Data Matching Methods and Systems for Logistics Freight Platforms Based on Big Data

Abstract

This invention relates to the field of industrial process control, specifically to a data matching method and system for a logistics freight platform based on big data. The method first examines the transportation routes selected by each logistics vehicle in its historical transportation processes and the historical transportation time along those routes. Based on the frequency and duration of the same transportation route selected by each logistics vehicle in various historical transportation processes, the current transportation route is determined. The feasibility of the current transportation route is analyzed, and logistics vehicles requiring route adjustments are selected. Multiple feasible transportation routes for each logistics vehicle to be adjusted are determined, along with suitable indicators for each feasible route. Furthermore, the priority of each logistics vehicle to be adjusted is analyzed during route adjustment. Based on the priority of the logistics vehicles to be adjusted and the suitable indicators of each feasible transportation route, the transportation routes of each logistics vehicle to be adjusted are matched and adjusted. This invention can accurately adjust the transportation routes of logistics vehicles in real time, improving the effectiveness of route planning and matching.

Description

Technical Field

[0001] This invention relates to the field of industrial process control, and more specifically to a data matching method and system for a logistics and freight platform based on big data. Background Technology

[0002] For integrated logistics hubs, in order to improve the efficiency of logistics cargo transportation, data matching is usually based on logistics transportation platforms. It is necessary to dynamically match suitable transportation routes for logistics vehicles according to specific freight demands, so as to achieve accurate route planning and matching, reduce congestion, and improve transportation efficiency.

[0003] In existing technologies, logistics vehicles are typically matched with appropriate transportation routes based on their historical transportation route information to avoid congestion. However, in actual logistics transportation, the actual road conditions can change dynamically, such as traffic accidents or maintenance incidents on certain road sections. This makes it impossible for existing methods to accurately adjust the transportation routes of logistics vehicles in real time, thereby reducing the effectiveness of route planning and matching. Summary of the Invention

[0004] To address the technical problem that existing methods cannot accurately adjust the transportation routes of logistics vehicles in real time, thus reducing the effectiveness of route planning and matching, the present invention aims to provide a data matching method and system for logistics freight platforms based on big data. The specific technical solution adopted is as follows:

[0005] This invention proposes a data matching method for logistics and freight platforms based on big data, the method comprising:

[0006] The system obtains the transportation route selected by each logistics vehicle in each historical transportation process within a preset time period and the historical transportation duration on the transportation route. The roadside unit of each segment of the transportation route records traffic flow and emergency information in real time.

[0007] Taking any logistics vehicle as the target logistics vehicle, the current transportation route of the target logistics vehicle is obtained based on the number of times the target logistics vehicle has selected the same transportation route in each historical transportation process and the historical transportation duration. During the transportation of the target logistics vehicle on the current transportation route, the route feasibility index of the target logistics vehicle at the current moment is obtained based on the number of times the roadside units of the road segment that the target logistics vehicle has passed through in the historical transportation process appeared in the selected transportation routes, as well as the traffic flow and emergency event information of the roadside units of the road segments that have not been passed. Based on the route feasibility index, logistics vehicles that need to be adjusted are selected from all logistics vehicles.

[0008] Take any one of the logistics vehicles to be adjusted as the target logistics vehicle to be adjusted. Based on the route feasibility index of the target logistics vehicle to be adjusted at the current time, obtain multiple feasible transportation routes for the target logistics vehicle to be adjusted at the current time. Based on the historical transportation time and length of each feasible transportation route, obtain the suitability index of each feasible transportation route. Based on the suitability index of each feasible transportation route and the number of feasible transportation routes, obtain the adjustment priority of the target logistics vehicle to be adjusted.

[0009] The transportation route of each logistics vehicle to be adjusted is matched and adjusted according to the adjustment priority of each logistics vehicle to be adjusted and the suitability index of each feasible transportation route of each logistics vehicle to be adjusted at the current time.

[0010] Furthermore, obtaining the current transportation route of the target logistics vehicle includes:

[0011] The ratio of the number of times the target logistics vehicle selected the same transportation route in all historical transportation processes is used as the numerator, and the number of times the target logistics vehicle selected the same transportation route in all historical transportation processes is used as the denominator. The ratio is used as the frequency value of the target logistics vehicle's selection of each transportation route.

