A logistics vehicle and cargo intelligent matching system and method based on carbon footprint

Abstract

The application discloses a kind of logistics car goods intelligent matching system and method based on carbon footprint, it is related to logistics car goods matching technical field, including the degree of adaptation between analysis vehicle and target goods, obtain candidate vehicle;Obtain logistics trajectory set, analyze the energy consumption distribution condition of candidate vehicle under different logistics trajectories in logistics trajectory set, analyze the carbon emission uncertainty degree of candidate vehicle under different logistics trajectories, and evaluate the carbon emission robustness of candidate vehicle in different logistics trajectories;Obtain target trajectory carbon emission data of different candidate vehicles, analyze the logistics matching degree of different candidate vehicles and target goods, determine target vehicle;Obtain target logistics trajectory of target vehicle, and according to target logistics trajectory, carry out logistics transportation to target goods, not only greatly reduce the carbon emission in the process of target goods transportation, but also take into account logistics efficiency, realize the true meaning of energy saving and environmental protection in the field of transportation.

Description

Technical Field

[0001] This invention relates to the field of logistics vehicle-cargo matching technology, specifically a logistics vehicle-cargo intelligent matching system and method based on carbon footprint. Background Technology

[0002] In the transportation industry, traditional vehicle-cargo matching only considers whether the vehicle type matches the cargo tonnage, fuel consumption, and transport distance, neglecting to consider the carbon emissions of vehicles during cargo transportation. This leads to inefficient fuel consumption and significant, avoidable emissions during actual cargo transport. Therefore, to address carbon emissions in logistics, current conventional vehicle-cargo matching methods primarily use digital platforms to match vehicles with cargo, thereby significantly reducing carbon emissions during cargo transport. However, current conventional vehicle-cargo matching... The method simply assumes that the carbon emissions of logistics vehicles during the transportation of goods are fixed, lacking consideration of the uncertainty of carbon emissions. It fails to take into account the uncertainty of carbon emissions of the same logistics vehicle during the transportation of goods, that is, the carbon emission performance of the same logistics vehicle on the same route may be different under different conditions. These uncertainties often lead to deviations between actual carbon emissions and predicted values. If decisions are made based solely on a single predicted value, it is very likely that a route that appears to be optimal on the surface may be chosen, but is actually accompanied by extremely high risks. This not only fails to effectively reduce carbon emissions during the logistics transportation process, but may even lead to excessive carbon emissions. Summary of the Invention

[0003] The purpose of this invention is to provide a carbon footprint-based intelligent matching system and method for logistics vehicles and goods, in order to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for intelligent matching of logistics vehicles and goods based on carbon footprint, the method comprising:

[0005] Step S1: Obtain vehicle feature data, obtain cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles;

[0006] Step S2: Generate the logistics trajectory of the candidate vehicle transporting the target goods, obtain the logistics trajectory set, obtain the historical logistics records of the candidate vehicle, analyze the energy consumption distribution of the candidate vehicle under different logistics trajectories in the logistics trajectory set, analyze the carbon emission uncertainty of the candidate vehicle under different logistics trajectories, and evaluate the carbon emission robustness of the candidate vehicle under different logistics trajectories to obtain the carbon emission data of the target trajectory.

[0007] Step S3: Obtain carbon emission data of target trajectories for different candidate vehicles, analyze the logistics matching degree between different candidate vehicles and target goods, and determine the target vehicle;

[0008] Step S4: Obtain the target logistics trajectory of the target vehicle, and transport the target goods according to the target logistics trajectory.

[0009] Furthermore, step S2 includes:

[0010] The location coordinates of the target cargo and its unloading point are obtained from the cargo feature data of the target cargo. The location coordinates of the candidate vehicles in the current period are obtained from the vehicle feature data. The logistics trajectories of the candidate vehicles transporting the target cargo are generated and aggregated to obtain the logistics trajectory set of the candidate vehicles transporting the target cargo.

[0011] The logistics trajectory is obtained from the logistics trajectory set, and each driving change point in the logistics trajectory is obtained. The road segment between any two adjacent driving change points in the logistics trajectory is recorded as the logistics segment of the logistics trajectory.

[0012] Obtain a pre-trained quantile energy consumption regression model, obtain data on various road segment attributes within the logistics route, obtain data on various vehicle indicators of candidate vehicles during their journey through the logistics route, use the quantile energy consumption regression model to obtain predicted values ​​of vehicle energy consumption at different quantiles of candidate vehicles in the logistics route, and construct the energy consumption quantile matrix of road segments in the logistics route.

[0013] Based on the energy consumption quantile matrix of the road segment, the mean and standard deviation of the predicted values ​​of vehicle energy consumption in the logistics segment are estimated to obtain the mean and standard deviation of energy consumption of the logistics segment.

[0014] Obtain adjacent road segments from the logistics trajectory, acquire historical logistics records of various features of the logistics segment and adjacent road segments, and calculate the energy consumption correlation coefficient ρ between the candidate vehicle and the logistics segment and adjacent road segments.

