, and S is the service risk coefficient.

[0034] Preferably, the scheduling modes are divided into cost-priority mode, time-priority mode, and safety-priority mode; the cost-priority mode sets the cost weight coefficient to the highest; the time-priority mode sets the time-priority weight coefficient to the highest; and the safety-priority mode sets the safety weight coefficient to the highest.

[0035] Preferably, the time connection verification specifically involves verifying the rationality of the time connection between various transportation modes in the candidate schemes, and predicting the actual transportation time T based on historical data. p and the actual start time of transportation T s Determine T s +T p Is it within the customer-specified time window start point T? w With T w +T win Within the range, while considering the shortest time T under ideal transportation conditions min The time efficiency factor f3 is verified to meet the preset timeliness threshold by comparing the historical average delay time ΔT with the time efficiency factor f3. Specifically, the equipment matching verification verifies the compatibility between the loading equipment and the package in the candidate solutions, comparing the available equipment type code E with the package requirement equipment code E. req Ensure E≥E req And E≤E max Simultaneously verify the maximum load-bearing capacity W of the logistics node. max Is the package weight W0 greater than or equal to the maximum allowable density D of the transport vehicle? lim Whether it is greater than or equal to the actual density D of the package, and whether the volume utilization factor f2 meets the preset volume utilization threshold.

[0036] Preferably, the dynamic correction is as follows:

[0037] A1. During traffic congestion, the overall congestion coefficient F in the transportation efficiency coefficient K and service risk coefficient S. avg and indicator function I(R) j The value of (∈Ω) is corrected;

[0038] A2. When weather changes abruptly, the impact of weather on the transportation efficiency coefficient K and the service risk coefficient S, as well as the environmental risk buffer coefficient η, is affected. env The value is corrected;

[0039] A3. In the event of equipment failure, the equipment compatibility coefficient ε and safety compliance score Q in the transportation efficiency coefficient K and service risk coefficient S are considered. sec The value is corrected;

[0040] A4. When a package is in an abnormal state, the weight utilization factor f1, volume utilization factor f2, and package damage rate p for the i-th transportation mode are considered in the transportation efficiency coefficient K, cost fluctuation coefficient C, and service risk coefficient S.i The value is corrected.

[0041] The technical effects and advantages of this invention are as follows:

[0042] This invention collects data from the entire parcel chain, from collection to delivery, through parcel data collection terminals, environmental data collection terminals, and loading equipment data collection terminals. This data forms parcel datasets, environmental datasets, and loading equipment datasets. The data is then processed and analyzed by logistics terminals to obtain transportation efficiency coefficients, cost fluctuation coefficients, and service risk coefficients. This provides multi-dimensional data support for scheduling decisions, solves the problem of fragmented traditional scheduling data, and improves the scientific nature and accuracy of scheduling decisions.

[0043] This invention uses a built-in evaluation model to dynamically allocate weights based on the customer's chosen scheduling modes, such as cost priority, time priority, and safety priority, and outputs an evaluation index. It combines a genetic algorithm to generate a combination of transportation modes and performs time connection verification and equipment matching verification, thus achieving multi-objective collaborative optimization. It can flexibly adapt to different customer needs, achieve a balance between transportation efficiency, cost, and safety, and improve the efficiency of multimodal transport resource allocation.

[0044] This invention monitors abnormal situations in real time through an information monitoring terminal, triggering dynamic corrections to the transportation efficiency coefficient, cost fluctuation coefficient, and service risk coefficient. When the evaluation index changes beyond a preset threshold, the scheduling decision terminal re-executes the scheme generation process to generate an emergency plan. This enhances the system's dynamic response capability to emergencies such as traffic congestion and sudden weather changes, ensuring the stability and reliability of the transportation process, reducing transportation risks, and improving the quality of logistics services. Attached Figure Description

[0045] Figure 1 This is a system framework diagram of the present invention.

