Logistics resource intelligent scheduling optimization system based on big data analysis

Abstract

The invention relates to the technical field of intelligent logistics scheduling optimization, and discloses a logistics resource intelligent scheduling optimization system based on big data analysis, and the system comprises a data collection module which is used for collecting basic data, and the basic data comprise temperature sensing data, transportation load data, path parameter data, and vehicle operation state information; the data fusion module is used for fusing the temperature sensing data and the transportation load data and outputting a temperature zone label and a temperature control load characteristic; the index construction module is used for calculating thermal exposure time and generating a thermal exposure intensity index and a quality risk index; the energy efficiency modeling module is used for calculating path cost values corresponding to the plurality of paths and vehicle combinations; and the path energy efficiency optimization module is used for constructing a multi-target path optimization model and outputting an optimal transportation path combination. According to the invention, efficient energy consumption control and quality risk collaborative optimization of resource scheduling in a cold-chain logistics scene are realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent logistics scheduling optimization, and specifically relates to a logistics resource intelligent scheduling optimization system based on big data analysis. Background Art

[0002] With the rapid development of cold chain logistics, urban distribution, and multi-temperature zone transportation, traditional logistics scheduling systems are facing challenges such as low transport resource utilization, high energy consumption, and weak quality risk control. Existing scheduling methods still prioritize minimizing transport distances or optimizing delivery times, ignoring the heat exposure risks of temperature-controlled goods during transportation and the varying energy consumption of refrigeration equipment. This makes it difficult to meet the multiple requirements of modern cold chain transportation for efficiency, safety, and energy control.

[0003] Furthermore, existing solutions often lack the ability to comprehensively utilize multi-source, heterogeneous logistics data. They are unable to fully collect and integrate dynamic information such as cargo temperature, ambient temperature, route distance, cargo load, and vehicle refrigeration power. This results in limited input dimensions for scheduling models and incomplete route evaluation. Furthermore, existing solutions rely on fixed rules or static models in their optimization algorithms, lacking dynamic updating and adaptability, making it difficult to guarantee optimization efficiency and scheduling quality. Summary of the Invention

[0004] The present invention provides an intelligent logistics resource scheduling and optimization system based on big data analysis, which solves the technical problems in related technologies such as one-sided transportation route selection, insufficient temperature control risk assessment, and failure to reflect differences in refrigeration energy consumption, which lead to unreasonable scheduling, high cargo damage rate and low resource utilization.

[0005] The present invention provides a logistics resource intelligent scheduling optimization system based on big data analysis, including:

[0006] A data acquisition module is used to collect basic data related to logistics and transportation, including temperature sensor data, transportation load data, route parameter data and vehicle operation status information;

[0007] Temperature sensing data includes: cargo temperature and ambient temperature;

[0008] Transport load data includes: cargo mass, delivery time and loading status;

[0009] Path parameter data include: path distance and path number;

[0010] Vehicle operating status information includes: vehicle cooling power, vehicle speed and vehicle volume capacity;

[0011] A data fusion module is used to fuse the temperature sensing data with the transport load data and output temperature zone labels and temperature control load characteristics according to a preset target temperature range;

[0012] An indicator construction module is used to calculate the heat exposure time based on the preset target temperature range and cargo temperature, and generate the heat exposure intensity index and quality risk index based on the temperature control load characteristics and heat exposure time;

[0013] Energy efficiency modeling module, used to calculate the path cost corresponding to multiple path and vehicle combinations based on heat exposure intensity indicators and quality risk indicators, combined with temperature zone labels, temperature control load characteristics and vehicle cooling power;

[0014] The path energy efficiency optimization module is used to construct a multi-objective path optimization model based on the path cost value and in combination with the constraint conditions, and output the optimal transportation path combination, wherein the transportation path combination includes transportation paths executed by multiple vehicles respectively, and each transportation path includes multiple stations.

[0015] Furthermore, the temperature zone label is generated based on the comparison result between the temperature of the goods and the preset target temperature range, and the temperature zone label includes: freezing zone, refrigeration zone and normal temperature zone;

[0016] The calculation formula for temperature control load characteristics is: ;

[0017] in, Indicates the temperature control load characteristics, Indicates cargo temperature, Indicates the preset minimum target temperature for the goods. Indicates the maximum target temperature preset for the goods. Indicates the ambient temperature, Indicates the quality of goods, Indicates the delivery time. Indicates loading status, 、 、 、 and They represent the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the fifth weight coefficient respectively.