[0015] Obtain the carbon emission factor for each logistics segment in the logistics trajectory, and calculate the average carbon emission μ of candidate vehicles along the logistics trajectory. R Calculate the variance S of carbon emissions of candidate vehicles along the logistics trajectory. R Calculate the standard deviation of carbon emissions from logistics trajectories. ;

[0016] Calculate the robustness of carbon emissions of candidate vehicles in the logistics trajectory. Where λ represents the preset risk aversion coefficient;

[0017] Obtain the minimum value M of the robust carbon emission values ​​of candidate vehicles within each logistics trajectory in the logistics trajectory set. min and Mmin The corresponding logistics trajectory is recorded as the target logistics trajectory of the candidate vehicle. The target logistics trajectory and carbon emission robustness value of the candidate vehicle are obtained and aggregated to obtain the carbon emission data of the target trajectory.

[0018] The above steps transform the carbon emissions of candidate vehicles in the logistics trajectory from a fixed single value to a probability distribution, solving the problem of ignoring the uncertainty of carbon emissions in traditional carbon emission analysis. The final robust value of carbon emissions of candidate vehicles in the logistics trajectory not only clarifies how much carbon the candidate vehicles need to emit on average during the logistics transportation process, but also allows decision-makers to know the carbon emissions of candidate vehicles in the logistics trajectory under the worst-case scenario. This ensures that the target logistics trajectory of the finally selected candidate vehicles avoids the defects of local optima, not only improving the accuracy of low-carbon matching, but also endowing it with the ability to cope with complex real-world environments.

[0019] Furthermore, step S1 includes:

[0020] Obtain cargo characteristic data of the target cargo to be shipped within the current period from the logistics platform, obtain the cargo type of the target cargo, and obtain vehicles that have not been used for cargo transportation and are compatible with the cargo type of the target cargo from the logistics platform.

[0021] Obtain vehicle characteristic data of each vehicle that has not transported goods in the current period from the logistics platform, and obtain the maximum available transport mass and maximum available transport volume of the vehicle from the vehicle characteristic data;

[0022] Obtain the total mass G and total volume V of the target cargo from the cargo characteristic data. If the maximum usable transport mass and maximum usable transport volume of a certain vehicle are greater than the total mass and total volume of the target cargo, then the vehicle is reserved.

[0023] Calculate the load utilization rate of a vehicle. G´ represents the maximum available transport capacity of a vehicle in the current period;

[0024] Calculate the volume utilization rate of a vehicle. Where V´ is the maximum available transport volume of a certain vehicle in the current period;

[0025] Obtain the straight-line distance L' between a vehicle and the target cargo, obtain the straight-line distance L between the target cargo and its unloading point, and calculate the total straight-line distance of the vehicle transporting the target cargo. ;

[0026] Based on the load utilization rate f of a certain vehicle G The volume utilization rate f of a certain vehicle V Total distance L along the line sumCalculate the compatibility score A between a vehicle and the target cargo, set a score threshold a, and when A>a, determine the compatibility between the vehicle and the target cargo and record the vehicle as a candidate vehicle for the target cargo.

[0027] Furthermore, step S3 includes:

[0028] Obtain the target trajectory carbon emission data of each candidate vehicle for the target cargo, obtain the target logistics trajectory of the candidate vehicles from the target trajectory carbon emission data, and obtain the estimated logistics time for the candidate vehicles to transport the target cargo according to the target logistics trajectory.

[0029] The system obtains the time threshold and carbon emission threshold for the target cargo logistics. When the estimated logistics time of a candidate vehicle for the target cargo through the target logistics trajectory is less than the time threshold, and at the same time the carbon emission robustness value of a candidate vehicle in the target logistics trajectory is less than the carbon emission threshold, the candidate vehicle is retained. Otherwise, the candidate vehicle is removed from all candidate vehicles for the target cargo.

[0030] The robust carbon emission values ​​and estimated logistics times of each candidate vehicle for the target cargo in the target logistics trajectory are normalized, and the characteristic logistics cost U for transporting the target cargo by a candidate vehicle is calculated:

[0031] ,

[0032] Where, φ t Indicates the preset time weight; φ M Indicates the preset carbon emission weight; φ t >0, φ M >0, T represents the estimated logistics time for a candidate vehicle within the target logistics trajectory; M represents... △ This represents the robust carbon emission value for a candidate vehicle within the target logistics trajectory.

[0033] Obtain the minimum characteristic logistics cost U for transporting target goods by each candidate vehicle. min Obtain the minimum value U min The corresponding candidate vehicle will have the minimum value U min The corresponding candidate vehicles are matched to become the target vehicles for the logistics transportation of the target goods, and the target logistics trajectory of the target vehicles is obtained.

[0034] Furthermore, step S4 includes:

[0035] Obtain each candidate package of the target goods from the logistics platform, obtain the remaining number of uses of each candidate package in the current period, and take the candidate package corresponding to the maximum number of remaining uses as the target package of the target goods.

[0036] The system obtains the target vehicle and target logistics trajectory of the target goods, sends the target logistics trajectory to the driver of the target vehicle, packages the target goods using the target packaging, and prompts the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

[0037] To better implement the above methods, a carbon footprint-based intelligent matching system for logistics vehicles and goods is also proposed. The system includes a matching degree analysis module, a logistics trajectory carbon emission assessment module, a logistics matching analysis module, and a logistics transportation module.

[0038] The compatibility analysis module is used to acquire vehicle feature data of the vehicle and cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles.