[0046] Figure 2 This is a flowchart illustrating the implementation steps of the method of the present invention. Detailed Implementation

[0047] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0048] This invention provides, for example Figure 1 The method for collaborative scheduling of multimodal transport in parcel logistics based on big data includes a parcel data collection terminal, an environmental data collection terminal, a loading equipment data collection terminal, a scheduling decision terminal, an information monitoring terminal, a logistics terminal, and a multimodal transport resource pool.

[0049] The package data collection terminal consists of electronic weighing equipment, laser scanning or visual recognition equipment, RFID tag reader, logistics camera and logistics platform system;

[0050] The environmental data acquisition terminal consists of a meteorological API interface, environmental sensors, a traffic condition API, and a map service platform or traffic management system.

[0051] The loading equipment data acquisition terminal consists of built-in sensors, such as vibration sensors and current sensors.

[0052] The scheduling decision terminal consists of a high-performance computer or server and a data interaction interface. The high-performance computer or server is used to run a genetic algorithm. The data interaction interface obtains real-time available resource data of railway, highway, aviation and waterway by connecting to the multimodal transport resource pool.

[0053] The information monitoring terminal consists of a monitoring software system, an alarm device, and a display screen. The monitoring software system is used to analyze data in real time and identify events such as traffic congestion, sudden weather changes, equipment failures, and abnormal package status. The alarm device is used to alert operators when abnormal events are triggered. The display screen is used to display real-time transportation status and abnormal warning information.

[0054] The logistics terminal consists of a high-performance computer or server, which has a built-in evaluation model. The high-performance computer or server is used to calculate the transportation efficiency coefficient, cost fluctuation coefficient, and service risk coefficient.

[0055] The multimodal transport resource pool consists of a distributed database server and a cloud computing platform, which stores and manages real-time available resource data for railways, highways, aviation, and waterways.

[0056] Specific steps are as follows: Figure 2 As shown:

[0057] S1. The parcel data collection terminal, environmental data collection terminal, and loading equipment data collection terminal collect data from the entire chain of parcels from receipt, sorting, transportation, warehousing to delivery, to obtain parcel datasets, environmental datasets, and loading equipment datasets.

[0058] Furthermore, in the above technical solution, the package dataset includes: package weight, package volume, actual package density, package demand equipment code, package status, customer-specified time window start point, time window length, historical lowest transportation cost for similar packages, package damage rate, complaint rate, historical on-time delivery rate, and historical cargo integrity rate; the environment dataset includes: weather status, weather level, environmental parameter safety thresholds, origin congestion coefficient, destination congestion coefficient, high-risk congested road segment collection, road segment identifiers in the transportation route, and environmental parameters, including: ambient temperature, ambient humidity, and ambient wind force; the loading equipment dataset includes: available equipment type code, maximum value of equipment type code, maximum load capacity of logistics nodes, maximum allowable density of transportation vehicles, optimal loading volume of transportation vehicles, maximum volume of logistics nodes, equipment failure status, and historical average delay time.