[0018] Furthermore, the heat exposure time is obtained based on the relationship between the temperature of the cargo during transportation and a preset target temperature range, and represents the cumulative time that the temperature of the cargo exceeds the target temperature range;

[0019] The calculation formula for the heat exposure intensity index is: , where TES represents the heat exposure intensity index and dt represents the time integral.

[0020] Furthermore, the quality risk index is calculated using a piecewise function based on the heat exposure intensity index, including:

[0021] When the heat exposure intensity index is lower than the first preset threshold, the quality risk index is 1;

[0022] When the heat exposure intensity index is between a first preset threshold and a second preset threshold, the quality risk index is an exponential decay function;

[0023] When the heat exposure intensity index is higher than the second preset threshold, the quality risk index is 0.

[0024] Furthermore, the path cost value is obtained by multiplying the path distance with the weighted coefficients of the heat exposure intensity index and the quality risk index. The calculation formula of the path cost value is: ;

[0025] in, represents the path cost of vehicle k from station i to station j, represents the path distance from site i to site j, and They represent the quality risk index of site j at the rth and r+1th steps of the path segment, and They represent the heat exposure intensity index of site j at the rth and r+1th steps of the path segment, and They represent the sixth weight coefficient and the seventh weight coefficient respectively.

[0026] Furthermore, the path cost is corrected based on the vehicle cooling power, and the correction formula is: , represents the corrected path cost, represents the correction factor, represents the vehicle cooling power of vehicle k, Indicates the maximum vehicle cooling power among all vehicles.

[0027] Furthermore, the specific steps of outputting the optimal transportation route combination include:

[0028] S201, initializing a transportation path combination based on the path cost and constraint conditions;

[0029] S202, constructing an objective function based on the path cost, wherein the objective function includes the total path cost, the cargo temperature control quality loss, and the vehicle refrigeration energy consumption;

[0030] S203, calculating the objective function value based on the current transportation path combination;

[0031] S204, using a first updating strategy to update the current transport path combination;

[0032] S205, repeat S203 to S204 until the number of iterations reaches the maximum number of iterations, and output the transportation path combination with the minimum objective function value as the optimal transportation path combination.

[0033] Furthermore, the constraints include transport time window constraints, temperature zone capacity constraints, load constraints, and temperature zone consistency constraints;

[0034] The transport time window constraint indicates that the delivery time of each transport is within a first preset time interval, and the first preset time interval is determined according to the content of the transport;

[0035] The temperature zone capacity constraint means that the total volume of the cargo assigned to the vehicle in each temperature zone is not higher than the preset volume threshold of the corresponding temperature zone;

[0036] The load constraint indicates that the mass of the cargo carried by the vehicle in a single route is not higher than a third preset threshold;

[0037] The temperature zone consistency constraint indicates that the goods transported on the same transportation route have the same temperature control requirements.

[0038] Furthermore, the objective function is composed of the total route cost, the cargo temperature control quality loss, and the vehicle refrigeration energy consumption. The calculation formula of the objective function is: ;

[0039] in, represents the objective function value, Indicates whether the path segment is selected, the value is 0 or 1, Indicates the mass attenuation coefficient of the goods, and Represent the eighth and ninth weight coefficients respectively.

[0040] Furthermore, the first update strategy includes:

[0041] S401, selecting a path in the current transport path combination for local perturbation, wherein the local perturbation includes: changing the order of sites in the path, merging paths, and splitting paths;

[0042] S402, calculating a corresponding objective function value based on the disturbed transportation path combination;

[0043] S403: If the objective function value after the disturbance is less than the objective function value before the disturbance, the transportation path combination after the disturbance is replaced with the current transportation path combination.