[0039] The logistics trajectory carbon emission assessment module is used to assess the carbon emission robustness of candidate vehicles in different logistics trajectories and obtain carbon emission data for the target trajectory.

[0040] The logistics matching analysis module is used to acquire carbon emission data of target trajectories of different candidate vehicles, analyze the degree of logistics matching between different candidate vehicles and target goods, and determine the target vehicle.

[0041] The logistics and transportation module is used to transport target goods according to the target vehicle's target logistics trajectory.

[0042] Furthermore, the compatibility analysis module includes a vehicle screening unit and a compatibility analysis unit;

[0043] The vehicle screening unit is used to screen vehicles that have not transported goods in the current period based on the total mass and total volume of the target goods.

[0044] The fit analysis unit is used to calculate the fit score between each vehicle that has not transported goods in the current period and the target goods, and to analyze the fit between the vehicle and the target goods based on the fit score to obtain candidate vehicles.

[0045] Furthermore, the logistics trajectory carbon emission assessment module includes an energy consumption distribution analysis unit and a logistics trajectory carbon emission assessment unit;

[0046] The energy consumption distribution analysis unit is used to acquire the generated logistics trajectory set, acquire the historical logistics records of candidate vehicles, and analyze the energy consumption distribution of candidate vehicles under different logistics trajectories in the logistics trajectory set.

[0047] The logistics trajectory carbon emission assessment unit is used to analyze the uncertainty of carbon emissions of candidate vehicles under different logistics trajectories, assess the carbon emission robustness of candidate vehicles under different logistics trajectories, and obtain carbon emission data for the target trajectory.

[0048] Furthermore, the logistics matching analysis module includes a data acquisition unit and a logistics matching analysis unit;

[0049] The data acquisition unit is used to acquire the target trajectory carbon emission data of each candidate vehicle for the target cargo;

[0050] The logistics matching analysis unit is used to analyze the degree of logistics matching between different candidate vehicles and target goods based on the carbon emission data of each candidate vehicle's target trajectory, and to determine the target vehicle.

[0051] Furthermore, the logistics and transportation module includes logistics and transportation units;

[0052] The logistics and transportation unit is used to acquire the target packaging for the target goods, acquire the target vehicle and target logistics trajectory for the target goods, package the target goods using the target packaging, and prompt the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

[0053] Compared with existing technologies, the beneficial effects of this invention are as follows: By analyzing the matching degree between vehicles and target goods, candidate vehicles with transportation capacity suitable for the target goods are selected. By analyzing the energy consumption distribution of candidate vehicles under different logistics trajectories, the energy consumption of candidate vehicles at different quantiles when transporting target goods under logistics trajectories is determined. Furthermore, by analyzing the distribution of vehicle energy consumption, the uncertainty of carbon emissions of candidate vehicles under logistics trajectories is accurately grasped, thereby obtaining target logistics trajectories that balance carbon emission expectations and risks among candidate vehicles. In selecting candidate vehicles, not only carbon emissions during logistics transportation are considered, but also the impact of transportation timeliness is taken into account. Finally, packaging with a long service life and reusable packaging is selected as the target packaging for the target goods. This not only greatly reduces carbon emissions during the transportation of target goods, but also takes into account logistics efficiency, achieving true energy conservation and environmental protection in the field of transportation. Attached Figure Description

[0054] Figure 1 This is a flowchart of the target logistics trajectory acquisition process for a carbon footprint-based intelligent matching method for logistics vehicles and goods.

[0055] Figure 2 This is a flowchart of a module of a carbon footprint-based intelligent matching system for logistics vehicles and goods. Detailed Implementation

[0056] 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.

[0057] Example: Figures 1-2 As shown, this invention provides a technical solution: a method for intelligent matching of logistics vehicles and goods based on carbon footprint, the method comprising:

[0058] Step S1: Obtain vehicle feature data, obtain cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles;

[0059] Step S1 includes:

[0060] Obtain cargo characteristic data of the target cargo to be shipped within the current period from the logistics platform, obtain the cargo type of the target cargo, and obtain vehicles that have not been used for cargo transportation and are compatible with the cargo type of the target cargo from the logistics platform.

[0061] For example, if the type of goods that the vehicle has the capability to transport is the same as the type of goods for the target goods, then the vehicle is deemed to be compatible with the type of goods for the target goods.

[0062] Obtain vehicle characteristic data of each vehicle that has not transported goods in the current period from the logistics platform, and obtain the maximum available transport mass and maximum available transport volume of the vehicle from the vehicle characteristic data;

[0063] Obtain the total mass G and total volume V of the target cargo from the cargo characteristic data. If the maximum usable transport mass and maximum usable transport volume of a certain vehicle are greater than the total mass and total volume of the target cargo, then the vehicle is reserved.

[0064] Calculate the load utilization rate of a vehicle. G´ represents the maximum available transport capacity of a vehicle in the current period;

[0065] Calculate the volume utilization rate of a vehicle. Where V´ is the maximum available transport volume of a certain vehicle in the current period;

[0066] Obtain the straight-line distance L' between a vehicle and the target cargo, obtain the straight-line distance L between the target cargo and its unloading point, and calculate the total straight-line distance of the vehicle transporting the target cargo. ;

[0067] Based on the load utilization rate f of a certain vehicle G The volume utilization rate f of a certain vehicle V Total distance L along the line sum Calculate the compatibility score A between a vehicle and the target cargo, set a score threshold a, and when A>a, determine the compatibility between a vehicle and the target cargo and record the vehicle as a candidate vehicle for the target cargo.