[0059] It is important to know that the package weight is automatically collected by electronic weighing equipment at logistics nodes, such as sorting centers and warehouses; the package volume is automatically measured using laser scanning or visual recognition equipment, such as 3D vision measuring instruments, to calculate the volume; the actual package density is automatically calculated from the package weight and volume; the package requires a specific equipment code, which is manually selected by staff based on package characteristics, such as refrigerated or fragile, or automatically identified using smart tags, such as RFID; the package status is identified and collected through manual sampling, visual inspection by logistics cameras, etc., such as package deformation detection; the customer-specified time window start point and time window length are determined by… The logistics platform collects data; the lowest historical transportation cost for similar parcels is calculated based on historical data; the parcel damage rate is obtained by statistically analyzing the ratio of the number of damaged parcels of the same type in historical transportation to the total transportation volume; the complaint rate is calculated by collecting the number of complaints from the customer service system and combining it with the number of orders placed from the order system, where the number of orders is in tens of thousands; the historical on-time delivery rate is obtained by statistically analyzing the number of on-time delivered orders to the total number of orders; the historical goods integrity rate is obtained by statistically analyzing the number of orders with no damaged goods to the total number of orders; the weather status and weather level are obtained in real time from the meteorological department's API along the transportation route and parsed into status data. The environmental parameters are defined as follows: status and level; the environmental parameters are collected by sensors deployed on logistics nodes and transportation vehicles, such as trucks and containers, including temperature sensors, humidity sensors, anemometers, rain gauges, and air quality sensors; the safety thresholds for the environmental parameters are preset by industry standards or internal company specifications; the congestion coefficients at the origin and destination are obtained through real-time traffic APIs from traffic management departments, such as Gaode Maps and Baidu Maps Open Platform; the set of high-risk congested road segments is automatically marked based on historical traffic data; the road segment identifiers in the transportation route are obtained through map service platforms or traffic management systems; the available device type code is preset and uses 8-bit binary. The equipment type is coded, with the first four digits identifying the major category and the last four digits identifying the sub-model. The maximum value of the equipment type code is preset, with a maximum of 256 possible types. The maximum load capacity of the logistics node is obtained from the design drawings or equipment manuals of the logistics node, such as warehouses or freight stations. The maximum allowable density of the transport vehicle is calculated based on the maximum load and volume of the transport vehicle. The optimal loading volume of the transport vehicle is obtained through statistical analysis of historical loading data. The maximum volume of the logistics node is preset. The equipment fault status is monitored in real time by built-in sensors, such as vibration sensors and current sensors, and an alarm is automatically triggered when a fault occurs. The historical average delay time is calculated based on historical data.

[0060] S2. The logistics terminal processes and analyzes the parcel dataset, environmental dataset, and loading equipment dataset to obtain the transportation efficiency coefficient, cost fluctuation coefficient, and service risk coefficient.

[0061] Furthermore, in the above technical solution, the transportation efficiency coefficient is specifically:

[0062] ,

[0063] in, The transportation mode adaptability coefficient is as follows: Where k is the mode of transport, Type(k) is the binary identifier of the mode of transport, and λ k These are the basic efficiency parameters for each mode of transportation; The weather impact coefficient is as follows: Where t represents the weather state, Weather(t) represents the weather level, and μ t The weather influence is weighted; ε is the equipment compatibility coefficient, specifically... Where E is the available device type code, E req For the package requirement equipment coding, E max The maximum value for device type encoding; η is the global scaling factor, specifically... , where e is the natural constant and Z is the evaluation index; Where ω1, ω2, ω3, and ω4 are weighting coefficients, ω1, ω2, ω3, and ω4 ∈ [0, 1], and ω1 + ω2 + ω + ω4 = 1; f1 is the weight utilization factor, specifically:

[0064] ,

[0065] Where D is the actual density of the package, specifically... W0 is the package weight, V0 is the package volume, and W max D is the maximum load-bearing capacity of the logistics node. lim f1 is the maximum allowable density for transportation vehicles; f2 is the volume utilization factor, specifically:

[0066] ,

[0067] Among them, V opt V is the optimal loading volume of the transport vehicle. max Let f be the maximum volume of the logistics node, e be the natural constant, and f3 be the time efficiency factor, specifically:

[0068] ,

[0069] Among them, T minThe shortest time required to complete the transportation task under ideal transportation conditions, where △T is the historical average delay time, and T is the shortest time required to complete the transportation task. w Specify the start point of the time window for the customer, T win T is the length of the time window. p T is the actual transportation time predicted based on historical data. s f4 represents the actual start time of transportation; f4 is the congestion impact factor, specifically:

[0070] ,

[0071] Among them, F avg The overall congestion coefficient is as follows: , of which F s F represents the congestion coefficient at the origin. d R represents the destination congestion coefficient; m represents the total number of road segments in the transportation route. j Let I(R) be the identifier of the j-th road segment in the transportation route, Ω be the set of high-risk congestion road segments, and I(R) be the identifier of the j-th road segment in the transportation route. j ∈Ω) is an indicator function, specifically , used to determine whether the j-th road segment belongs to the set of high-risk congested road segments Ω;

[0072] It should be noted that the values ​​of ω1, ω2, ω3, and ω4 in the transportation efficiency coefficients are dynamically updated according to the scheduling mode. If it is a time-priority mode, then ω1=0.4, ω2=0.3, ω=0.2, and ω4=0.1; if it is a cost-priority mode, then ω1=0.35, ω2=0.35, ω=0.2, and ω4=0.1; if it is a safety-priority mode, then ω1=0.3, ω2=0.3, ω=0.2, and ω4=0.2.