[0044] The beneficial effects of the present invention are as follows: the present invention integrates multi-source data such as temperature, path, load and vehicle status to construct a multi-objective optimization model that comprehensively considers the transportation path cost, temperature control quality risk and refrigeration energy consumption. The present invention ensures data comparability through normalization processing, and combines heat exposure indicators and quality risk functions to calculate path cost. At the same time, it introduces a path combination initialization strategy and update mechanism to achieve iterative optimization of the transportation path. Compared with the existing technology, the present invention can improve scheduling intelligence and cold chain transportation energy efficiency, effectively control cargo damage rate, and is suitable for the optimization of high-complexity transportation tasks in multi-vehicle and multi-constraint scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 It is a module diagram of the logistics resource intelligent scheduling optimization system based on big data analysis of the present invention. DETAILED DESCRIPTION

[0046] The subject matter described herein will now be discussed with reference to exemplary embodiments. It should be understood that these embodiments are discussed solely to enable those skilled in the art to better understand and implement the subject matter described herein, and that the functions and arrangements of the elements discussed may be varied without departing from the scope of this specification. Various examples may omit, substitute, or add various processes or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

[0047] like Figure 1 As shown in the figure, the intelligent scheduling and optimization system for logistics resources based on big data analysis includes:

[0048] The data acquisition module 101 is used to collect basic data related to logistics and transportation, including temperature sensor data, transportation load data, route parameter data and vehicle operation status information;

[0049] Temperature sensing data includes: cargo temperature and ambient temperature;

[0050] Transport load data includes: cargo mass, delivery time and loading status;

[0051] Path parameter data include: path distance and path number;

[0052] Vehicle operating status information includes: vehicle cooling power, vehicle speed and vehicle volume capacity;

[0053] The data fusion module 102 is used to fuse the temperature sensing data with the transport load data and output a temperature zone label and temperature control load characteristics according to a preset target temperature range;

[0054] An indicator construction module 103 is used to calculate the heat exposure time according to the preset target temperature range and the cargo temperature, and generate a heat exposure intensity index and a quality risk index based on the temperature control load characteristics and the heat exposure time;

[0055] Energy efficiency modeling module 104, used to calculate the path cost corresponding to multiple path and vehicle combinations based on the heat exposure intensity index and the quality risk index, combined with the temperature zone label, temperature control load characteristics and vehicle cooling power;

[0056] The path energy efficiency optimization module 105 is used to construct a multi-objective path optimization model based on the path cost and in combination with the constraint conditions, and output an optimal transportation path combination, where the transportation path combination includes transportation paths executed by multiple vehicles respectively, and each transportation path includes multiple stations.

[0057] In one embodiment of the present invention, the cargo temperature and the ambient temperature are collected by the installed temperature sensor, the unit is ℃, the cargo mass is obtained through the record at the time of loading, the delivery time is obtained through the order system, the unit is h, the loading status includes empty and non-empty, and 0 indicates that the loading status is empty, and 1 indicates that the loading status is not empty, the path distance is obtained through the Amap interface service, the unit is km, the path number is pre-assigned, the vehicle refrigeration power is the power value of the vehicle refrigeration equipment in the basic operating state, the unit is kW, the vehicle speed is km / h, and the vehicle volume capacity is ;

[0058] To ensure that input data from different sources and different physical dimensions can be used for unified optimization model calculations, this embodiment first normalizes all basic data using the maximum and minimum normalization method before path modeling and objective function construction, compressing each data item to between 0 and 1.

[0059] In one embodiment of the present invention, the temperature zone label is generated based on the comparison result between the cargo temperature and a preset target temperature range. The target temperature range represents the range between a minimum target temperature and a maximum target temperature. The temperature zone labels include: freezing zone, refrigeration zone, and normal temperature zone. When the cargo temperature is lower than the preset minimum target temperature, the temperature zone label is freezing zone; when the cargo temperature is within the preset target temperature range, the temperature zone label is refrigeration zone; and when the cargo temperature is higher than the preset maximum target temperature, the temperature zone label is normal temperature zone.

[0060] The calculation formula for temperature control load characteristics is: ;

[0061] in, Indicates the temperature control load characteristics, which are used to reflect the degree of dependence of transported goods on temperature control capabilities under specific conditions. Indicates cargo temperature, Indicates the preset minimum target temperature for the goods. Indicates the maximum target temperature preset for the goods. Indicates the ambient temperature, Indicates the quality of goods, Indicates the delivery time. Indicates loading status, 、 、 、 and They represent the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the fifth weight coefficient respectively.