[0068] For example, the specific process for calculating the compatibility score A between a vehicle and target cargo is as follows:

[0069] The load utilization rate f of a certain vehicle g The volume utilization rate f of a certain vehicle v Total distance L along the line sum After normalization, calculate the fit score A:

[0070] ,

[0071] Where, η G η V and η L These are the preset load factor, volume factor, and distance factor, respectively; η G η V and η L All are greater than 0 and their sum is 1.

[0072] Step S2: Generate the logistics trajectory of the candidate vehicle transporting the target goods, obtain the logistics trajectory set, obtain the historical logistics records of the candidate vehicle, analyze the energy consumption distribution of the candidate vehicle under different logistics trajectories in the logistics trajectory set, analyze the carbon emission uncertainty of the candidate vehicle under different logistics trajectories, and evaluate the carbon emission robustness of the candidate vehicle under different logistics trajectories to obtain the carbon emission data of the target trajectory.

[0073] Step S2 includes:

[0074] The location coordinates of the target cargo and its unloading point are obtained from the cargo feature data of the target cargo. The location coordinates of the candidate vehicles in the current period are obtained from the vehicle feature data. The logistics trajectories of the candidate vehicles transporting the target cargo are generated and aggregated to obtain the logistics trajectory set of the candidate vehicles transporting the target cargo.

[0075] For example, the specific process for generating the logistics trajectories of candidate vehicles transporting target goods is as follows:

[0076] The location coordinates of the candidate vehicle in the current cycle are set as the starting point, the location coordinates of the target cargo are set as the necessary route point, and the location coordinates of the unloading point of the target cargo are set as the ending point. Multiple logistics trajectories for the candidate vehicle to transport the target cargo are generated using the route planning interface of the map service provider.

[0077] The logistics trajectory is obtained from the logistics trajectory set, and each driving change point in the logistics trajectory is obtained. The road segment between any two adjacent driving change points in the logistics trajectory is recorded as the logistics road segment of the logistics trajectory.

[0078] For example, to obtain the points of change in the logistics trajectory, the specific process is as follows:

[0079] Set a unit distance, divide the logistics trajectory into several path feature points every unit distance, obtain the road segments between adjacent path feature points, and use them as the road segments within the path feature points closest to the starting point of adjacent recorded feature points.

[0080] Obtain the average vehicle speed within several path feature points from the map service provider, and calculate the speed change value C of the b-th path feature point in the logistics trajectory. b :

[0081] ,

[0082] Among them, v b v represents the average speed of the traffic flow within the b-th path feature point in the logistics trajectory; (b+1) This represents the average speed of the traffic flow within the (b+1)th path feature point in the logistics trajectory;

[0083] Obtain a pre-trained quantile energy consumption regression model, obtain data on various road segment attributes within the logistics route, obtain data on various vehicle indicators of candidate vehicles during their journey through the logistics route, use the quantile energy consumption regression model to obtain predicted values ​​of vehicle energy consumption at different quantiles of candidate vehicles in the logistics route, and construct the energy consumption quantile matrix of road segments in the logistics route.

[0084] For example, the various road attributes in a logistics route include the average slope of the road segment and the road segment type (such as expressway, national highway, and urban road).

[0085] For example, vehicle indicators include vehicle load capacity, cumulative mileage, and type of goods transported.

[0086] For example, the pre-training process of the quantile energy consumption regression model is as follows:

[0087] Obtain historical logistics records of other vehicles with the same vehicle model as the candidate vehicle; extract data on various road segment attributes of historical logistics segments from the historical logistics records; and extract data on vehicle indicators of other vehicles in historical logistics segments from the historical logistics records.

[0088] The data of various road attributes of historical logistics routes and vehicle indicators of other vehicles are used as input data for the quantile energy consumption regression model. The algorithm used in the quantile energy consumption regression model is the quantile regression forest algorithm.

[0089] For each input data point, the quantile energy consumption regression model outputs the predicted values ​​of vehicle energy consumption y at multiple quantiles, where the unit of vehicle energy consumption y is kg CO2 / km;

[0090] Among them, quantiles The output vector can be represented as:

[0091] ,

[0092] Among them, y τ This indicates that there is a probability τ that the vehicle energy consumption y of a vehicle will not exceed the predicted value;

[0093] Obtain the loss function in the quantile energy consumption regression model :

[0094] ,

[0095] Obtain historical logistics records of other vehicles of the same type as the candidate vehicle from the logistics platform, and divide each historical logistics record into a training set and a test set according to a preset ratio.

[0096] The quantile energy consumption regression model is trained using the training set and tested using the test set. The average loss of the quantile energy consumption regression model at each quantile is calculated and averaged to obtain the average quantile loss of the quantile energy consumption regression model. When the average quantile loss is less than the preset loss threshold, the quantile energy consumption regression model is considered to have completed training. Otherwise, the hyperparameters (number of trees, depth, learning rate, etc.) of the quantile energy consumption regression model are adjusted until the average quantile loss is less than the preset loss threshold.