[0073] In γ, the value of k is 1 for water transport, 2 for road transport, 3 for rail transport, and 4 for air transport. λ1=0.7, λ2=0.7, λ3=0.8, λ4=0.9. Specifically, when only road transport is used, Type(k) is 0, Type(2)=1, Type(3)=0, and Type(4)=0.

[0074] In δ, a value of t represents sunny weather (1), cloudy weather (2), light rain or light snow (3), moderate rain or moderate snow (4), and heavy rain, heavy snow, or typhoon (5). Substituting the values ​​of k into Weather(k), Weather(1) = 1, Weather(2) = 2, Weather(3) = 3, Weather(4) = 4, Weather(5) = 5. The weather level Weather(k) can be adjusted according to the climate characteristics of the business area. The weather impact weight μ tIt can be set as μ1∈[0.1, 0.2], μ2∈[0.2, 0.3], μ3∈[0.4, 0.5], μ4∈[0.6, 0.7], μ5∈[0.8, 1.0], where the weather influence weight μ t Set based on weather levels and historical transportation data;

[0075] The initial value of Z in η is set to 0.5. The constant "-5" determines the sensitivity of η to changes in the evaluation index Z. When Z is slightly higher than 0.5, η approaches 0, significantly amplifying the weight of the transportation efficiency coefficient. When Z is slightly lower than 0.5, η rapidly approaches 1, greatly weakening the weight of the transportation efficiency coefficient.

[0076] The cost fluctuation coefficient is specifically as follows:

[0077] ,

[0078] Where n is the number of possible combinations of transportation modes, c i Let be the unit weight cost of the i-th mode of transportation. Let p be the estimated transport distance for the i-th mode of transport. i Let be the damage rate of the package for the i-th transportation method. The lowest transportation cost for similar packages in history is represented by θ, where θ is the fuel price fluctuation coefficient.

[0079] The service risk coefficient is specifically as follows:

[0080] ,

[0081] Among them, O tr For historical on-time delivery rate, I cr For the historical package integrity rate, η time The time sensitivity coefficient is, specifically... , among which, T remain For the remaining transportation time, T plan For planned transportation time; η env This is the environmental risk buffer coefficient, specifically... X i Let X be the actual data for the i-th environment. i，max The safety thresholds for each environmental parameter; Q sec For safety compliance scoring, Q cus The customer complaint rate is scored, specifically as follows: Where, complaint rate = number of complaints ÷ number of orders, with the number of orders in tens of thousands; m is the number of modes in the transportation mode combination, R risk，kLet be the specific risk index for the k-th mode of transportation, n be the total number of environmental parameters, and δ1, δ2, δ3 and δ4 be weighting coefficients, where δ1, δ2, δ3 and δ4 ∈ [0, 1] and δ1 + δ2 + δ3 + δ4 = 1.

[0082] It is important to know the safety threshold X for each of the aforementioned environmental parameters. i，max Pre-defined by industry standards or company specifications, such as the upper temperature limit for cold chain transportation; the service risk coefficient... When k=1, it represents water transport, R risk，1 =Port operation delay time ÷ Standard operation time; When k=2, for highways, R risk，2 = Actual congested mileage ÷ Total mileage; When k=3, for railways, R risk，3 =1 - Current train punctuality rate ÷ 100, where current train punctuality rate = actual on-time trains ÷ total number of trains; when k=4, it is for air travel, R risk，4 = Airport Delay Index ÷ 5, where the delay index is between 0 and 5, with 5 indicating severe delay.

[0083] S3, the logistics terminal imports the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient into the built-in evaluation model, dynamically allocates the weight of the evaluation model according to the scheduling mode selected by the customer, and outputs the evaluation index.