[0062] In one embodiment of the present invention, the heat exposure time is obtained based on the relationship between the temperature of the cargo during transportation and a preset target temperature range, and represents the cumulative time that the temperature of the cargo exceeds the target temperature range;

[0063] The calculation formula for the heat exposure intensity index is: Among them, TES represents the heat exposure intensity index, which is used to measure the impact of the time and intensity of the goods exceeding the target temperature range during transportation. dt represents the time integral. The larger the heat exposure intensity index, the more serious the temperature control deviation and the higher the transportation risk.

[0064] In one embodiment of the present invention, the quality risk index is calculated based on the heat exposure intensity index using a piecewise function, including:

[0065] When the heat exposure intensity index is lower than the first preset threshold, the quality risk index is 1;

[0066] When the heat exposure intensity index is between a first preset threshold and a second preset threshold, the quality risk index is an exponential decay function;

[0067] When the heat exposure intensity index is higher than the second preset threshold, the quality risk index is 0;

[0068] Specifically, the calculation formula for the quality risk index is: ,in, represents the first preset threshold, represents the second preset threshold, exp represents the exponential function, Indicates the cargo sensitivity coefficient.

[0069] In one embodiment of the present invention, the path cost value is obtained by multiplying the path distance with the weighted coefficients of the heat exposure intensity index and the quality risk index. The calculation formula of the path cost value is: ;

[0070] in, represents the path cost of vehicle k from station i to station j, which is used to comprehensively evaluate the temperature control risk and energy consumption cost faced by the path segment during transportation. represents the path distance from site i to site j, and They represent the quality risk index of site j at the rth and r+1th steps of the path segment, and They represent the thermal exposure intensity index of site j at the rth and r+1th steps of the path segment, respectively, and are used to quantify the intensity of temperature control deviation. and They represent the sixth weight coefficient and the seventh weight coefficient respectively.

[0071] In one embodiment of the present invention, the path cost is corrected based on the vehicle cooling power, and the correction formula is: , represents the corrected path cost, represents the correction factor, represents the vehicle cooling power of vehicle k, Represents the maximum vehicle cooling power among all vehicles. By correcting the vehicle cooling power, vehicles with larger vehicle cooling power will have higher transportation costs on the same route, making the route selection closer to the actual operating energy consumption.

[0072] In one embodiment of the present invention, the specific steps of outputting the optimal transportation path combination include:

[0073] S201, initializing a transportation path combination based on the path cost and constraint conditions;

[0074] Specifically, the transport path combination is generated by the nearest neighbor path construction principle. The specific steps include:

[0075] S301, obtain a set of all sites to be delivered and arrange them in a preset order;

[0076] S302, selecting a vehicle from the set of vehicles as the current dispatch vehicle and initializing its transportation path;

[0077] S303, starting from the current site, select the nearest site as the next site to visit;

[0078] S304, continuously repeating the nearest neighbor selection and site addition until the vehicle's load reaches the limit;

[0079] S305, select the next vehicle and repeat S302 to S304 until all stations are assigned to at least one route, obtaining an initial transport route combination;

[0080] S202, constructing an objective function based on the route cost, wherein the objective function is used to comprehensively evaluate the total route cost, the loss of cargo temperature control quality, and the energy consumption of the vehicle refrigeration machine;

[0081] S203, calculating the objective function value based on the current transportation path combination;

[0082] S204, using a first updating strategy to update the current transport path combination;

[0083] S205, repeat S203 to S204 until the number of iterations reaches the maximum number of iterations, and output the transportation path combination with the minimum objective function value as the optimal transportation path combination.

[0084] In one embodiment of the present invention, the constraints include a transport time window constraint, a temperature zone capacity constraint, a load constraint, and a temperature zone consistency constraint;

[0085] The transport time window constraint indicates that the delivery time of each transport is within a first preset time interval, and the first preset time interval is determined according to the content of the transport;

[0086] The temperature zone capacity constraint means that the total volume of the cargo assigned to the vehicle in each temperature zone is not higher than the preset volume threshold of the corresponding temperature zone;

[0087] The load constraint indicates that the mass of the cargo carried by the vehicle in a single route is not higher than a third preset threshold;

[0088] The temperature zone consistency constraint indicates that the goods transported on the same transportation route have the same temperature control requirements.