[0097] For example, the process of constructing the energy consumption quantile matrix for a logistics route is as follows:

[0098] Several logistics segments in the logistics trajectory are obtained. The quantile energy consumption regression model is used to obtain the predicted values ​​of vehicle energy consumption at different quantiles of candidate vehicles in several logistics segments and aggregate them to obtain the segment energy consumption quantile matrix of the logistics trajectory.

[0099] Based on the energy consumption quantile matrix of the road segment, the mean and standard deviation of the predicted values ​​of vehicle energy consumption in the logistics segment are estimated to obtain the mean and standard deviation of energy consumption of the logistics segment.

[0100] For example, the process of estimating the average energy consumption of a logistics segment is as follows: obtain the predicted energy consumption of vehicles at the median quantile in the logistics segment from the segment energy consumption quantile matrix, and record it as the average energy consumption.

[0101] For example, the process for estimating the standard deviation of energy consumption in a logistics route is as follows:

[0102] When quantile At quantiles of 0.1 and 0.9, the predicted values ​​q of vehicle energy consumption in the logistics segment were obtained respectively. 0.1 and q 0.9 Obtain the 0.9 quantile Φ in the standard normal distribution. -1 (0.9), calculate the standard deviation of energy consumption σ´:

[0103] ,

[0104] Obtain adjacent road segments from the logistics trajectory, acquire historical logistics records of various features of the logistics segment and adjacent road segments, and calculate the energy consumption correlation coefficient ρ between the candidate vehicle and the logistics segment and adjacent road segments.

[0105] For example, the specific process for obtaining characteristic historical logistics records of logistics segments and adjacent segments is as follows:

[0106] Obtain historical logistics records of other vehicles that simultaneously pass through the logistics segment and adjacent segments from the logistics platform, and record them as characteristic historical logistics records. Among them, the other vehicles have the same vehicle model as the candidate vehicle.

[0107] For example, the specific calculation process for the energy consumption correlation coefficient ρ is as follows:

[0108] The average energy consumption of other vehicles in the logistics segment and adjacent segments of the logistics segment is obtained from the historical logistics records of each feature, and the energy consumption correlation coefficient ρ is calculated:

[0109] ,

[0110] Among them, Q i Let Q be the average energy consumption of other vehicles within the logistics segment in the historical logistics record of the i-th feature; Q is the mean of the average energy consumption of other vehicles within the logistics segment in the historical logistics records of each feature; Q (△,i) Let Q be the average energy consumption of other vehicles in adjacent road segments in the historical logistics records of the i-th feature; △ is the average energy consumption of other vehicles in adjacent road segments in the historical logistics records of each feature; j is the total number of historical logistics records for each feature;

[0111] Obtain the carbon emission factor for each logistics segment in the logistics trajectory, and calculate the average carbon emission μ of candidate vehicles along the logistics trajectory. R Calculate the variance S of carbon emissions of candidate vehicles along the logistics trajectory. R Calculate the standard deviation of carbon emissions from logistics trajectories. ;

[0112] For example, carbon emission factor refers to the amount of carbon dioxide emitted by a vehicle for consuming a unit of fuel or energy on a road segment, and its unit is kg CO2 / L or kg CO2 / kg;

[0113] For example, the average carbon emissions μ R The specific formula is as follows:

[0114] ,

[0115] Where, γ x μ represents the carbon emission factor of the x-th logistics segment in the logistics trajectory. x This represents the average energy consumption of the candidate vehicle in the x-th logistics segment; k is the total number of logistics segments in the logistics trajectory.

[0116] For example, the variance of carbon emissions S R The specific calculation formula is as follows:

[0117] ,

[0118] Where, γ z γ represents the carbon emission factor of the z-th logistics segment in the logistics trajectory; z+1 ρ represents the carbon emission factor of the (z+1)th logistics segment in the logistics trajectory. z σ represents the energy consumption correlation coefficient between the z-th logistics segment and the (z+1)-th logistics segment; z σ represents the standard deviation of energy consumption of candidate vehicles in the z-th logistics segment; z+1 This represents the standard deviation of energy consumption of the candidate vehicle in the (z+1)th logistics segment.

[0119] Calculate the robustness of carbon emissions of candidate vehicles in the logistics trajectory. Where λ represents the preset risk aversion coefficient;

[0120] For example, λ represents the risk aversion coefficient, which is a preset value. The higher the decision-maker's risk aversion, the more they value the standard deviation, and the larger the value of λ is, λ≥0;

[0121] Obtain the minimum value M of the robust carbon emission values ​​of candidate vehicles within each logistics trajectory in the logistics trajectory set. min and M minThe corresponding logistics trajectory is recorded as the target logistics trajectory of the candidate vehicle. The target logistics trajectory and carbon emission robustness value of the candidate vehicle are obtained and aggregated to obtain the carbon emission data of the target trajectory.

[0122] Step S3: Obtain carbon emission data of target trajectories for different candidate vehicles, analyze the logistics matching degree between different candidate vehicles and target goods, and determine the target vehicle;

[0123] Step S3 includes:

[0124] Obtain the target trajectory carbon emission data of each candidate vehicle for the target cargo, obtain the target logistics trajectory of the candidate vehicles from the target trajectory carbon emission data, and obtain the estimated logistics time for the candidate vehicles to transport the target cargo according to the target logistics trajectory.