[0084] Furthermore, in the above technical solution, the evaluation model specifically refers to:

[0085] ,

[0086] Where k1 is the timeliness weight coefficient, k2 is the cost weight coefficient, k3 is the safety weight coefficient, k1, k2 and k3 ∈ [0, 1], and k1+k2+k3=1, K is the transportation efficiency coefficient, C is the cost fluctuation coefficient, and S is the service risk coefficient.

[0087] The scheduling modes are divided into cost-priority mode, time-priority mode, and safety-priority mode; the cost-priority mode sets the cost weight coefficient to the highest; the time-priority mode sets the time-priority weight coefficient to the highest; and the safety-priority mode sets the safety weight coefficient to the highest.

[0088] It's important to know that weights are automatically assigned based on the scheduling mode selected by the customer, with the specific rules as follows:

[0089] Time-priority mode: k1=0.6, k2=0.2, k3=0.2;

[0090] Cost-first model: k1=0.5, k2=0.3, k3=0.2;

[0091] Safety priority mode: k1=0.5, k2=0.3, k3=0.2.

[0092] S4. The scheduling decision terminal calls the multimodal transport resource pool to obtain real-time available resources for railway, highway, aviation and water transport. It generates all possible combinations of transport modes through a genetic algorithm, calculates the evaluation index of each combination and sorts them in descending order, then selects the top five as candidate schemes, and then performs time connection verification and equipment matching verification. Finally, it selects the scheme with the highest evaluation index and carbon emissions lower than the industry average from the feasible candidate schemes.

[0093] It is important to know that, according to the rules of the genetic algorithm, the combination of "railway + highway + air + water transport" is represented by binary code 1111, where the first bit is railway, the second bit is highway, the third bit is air, and the fourth bit is water transport. 1 indicates that the mode of transport is selected, and 0 indicates that it is not selected.

[0094] The carbon emissions are specifically: Where i represents the i-th mode of transportation, such as i=1 for water transport, i=2 for road transport, etc. The carbon emission coefficient can be obtained by referencing industry standards, such as the National Greenhouse Gas Accounting Guidelines and the emission factor database of industry associations.

[0095] Furthermore, in the above technical solution, the time connection verification specifically involves verifying the rationality of the time connection between various transportation modes in the candidate solutions, and predicting the actual transportation time T based on historical data. p and the actual start time of transportation T s Determine T s +T p Is it within the customer-specified time window start point T? w With T w +T win Within the range, while considering the shortest time T under ideal transportation conditions min The time efficiency factor f3 is verified to meet the preset timeliness threshold by comparing the historical average delay time ΔT with the time efficiency factor f3. Specifically, the equipment matching verification verifies the compatibility between the loading equipment and the package in the candidate solutions, comparing the available equipment type code E with the package requirement equipment code E. req Ensure E≥E req And E≤E max Simultaneously verify the maximum load-bearing capacity W of the logistics node. max Is the package weight W0 greater than or equal to the maximum allowable density D of the transport vehicle? lim Whether it is greater than or equal to the actual density D of the package, and whether the volume utilization factor f2 meets the preset volume utilization threshold.

[0096] It is important to know that the preset threshold for f2 is shown in Table 1:

[0097] Table 1

[0098] Threshold type Threshold value Coverage scenarios High efficiency ≥0.6 High volumetric efficiency scenarios in air or container shipping keep ≥0.5 High-value goods or volume-sensitive transportation conventional ≥0.45 Standard volume requirements for general cargo Minimum feasible ≥0.1 Emergency dispatch or oversized cargo transportation

[0099] The preset thresholds for f3 are shown in Table 2:

[0100] Table 2

[0101] Threshold type Threshold value Coverage scenarios Extreme punctuality ≥0.97 The need for extreme timeliness in medical emergency care or fresh food cold chain keep ≥0.9 Time-limited delivery conventional ≥0.8 Minimum delivery time for ordinary e-commerce parcels Minimum tolerance ≥0.2 Bulk supplies or non-emergency transportation