[0089] In one embodiment of the present invention, the objective function is composed of the total route cost, the cargo temperature control quality loss, and the vehicle refrigeration energy consumption. The objective function is calculated as follows: ;

[0090] in, represents the objective function value, Indicates whether the path segment is selected, the value is 0 or 1, Indicates the mass attenuation coefficient of the goods, and Represent the eighth and ninth weight coefficients respectively. If you need to give priority to controlling the risk of cargo damage, you can increase If you need to reduce energy costs, you can increase , is the total path cost, which is used to reflect the total path cost. The temperature control quality loss of goods is used to reflect the estimated loss of goods quality under temperature control. The energy consumption of the vehicle refrigeration machine is used to reflect the cumulative energy consumption during the operation of the vehicle refrigeration machine. The objective function of this embodiment not only reflects the transportation route length, temperature control risk and energy consumption, but also has good adjustment flexibility and optimization adaptability. It can improve the cargo damage control capability and system scheduling intelligence, and meet the comprehensive optimization needs of multiple objectives and multiple constraints in actual cold chain transportation.

[0091] In one embodiment of the present invention, the first update strategy includes:

[0092] S401, selecting a path in the current transport path combination for local perturbation, wherein the local perturbation includes: changing the order of sites in the path, merging paths, and splitting paths;

[0093] S402, calculating a corresponding objective function value based on the disturbed transportation path combination;

[0094] S403: If the objective function value after the disturbance is less than the objective function value before the disturbance, the transportation path combination after the disturbance is replaced with the current transportation path combination.

[0095] In this embodiment, through the above-mentioned first update strategy, an adaptive path structure update mechanism with the objective function as the core can be realized, and the iterative optimization of the transportation path combination can be achieved on the basis of satisfying multiple constraints. The first update strategy can not only control the disturbance amplitude, but also keep the optimization direction reasonable, and is suitable for the dynamic path solution needs of large-scale multi-vehicle cold chain transportation tasks.

[0096] It should be noted that the intervals and thresholds are set for ease of comparison. The threshold size depends on the amount of sample data and the cardinality set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless numerical calculations. These formulas are derived from software simulations of the most recent real-world conditions using large amounts of data. The preset parameters in these formulas are set by those skilled in the art based on actual conditions.

[0097] The above describes the embodiments of the present invention, but the present invention is not limited to the above specific implementation methods. The above specific implementation methods are merely illustrative and not restrictive. Ordinary technicians in this field can also make many forms based on the inspiration of this embodiment, all of which are protected by this embodiment.

Claims

1. Logistics resource intelligent scheduling optimization system based on big data analysis, characterized by: include: A data acquisition module is used to collect basic data related to logistics and transportation, including temperature sensor data, transportation load data, route parameter data and vehicle operation status information; Temperature sensing data includes: cargo temperature and ambient temperature; Transport load data includes: cargo mass, delivery time and loading status; Path parameter data include: path distance and path number; Vehicle operating status information includes: vehicle cooling power, vehicle speed and vehicle volume capacity; A data fusion module is used to fuse the temperature sensing data with the transport load data and output temperature zone labels and temperature control load characteristics according to a preset target temperature range; An indicator construction module is used to calculate the heat exposure time based on the preset target temperature range and cargo temperature, and generate the heat exposure intensity index and quality risk index based on the temperature control load characteristics and heat exposure time; Energy efficiency modeling module, used to calculate the path cost corresponding to multiple path and vehicle combinations based on heat exposure intensity indicators and quality risk indicators, combined with temperature zone labels, temperature control load characteristics and vehicle cooling power; The path energy efficiency optimization module is used to construct a multi-objective path optimization model based on the path cost value and in combination with the constraint conditions, and output the optimal transportation path combination, wherein the transportation path combination includes transportation paths executed by multiple vehicles respectively, and each transportation path includes multiple stations.

2. The intelligent logistics resource scheduling and optimization system based on big data analysis according to claim 1 is characterized in that: The temperature zone label is generated based on the comparison result between the cargo temperature and the preset target temperature range. The temperature zone labels include: frozen zone, refrigerated zone and normal temperature zone; The calculation formula for temperature control load characteristics is: ； in, Indicates the temperature control load characteristics, Indicates cargo temperature, Indicates the preset minimum target temperature for the goods. Indicates the maximum target temperature preset for the goods. Indicates the ambient temperature, Indicates the quality of goods, Indicates the delivery time. Indicates loading status, 、 、 、 and They represent the first weight coefficient, the second weight coefficient, the third weight coefficient, the fourth weight coefficient and the fifth weight coefficient respectively.