[0125] For example, the target logistics trajectory of the candidate vehicle is input into the map software of the map service provider to obtain the estimated logistics time for the candidate vehicle to transport the target goods according to the target logistics trajectory.

[0126] The system obtains the time threshold and carbon emission threshold for the target cargo logistics. When the estimated logistics time of a candidate vehicle for the target cargo through the target logistics trajectory is less than the time threshold, and at the same time the carbon emission robustness value of a candidate vehicle in the target logistics trajectory is less than the carbon emission threshold, the candidate vehicle is retained. Otherwise, the candidate vehicle is removed from all candidate vehicles for the target cargo.

[0127] The robust carbon emission values ​​and estimated logistics times of each candidate vehicle for the target cargo in the target logistics trajectory are normalized, and the characteristic logistics cost U for transporting the target cargo by a candidate vehicle is calculated:

[0128] ,

[0129] Where, φ t Indicates the preset time weight; φ M Indicates the preset carbon emission weight; φ t >0, φ M >0, T represents the estimated logistics time for a candidate vehicle within the target logistics trajectory; M represents... △ This represents the robust carbon emission value for a candidate vehicle within the target logistics trajectory.

[0130] For example, the process of normalizing the robust carbon emission values ​​of each candidate vehicle for the target cargo along the target logistics trajectory is as follows:

[0131] Obtain the maximum value M of the carbon emission robustness of each candidate vehicle for the target cargo along the target logistics trajectory. max and minimum value Mmin Obtain the robust carbon emission value M' of a candidate vehicle in the target logistics trajectory, and normalize the robust carbon emission value M' to obtain M. △ , of which M △ The specific formula is as follows:

[0132] ,

[0133] For example, the process of normalizing the estimated logistics time of each candidate vehicle for the target goods in the target logistics trajectory is as follows:

[0134] Obtain the maximum estimated delivery time T for each candidate vehicle carrying the target cargo within the target logistics trajectory. max and minimum value T min To obtain the estimated logistics time T´ of a candidate vehicle in the target logistics trajectory, normalize the estimated logistics time T´ to obtain T, where the specific formula for T is:

[0135] ,

[0136] Obtain the minimum characteristic logistics cost U for transporting target goods by each candidate vehicle. min Obtain the minimum value U min The corresponding candidate vehicle will have the minimum value U min The corresponding candidate vehicles are matched as target vehicles for the logistics transportation of the target goods, and the target logistics trajectory of the target vehicles is obtained.

[0137] Step S4: Obtain the target logistics trajectory of the target vehicle, and transport the target goods according to the target logistics trajectory;

[0138] Step S4 includes:

[0139] Obtain each candidate package of the target goods from the logistics platform, obtain the remaining number of uses of each candidate package in the current period, and take the candidate package corresponding to the maximum number of remaining uses as the target package of the target goods.

[0140] The system obtains the target vehicle and target logistics trajectory of the target goods, sends the target logistics trajectory to the driver of the target vehicle, packages the target goods using the target packaging, and prompts the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

[0141] To better implement the above methods, a carbon footprint-based intelligent matching system for logistics vehicles and goods is also proposed. The system includes a matching degree analysis module, a logistics trajectory carbon emission assessment module, a logistics matching analysis module, and a logistics transportation module.

[0142] The compatibility analysis module is used to acquire vehicle feature data of the vehicle and cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles.

[0143] The logistics trajectory carbon emission assessment module is used to assess the carbon emission robustness of candidate vehicles in different logistics trajectories and obtain carbon emission data for the target trajectory.

[0144] The logistics matching analysis module is used to acquire carbon emission data of target trajectories of different candidate vehicles, analyze the degree of logistics matching between different candidate vehicles and target goods, and determine the target vehicle.

[0145] The logistics and transportation module is used to transport target goods according to the target vehicle's target logistics trajectory.

[0146] The compatibility analysis module includes a vehicle screening unit and a compatibility analysis unit.

[0147] The vehicle screening unit is used to screen vehicles that have not transported goods in the current period based on the total mass and total volume of the target goods.

[0148] The fit analysis unit is used to calculate the fit score between each vehicle that has not transported goods in the current period and the target goods, and to analyze the fit between the vehicle and the target goods based on the fit score to obtain candidate vehicles.

[0149] The logistics trajectory carbon emission assessment module includes an energy consumption distribution analysis unit and a logistics trajectory carbon emission assessment unit.

[0150] The energy consumption distribution analysis unit is used to acquire the generated logistics trajectory set, acquire the historical logistics records of candidate vehicles, and analyze the energy consumption distribution of candidate vehicles under different logistics trajectories in the logistics trajectory set.

[0151] The logistics trajectory carbon emission assessment unit is used to analyze the uncertainty of carbon emissions of candidate vehicles under different logistics trajectories, assess the carbon emission robustness of candidate vehicles under different logistics trajectories, and obtain carbon emission data for the target trajectory.

[0152] The logistics matching analysis module includes a data acquisition unit and a logistics matching analysis unit.