[0102] In one specific embodiment, assuming the customer selects the time-priority mode, the scheduling decision terminal generates the following 5 candidate schemes through a genetic algorithm, as shown in Table 3:

[0103] Table 3

[0104] Candidate solutions Transportation methods Evaluation Index Z Time coherence verification Device matching verification Carbon emissions (t) 1 Highway + Aviation 0.85 pass pass 1.2 2 Railway + Aviation 0.82 pass pass 1.0 3 Highway + Railway 0.78 pass Device coding mismatch 1.3 4 aviation 0.75 Time window out of bounds - 1.1 5 Highway + Water Transport 0.70 pass pass 1.6

[0105] Based on industry standards, determine carbon emissions and select Option 1;

[0106] S5. When the information monitoring terminal detects an abnormal situation, it triggers dynamic correction of the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient. When the absolute value of the difference between the updated evaluation index and the original evaluation index exceeds the preset threshold, the dispatch decision terminal re-executes the plan generation process to generate an emergency plan.

[0107] Furthermore, in the above technical solution, the dynamic correction is as follows:

[0108] A1. During traffic congestion, the overall congestion coefficient F in the transportation efficiency coefficient K and service risk coefficient S. avg and indicator function I(R) j The value of (∈Ω) is corrected;

[0109] A2. When weather changes abruptly, the impact of weather on the transportation efficiency coefficient K and the service risk coefficient S, as well as the environmental risk buffer coefficient η, is affected. env The value is corrected;

[0110] A3. In the event of equipment failure, the equipment compatibility coefficient ε and safety compliance score Q in the transportation efficiency coefficient K and service risk coefficient S are considered. sec The value is corrected;

[0111] A4. When a package is in an abnormal state, the weight utilization factor f1, volume utilization factor f2, and package damage rate p for the i-th transportation mode are considered in the transportation efficiency coefficient K, cost fluctuation coefficient C, and service risk coefficient S. i The value is corrected.

[0112] In one specific embodiment, assuming the information monitoring terminal detects via a meteorological API that the weather along the transportation route suddenly changes from cloudy to heavy rain, the ambient temperature rises from 25°C to 30°C (approaching the safety threshold of 35°C), and the humidity rises from 60% to 90% (exceeding the safety threshold of 80%), an efficiency coefficient K correction is triggered. Specifically, the weather influence coefficient δ increases from 0.5 to 4.5. If the package requires a refrigerated box E... req =0100, currently available devices E=0100, but heavy rain may cause temporary device failure risk, the device compatibility coefficient ε drops from 1 to 0.8, and at the same time triggers the service risk coefficient S correction, specifically the environmental risk buffer coefficient η. env The safety compliance score rose from 0.3 to 0.7 due to potential violations of transportation safety regulations caused by heavy rain; the score is now Q. sec The score dropped from 90 to 75. After dynamic correction, the evaluation index Z′=0.48. Based on the original evaluation index Z=0.6, the difference of 0.12 was calculated, which is greater than the preset threshold of 0.1. This triggered the re-execution of the scheme generation process. The scheduling decision terminal then generated an "air + road" combination through a genetic algorithm. The scheme passed the time connection verification and equipment matching verification. Although the cost increased, it avoided the risk of delays and cargo damage caused by heavy rain.