[0012] By performing a negative correlation mapping on the average historical transportation time of the target logistics vehicle on the same transportation route in all historical transportation processes, the transportation timeliness value of the target logistics vehicle on each transportation route can be obtained.

[0013] By combining the selection frequency value and the transportation timeliness value, the optimal selection degree of the target logistics vehicle on each transportation route is obtained;

[0014] The transportation path corresponding to the maximum value of the optimization degree is taken as the current transportation path of the target logistics vehicle.

[0015] Furthermore, the feasibility indicators for obtaining the target logistics vehicle's path at the current moment include:

[0016] Among all the transportation routes selected by the target logistics vehicle in all historical transportation processes other than the current transportation route, multiple reference transportation routes are selected for the current transportation route. The starting point of the reference transportation route is the same as the starting point of the current transportation route, and the ending point of the reference transportation route is the same as the ending point of the current transportation route.

[0017] The sequence of roadside units formed by the roadside units of the target logistics vehicle in each reference transportation route within a preset time period is used as the reference roadside unit sequence for each reference transportation route.

[0018] In the current transportation route, the sequence of roadside units that transport the target logistics vehicle to the road segment it passes through at the current moment is taken as the current roadside unit sequence of the target logistics vehicle at the current moment.

[0019] Take the current roadside unit sequence or any reference roadside unit sequence as the target sequence, and extract all continuous subsequences of the target sequence, wherein the number of elements in the continuous subsequence is greater than the value 1;

[0020] The numerator is the number of times each continuous subsequence of the current roadside unit sequence appears in each continuous subsequence of the reference roadside unit sequence, and the denominator is the number of each continuous subsequence of the reference roadside unit sequence. The ratio is used as the repeatability parameter of the current roadside unit sequence in each reference roadside unit sequence. The average of the repeatability parameters of the current roadside unit sequence in all reference roadside unit sequences is used as the first feasibility coefficient of the target logistics vehicle at the current moment.

[0021] During the transportation of the target logistics vehicle along the current transportation route, the number of roadside units on the road segment that the target logistics vehicle has not yet passed at the current time and that have the information of the sudden event is used as the reference number of the target logistics vehicle at the current time. The average traffic flow of the roadside units on all road segments that the target logistics vehicle has not yet passed at the current time is used as the reference traffic flow of the target logistics vehicle at the current time. The reference number and the reference traffic flow are combined and negatively correlated to obtain the second feasibility coefficient of the target logistics vehicle at the current time.

[0022] The first feasibility coefficient and the second feasibility coefficient are combined and normalized to obtain the path feasibility index of the target logistics vehicle at the current moment.

[0023] Furthermore, the process of selecting the logistics vehicles to be adjusted from all logistics vehicles includes:

[0024] Logistics vehicles whose route feasibility index is less than the preset feasibility threshold are designated as logistics vehicles to be adjusted.

[0025] Furthermore, the multiple feasible transportation routes for the target logistics vehicle to be adjusted at the current moment include:

[0026] Based on the path feasibility index of the target logistics vehicle to be adjusted at the current moment, the pheromone concentration in the ant colony algorithm is adjusted to obtain the adjusted pheromone concentration for each segment of each transportation path.

[0027] Using the roadside units of each road segment as nodes, and the roadside unit of the current road segment where the target logistics vehicle to be adjusted is transported as the initial node, the ant colony algorithm is used, and based on the adjustment pheromone concentration of each road segment in each transportation path, multiple feasible transportation paths of the target logistics vehicle to be adjusted at the current time are obtained.

[0028] Furthermore, obtaining the adjusted pheromone concentration for each segment of each transportation path includes:

[0029] The product of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the path feasibility index of the target logistics vehicle at the current moment is used as the concentration adjustment amount for each segment in each transportation path.

[0030] The sum of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the concentration adjustment amount is used as the adjusted pheromone concentration of each segment in each transportation path.

[0031] Furthermore, the appropriate indicators for obtaining each feasible transportation route include:

[0032] Any feasible transportation route is taken as the target feasible transportation route, and the average value of the adjusted pheromone concentration of all segments in the target feasible transportation route is taken as the first suitability coefficient of the target feasible transportation route.