[0153] The data acquisition unit is used to acquire the target trajectory carbon emission data of each candidate vehicle for the target cargo;

[0154] The logistics matching analysis unit is used to analyze the degree of logistics matching between different candidate vehicles and target goods based on the carbon emission data of each candidate vehicle's target trajectory, and to determine the target vehicle.

[0155] The logistics and transportation module includes logistics and transportation units;

[0156] The logistics and transportation unit is used to acquire the target packaging for the target goods, acquire the target vehicle and target logistics trajectory for the target goods, package the target goods using the target packaging, and prompt the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

[0157] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for intelligent matching of logistics vehicles and goods based on carbon footprint, characterized in that, The method includes: Step S1: Obtain vehicle feature data, obtain cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles; Step S2: Generate the logistics trajectory of the candidate vehicle transporting the target goods, obtain the logistics trajectory set, obtain the historical logistics records of the candidate vehicle, analyze the energy consumption distribution of the candidate vehicle under different logistics trajectories in the logistics trajectory set, analyze the carbon emission uncertainty of the candidate vehicle under different logistics trajectories, and evaluate the carbon emission robustness of the candidate vehicle under different logistics trajectories to obtain the carbon emission data of the target trajectory. Step S3: Obtain carbon emission data of target trajectories for different candidate vehicles, analyze the logistics matching degree between different candidate vehicles and target goods, and determine the target vehicle; Step S4: Obtain the target logistics trajectory of the target vehicle, and transport the target goods according to the target logistics trajectory; Step S2 includes: The location coordinates of the target cargo and its unloading point are obtained from the cargo feature data of the target cargo. The location coordinates of the candidate vehicles in the current period are obtained from the vehicle feature data. The logistics trajectories of the candidate vehicles transporting the target cargo are generated and aggregated to obtain the logistics trajectory set of the candidate vehicles transporting the target cargo. The logistics trajectory is obtained from the logistics trajectory set, and each driving change point in the logistics trajectory is obtained. The road segment between any two adjacent driving change points in the logistics trajectory is recorded as the logistics road segment of the logistics trajectory. Obtain a pre-trained quantile energy consumption regression model, obtain data on various road segment attributes within the logistics route, obtain data on various vehicle indicators of candidate vehicles during their journey through the logistics route, use the quantile energy consumption regression model to obtain predicted values ​​of vehicle energy consumption at different quantiles of candidate vehicles in the logistics route, and construct the energy consumption quantile matrix of road segments in the logistics route. Based on the energy consumption quantile matrix of the road segment, the mean and standard deviation of the predicted values ​​of vehicle energy consumption in the logistics segment are estimated to obtain the mean and standard deviation of energy consumption of the logistics segment. Obtain adjacent road segments from the logistics trajectory, acquire historical logistics records of various features of the logistics segment and adjacent road segments, and calculate the energy consumption correlation coefficient ρ between the candidate vehicle and the logistics segment and adjacent road segments. Obtain the carbon emission factor for each logistics segment in the logistics trajectory, and calculate the average carbon emission μ of candidate vehicles along the logistics trajectory. R Calculate the variance S of carbon emissions of candidate vehicles along the logistics trajectory. R Calculate the standard deviation of carbon emissions from logistics trajectories. ; Calculate the robustness of carbon emissions of candidate vehicles in the logistics trajectory. Where λ represents the preset risk aversion coefficient; Obtain the minimum value M of the robust carbon emission values ​​of candidate vehicles within each logistics trajectory in the logistics trajectory set. min and M min The corresponding logistics trajectory is recorded as the target logistics trajectory of the candidate vehicle. The target logistics trajectory and carbon emission robustness value of the candidate vehicle are obtained and aggregated to obtain the carbon emission data of the target trajectory.

2. The intelligent matching method for logistics vehicles and goods based on carbon footprint according to claim 1, characterized in that, Step S1 includes: Obtain cargo characteristic data of the target cargo to be shipped within the current period from the logistics platform, obtain the cargo type of the target cargo, and obtain vehicles that have not been used for cargo transportation and are compatible with the cargo type of the target cargo from the logistics platform. Obtain vehicle characteristic data of each vehicle that has not transported goods in the current period from the logistics platform, and obtain the maximum available transport mass and maximum available transport volume of the vehicle from the vehicle characteristic data; Obtain the total mass G and total volume V of the target cargo from the cargo characteristic data. If the maximum usable transport mass and maximum usable transport volume of a certain vehicle are greater than the total mass and total volume of the target cargo, then the vehicle is reserved. Calculate the load utilization rate of a vehicle. G´ represents the maximum available transport capacity of a vehicle in the current period; Calculate the volume utilization rate of a vehicle. Where V´ is the maximum available transport volume of a certain vehicle in the current period; Obtain the straight-line distance L' between a vehicle and the target cargo, obtain the straight-line distance L between the target cargo and its unloading point, and calculate the total straight-line distance of the vehicle transporting the target cargo. ; Based on the load utilization rate f of a certain vehicle G The volume utilization rate f of a certain vehicle V Total distance L along the line sum Calculate the compatibility score A between a vehicle and the target cargo, set a score threshold a, and when A>a, determine the compatibility between the vehicle and the target cargo and record the vehicle as a candidate vehicle for the target cargo.