[0113] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A multimodal transport collaborative scheduling method for parcel logistics based on big data, characterized in that, This includes parcel data collection terminals, environmental data collection terminals, loading equipment data collection terminals, scheduling decision terminals, information monitoring terminals, logistics terminals, and a multimodal transport resource pool. The specific steps are as follows: S1. The parcel data collection terminal, environmental data collection terminal, and loading equipment data collection terminal collect data from the entire chain of parcels from receipt, sorting, transportation, warehousing to delivery, to obtain parcel datasets, environmental datasets, and loading equipment datasets. S2. The logistics terminal processes and analyzes the parcel dataset, environmental dataset, and loading equipment dataset to obtain the transportation efficiency coefficient, cost fluctuation coefficient, and service risk coefficient. The transportation efficiency coefficient is specifically: ， Where γ is the transportation mode adaptation coefficient, specifically... Where k is the mode of transport, Type(k) is the binary identifier of the mode of transport, and λ k These are the basic efficiency parameters for each mode of transportation; δ is the weather impact coefficient, specifically... Where t represents the weather state, Weather(t) represents the weather level, and μ t The weather influence is weighted; ε is the equipment compatibility coefficient, specifically... Where E is the available device type code, E req For the package requirement equipment coding, E max The maximum value for device type encoding; η is the global scaling factor, specifically... , where e is the natural constant and Z is the evaluation index; Where ω1, ω2, ω3, and ω4 are weighting coefficients, ω1, ω2, ω3, and ω4 ∈ [0, 1], and ω1 + ω2 + ω + ω4 = 1; f1 is the weight utilization factor, specifically: ， Where D is the actual density of the package, specifically... W0 is the package weight, V0 is the package volume, and W max D is the maximum load-bearing capacity of the logistics node. lim f1 is the maximum allowable density for transportation vehicles; f2 is the volume utilization factor, specifically: ， Among them, V opt V is the optimal loading volume of the transport vehicle. max Let f be the maximum volume of the logistics node, e be the natural constant, and f3 be the time efficiency factor, specifically: ， Among them, T min The shortest time required to complete the transportation task under ideal transportation conditions, where △T is the historical average delay time, and T is the shortest time required to complete the transportation task. w Specify the start point of the time window for the customer, T win T is the length of the time window. p T is the actual transportation time predicted based on historical data. s f4 represents the actual start time of transportation; f4 is the congestion impact factor, specifically: ， Among them, F avg The overall congestion coefficient is as follows: , of which F s F represents the congestion coefficient at the origin. d R represents the destination congestion coefficient; m represents the total number of road segments in the transportation route. j Let I(R) be the identifier of the j-th road segment in the transportation route, Ω be the set of high-risk congestion road segments, and I(R) be the identifier of the j-th road segment in the transportation route. j ∈Ω) is an indicator function, specifically , used to determine whether the j-th road segment belongs to the set of high-risk congested road segments Ω; The cost fluctuation coefficient is specifically as follows: ， Where n is the number of possible combinations of transportation modes, c i Let l be the unit weight cost of the i-th mode of transportation. i Let p be the estimated transport distance for the i-th mode of transport. i Let be the damage rate of the package for the i-th transportation method. The lowest transportation cost for similar packages in history, where θ is the fuel price fluctuation coefficient; The service risk coefficient is specifically as follows: ， Among them, O tr For historical on-time delivery rate, I cr For the historical package integrity rate, η time The time sensitivity coefficient is, specifically... , among which, T remain For the remaining transportation time, T plan For planned transportation time; η env This is the environmental risk buffer coefficient, specifically... X i Let X be the actual data for the i-th environment. i，max The safety thresholds for each environmental parameter; Q sec For safety compliance scoring, Q cus The customer complaint rate is scored, specifically as follows: Where, complaint rate = number of complaints ÷ number of orders, with the number of orders in tens of thousands; m is the number of modes in the transportation mode combination, R risk，k Let be the specific risk index for the k-th mode of transportation, n be the total number of environmental parameters, and δ1, δ2, δ3 and δ4 be weighting coefficients, where δ1, δ2, δ3 and δ4 ∈ [0, 1] and δ1 + δ2 + δ3 + δ4 = 1. S3, the logistics terminal imports the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient into the built-in evaluation model, dynamically allocates the weight of the evaluation model according to the scheduling mode selected by the customer, and outputs the evaluation index. S4. The scheduling decision terminal calls the multimodal transport resource pool to obtain real-time available resources for railway, highway, aviation and water transport. It generates all possible combinations of transport modes through a genetic algorithm, calculates the evaluation index of each combination and sorts them in descending order, then selects the top five as candidate schemes, and then performs time connection verification and equipment matching verification. Finally, it selects the scheme with the highest evaluation index and carbon emissions lower than the industry average from the feasible candidate schemes. S5. When the information monitoring terminal detects an abnormal situation, it triggers dynamic correction of the transportation efficiency coefficient, cost fluctuation coefficient and service risk coefficient. When the absolute value of the difference between the updated evaluation index and the original evaluation index exceeds the preset threshold, the dispatch decision terminal re-executes the plan generation process to generate an emergency plan.