3. The intelligent logistics resource scheduling and optimization system based on big data analysis according to claim 2 is characterized in that: The heat exposure time is obtained based on the relationship between the cargo temperature during transportation and a preset target temperature range, and represents the cumulative time that the cargo temperature exceeds the target temperature range; The calculation formula for the heat exposure intensity index is: , where TES represents the heat exposure intensity index and dt represents the time integral.

4. The intelligent scheduling and optimization system for logistics resources based on big data analysis according to claim 1 is characterized in that: The quality risk index is calculated using a piecewise function based on the heat exposure intensity index, including: When the heat exposure intensity index is lower than the first preset threshold, the quality risk index is 1; When the heat exposure intensity index is between a first preset threshold and a second preset threshold, the quality risk index is an exponential decay function; When the heat exposure intensity index is higher than the second preset threshold, the quality risk index is 0.

5. The intelligent scheduling and optimization system for logistics resources based on big data analysis according to claim 1 is characterized in that: The path cost value is obtained by multiplying the path distance with the weighted coefficients of the heat exposure intensity index and the quality risk index. The calculation formula of the path cost value is: ； in, represents the path cost of vehicle k from station i to station j, represents the path distance from site i to site j, and They represent the quality risk index of site j at the rth and r+1th steps of the path segment, and They represent the heat exposure intensity index of site j at the rth and r+1th steps of the path segment, and They represent the sixth weight coefficient and the seventh weight coefficient respectively.

6. The intelligent scheduling and optimization system for logistics resources based on big data analysis according to claim 5 is characterized in that: The path cost is corrected based on the vehicle cooling power, and the correction formula is: , represents the corrected path cost, represents the correction factor, represents the vehicle cooling power of vehicle k, Indicates the maximum vehicle cooling power among all vehicles.

7. The intelligent scheduling and optimization system for logistics resources based on big data analysis according to claim 1 is characterized in that: The specific steps of outputting the optimal transportation path combination include: S201, initializing a transportation path combination based on the path cost and constraint conditions; S202, constructing an objective function based on the path cost, wherein the objective function includes the total path cost, the cargo temperature control quality loss, and the vehicle refrigeration energy consumption; S203, calculating the objective function value based on the current transportation path combination; S204, using a first updating strategy to update the current transport path combination; S205, repeat S203 to S204 until the number of iterations reaches the maximum number of iterations, and output the transportation path combination with the minimum objective function value as the optimal transportation path combination.

8. The logistics resource intelligent scheduling optimization system based on big data analysis according to claim 7 is characterized in that: The constraints include transport time window constraints, temperature zone capacity constraints, load constraints and temperature zone consistency constraints; The transport time window constraint indicates that the delivery time of each transport is within a first preset time interval, and the first preset time interval is determined according to the content of the transport; The temperature zone capacity constraint means that the total volume of the cargo assigned to the vehicle in each temperature zone is not higher than the preset volume threshold of the corresponding temperature zone; The load constraint indicates that the mass of the cargo carried by the vehicle in a single route is not higher than a third preset threshold; The temperature zone consistency constraint indicates that the goods transported on the same transportation route have the same temperature control requirements.

9. The logistics resource intelligent scheduling and optimization system based on big data analysis according to claim 7 is characterized in that: The objective function is composed of the total route cost, the cargo temperature control quality loss, and the vehicle refrigeration energy consumption. The objective function is calculated as follows: ； in, represents the objective function value, Indicates whether the path segment is selected, the value is 0 or 1, Indicates the mass attenuation coefficient of the goods, and Represent the eighth and ninth weight coefficients respectively.

10. The logistics resource intelligent scheduling and optimization system based on big data analysis according to claim 7 is characterized in that: The first update strategy includes: S401, selecting a path in the current transport path combination for local perturbation, wherein the local perturbation includes: changing the order of sites in the path, merging paths, and splitting paths; S402, calculating a corresponding objective function value based on the disturbed transportation path combination; S403: If the objective function value after the disturbance is less than the objective function value before the disturbance, the transportation path combination after the disturbance is replaced with the current transportation path combination.

Images