3. The intelligent matching method for logistics vehicles and goods based on carbon footprint as described in claim 1, characterized in that, Step S3 includes: Obtain the target trajectory carbon emission data of each candidate vehicle for the target cargo, obtain the target logistics trajectory of the candidate vehicles from the target trajectory carbon emission data, and obtain the estimated logistics time for the candidate vehicles to transport the target cargo according to the target logistics trajectory. The system obtains the time threshold and carbon emission threshold for the target cargo logistics. When the estimated logistics time of a candidate vehicle for the target cargo through the target logistics trajectory is less than the time threshold, and at the same time the carbon emission robustness value of a candidate vehicle in the target logistics trajectory is less than the carbon emission threshold, the candidate vehicle is retained. Otherwise, the candidate vehicle is removed from all candidate vehicles for the target cargo. The robust carbon emission values ​​and estimated logistics times of each candidate vehicle for the target cargo in the target logistics trajectory are normalized, and the characteristic logistics cost U for transporting the target cargo by a candidate vehicle is calculated: ， Where, φ t Indicates the preset time weight; φ M Indicates the preset carbon emission weight; φ t >0, φ M >0, T represents the estimated logistics time for a candidate vehicle within the target logistics trajectory; M represents... △ This represents the robust carbon emission value for a candidate vehicle within the target logistics trajectory. Obtain the minimum characteristic logistics cost U for transporting target goods by each candidate vehicle. min Obtain the minimum value U min The corresponding candidate vehicle will have the minimum value U min The corresponding candidate vehicles are matched as target vehicles for the logistics transportation of the target goods, and the target logistics trajectory of the target vehicles is obtained.

4. The intelligent matching method for logistics vehicles and goods based on carbon footprint as described in claim 1, characterized in that, Step S4 includes: Obtain each candidate package of the target goods from the logistics platform, obtain the remaining number of uses of each candidate package in the current period, and take the candidate package corresponding to the maximum number of remaining uses as the target package of the target goods. The system obtains the target vehicle and target logistics trajectory of the target goods, sends the target logistics trajectory to the driver of the target vehicle, packages the target goods using the target packaging, and prompts the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

5. A carbon footprint-based intelligent vehicle-cargo matching system for logistics, used to execute the carbon footprint-based intelligent vehicle-cargo matching method according to any one of claims 1-4, characterized in that, The system includes an adaptation analysis module, a logistics trajectory carbon emission assessment module, a logistics matching analysis module, and a logistics transportation module. The compatibility analysis module is used to acquire vehicle feature data of the vehicle, acquire cargo feature data of the target cargo, analyze the compatibility between the vehicle and the target cargo, and obtain candidate vehicles. The logistics trajectory carbon emission assessment module is used to assess the carbon emission robustness of candidate vehicles in different logistics trajectories and obtain carbon emission data for the target trajectory. The logistics matching analysis module is used to acquire carbon emission data of target trajectories of different candidate vehicles, analyze the degree of logistics matching between different candidate vehicles and target goods, and determine the target vehicle. The logistics transportation module is used to transport target goods according to the target logistics trajectory of the target vehicle.

6. The intelligent vehicle-cargo matching system based on carbon footprint according to claim 5, characterized in that, The compatibility analysis module includes a vehicle screening unit and a compatibility analysis unit. The vehicle screening unit is used to screen vehicles that have not transported goods in the current period based on the total mass and total volume of the target goods. The adaptation analysis unit is used to calculate the adaptation score between each vehicle that has not transported goods in the current period and the target goods, and to analyze the adaptation score to obtain candidate vehicles.

7. A carbon footprint-based intelligent vehicle-cargo matching system for logistics according to claim 5, characterized in that, The logistics trajectory carbon emission assessment module includes an energy consumption distribution analysis unit and a logistics trajectory carbon emission assessment unit. The energy consumption distribution analysis unit is used to acquire the generated logistics trajectory set, acquire the historical logistics records of candidate vehicles, and analyze the energy consumption distribution of candidate vehicles under different logistics trajectories in the logistics trajectory set. The logistics trajectory carbon emission assessment unit is used to analyze the uncertainty of carbon emissions of candidate vehicles under different logistics trajectories, assess the carbon emission robustness of candidate vehicles under different logistics trajectories, and obtain carbon emission data for the target trajectory.

8. A carbon footprint-based intelligent vehicle-cargo matching system for logistics according to claim 5, characterized in that, The logistics matching and analysis module includes a data acquisition unit and a logistics matching and analysis unit; The data acquisition unit is used to acquire the target trajectory carbon emission data of each candidate vehicle for the target cargo. The logistics matching analysis unit is used to analyze the degree of logistics matching between different candidate vehicles and target goods based on the carbon emission data of each candidate vehicle's target trajectory, and to determine the target vehicle.

9. A carbon footprint-based intelligent vehicle-cargo matching system for logistics according to claim 5, characterized in that, The logistics transportation module includes a logistics transportation unit; The logistics transportation unit is used to acquire the target packaging for the target goods logistics transportation, acquire the target vehicle and target logistics trajectory of the target goods, package the target goods using the target packaging, and prompt the driver of the target vehicle to transport the target goods according to the target logistics trajectory through the logistics platform.

Images