2. The method for collaborative scheduling of multimodal transport of parcel logistics based on big data as described in claim 1, characterized in that, The package dataset includes: package weight, package volume, actual package density, package equipment code, package status, customer-specified time window start point, time window length, historical lowest transportation cost for similar packages, package damage rate, complaint rate, historical on-time delivery rate, and historical cargo integrity rate. The environment dataset includes: weather status, weather level, environmental parameter safety thresholds, origin congestion coefficient, destination congestion coefficient, high-risk congested road segment collection, road segment identifiers in the transportation route, and environmental parameters, including: ambient temperature, ambient humidity, and ambient wind force. The loading equipment dataset includes: available equipment type code, maximum value of equipment type code, maximum load capacity of logistics nodes, maximum allowable density of transportation vehicles, optimal loading volume of transportation vehicles, maximum volume of logistics nodes, equipment failure status, and historical average delay time.

3. The method for collaborative scheduling of multimodal transport of parcel logistics based on big data as described in claim 1, characterized in that, The evaluation model is specifically as follows: ， Where k1 is the timeliness weight coefficient, k2 is the cost weight coefficient, k3 is the safety weight coefficient, k1, k2 and k3 ∈ [0, 1], and k1+k2+k3=1, K is the transportation efficiency coefficient, C is the cost fluctuation coefficient, and S is the service risk coefficient.

4. The method for collaborative scheduling of multimodal transport of parcel logistics based on big data as described in claim 1, characterized in that, The scheduling modes are divided into cost-priority mode, time-priority mode, and safety-priority mode; the cost-priority mode sets the cost weight coefficient to the highest; the time-priority mode sets the time-priority weight coefficient to the highest; and the safety-priority mode sets the safety weight coefficient to the highest.

5. The method for collaborative scheduling of multimodal transport of parcel logistics based on big data according to claim 1, characterized in that, The time coordination verification specifically involves verifying the rationality of the time coordination among various transportation modes in the candidate schemes, and predicting the actual transportation time T based on historical data. p and the actual start time of transportation T s Determine T s +T p Is it within the customer-specified time window start point T? w With T w +T win Within the range, while considering the shortest time T under ideal transportation conditions min The time efficiency factor f3 is verified to meet the preset timeliness threshold by comparing the historical average delay time ΔT with the time efficiency factor f3. Specifically, the equipment matching verification verifies the compatibility between the loading equipment and the package in the candidate solutions, comparing the available equipment type code E with the package requirement equipment code E. req Ensure E≥E req And E≤E max Simultaneously verify the maximum load-bearing capacity W of the logistics node. max Is the package weight W0 greater than or equal to the maximum allowable density D of the transport vehicle? lim Whether it is greater than or equal to the actual density D of the package, and whether the volume utilization factor f2 meets the preset volume utilization threshold.

6. The method for collaborative scheduling of multimodal transport of parcel logistics based on big data according to claim 3, characterized in that, The dynamic correction is as follows: A1. During traffic congestion, the overall congestion coefficient F in the transportation efficiency coefficient K and service risk coefficient S. avg and indicator function I(R) j The value of ∈Ω is corrected; A2. When weather changes abruptly, the impact of weather on the transportation efficiency coefficient K and the service risk coefficient S, as well as the environmental risk buffer coefficient η, is affected. env The value is corrected; A3. In the event of equipment failure, the equipment compatibility coefficient ε and safety compliance score Q in the transportation efficiency coefficient K and service risk coefficient S are considered. sec The value is corrected; A4. When a package is in an abnormal state, the weight utilization factor f1, volume utilization factor f2, and package damage rate p for the i-th transportation mode are considered in the transportation efficiency coefficient K, cost fluctuation coefficient C, and service risk coefficient S. i The value is corrected.

Images