[0033] The average historical transportation time of all logistics vehicles on the target feasible transportation route during all historical transportation processes within the preset time period and the length of the target feasible transportation route are combined and negatively correlated to obtain the second suitability coefficient of the target feasible transportation route.

[0034] The first suitability coefficient and the second suitability coefficient of the target feasible transportation route are combined and normalized to obtain the suitability index of the target feasible transportation route.

[0035] Furthermore, the adjustment priority of the target logistics vehicle to be adjusted includes:

[0036] The numerator is the average of the number of feasible transportation routes for all the logistics vehicles to be adjusted at the current moment, and the denominator is the number of feasible transportation routes for the target logistics vehicle to be adjusted at the current moment. The ratio is used as the first priority of the target logistics vehicle to be adjusted.

[0037] The difference between the planned arrival time and the current time of the target logistics vehicle to be adjusted is used as the remaining time of the order for the target logistics vehicle to be adjusted. The average value of the suitability index of all feasible transportation routes of the target logistics vehicle to be adjusted at the current time is used as the overall suitability index of the target logistics vehicle to be adjusted. The remaining time of the order and the overall suitability index are combined and negatively correlated to obtain the second priority of the target logistics vehicle to be adjusted.

[0038] The first priority and the second priority are combined and normalized to obtain the adjustment priority of the target logistics vehicle to be adjusted.

[0039] Furthermore, the matching and adjustment of the transportation route for each logistics vehicle to be adjusted includes:

[0040] The adjustment priorities of each logistics vehicle to be adjusted are sorted in descending order. Starting from the maximum adjustment priority, each logistics vehicle to be adjusted is moved to the feasible transportation route corresponding to the maximum value of the appropriate index of that logistics vehicle.

[0041] The present invention also proposes a data matching system for a logistics freight platform based on big data. The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of any one of the data matching methods for a logistics freight platform based on big data.

[0042] The present invention has the following beneficial effects:

[0043] This invention addresses the limitation of existing methods in accurately adjusting the transportation routes of logistics vehicles in real time, thus reducing the effectiveness of route planning and matching. First, it determines the current transportation route of the target logistics vehicle based on the number of times the same route was selected and the historical transportation duration in each historical transportation process, ensuring high transportation efficiency on the current route. Since road conditions on different sections of the current transportation route may dynamically change during actual transportation, potentially affecting the transportation efficiency, this invention first uses a route feasibility index to reflect the passability of the target logistics vehicle's current transportation route at the current moment. The system uses route feasibility indicators to determine whether the current transportation route is still suitable for the target logistics vehicle at the current moment. This allows for the selection of logistics vehicles requiring route adjustments, and the identification of feasible transportation routes for these vehicles. Furthermore, suitability indicators are used to evaluate the suitability of each feasible transportation route for the logistics vehicles to be adjusted. Adjustment priorities are then used to reflect the priority of route adjustments for each logistics vehicle. Combining the suitability indicators of the logistics vehicles on feasible transportation routes, routes are adjusted for the logistics vehicles according to different priorities to avoid congestion after adjustments and improve the transportation efficiency of the logistics vehicles. Attached Figure Description

[0044] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1This is a flowchart of a data matching method for a logistics freight platform based on big data, provided as an embodiment of the present invention. Detailed Implementation

[0046] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of a data matching method and system for a logistics freight platform based on big data proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0048] The following description, in conjunction with the accompanying drawings, details the specific solution of a data matching method and system for a logistics freight platform based on big data provided by this invention.

[0049] Please see Figure 1 The diagram illustrates a flowchart of a data matching method for a logistics freight platform based on big data, according to an embodiment of the present invention. The method includes:

[0050] Step S1: Obtain the transportation route selected by each logistics vehicle in each historical transportation process within a preset time period and the historical transportation duration on the transportation route. The roadside unit of each segment of the transportation route records traffic flow and emergency information in real time.

[0051] This invention first collects data from a logistics freight platform, including the selected transportation routes and historical transportation durations of each logistics vehicle during each historical transportation process within a preset time period. Each transportation route includes multiple road segments, and roadside units (RSUs) are installed on each segment. The RSUs can interact with the onboard units (OBUs) of the logistics vehicles, enabling the OBUs to record the transportation routes of the logistics vehicles. Simultaneously, the RSUs can also record the traffic flow and emergency information of their respective road segments in real time. Emergency information refers to events such as traffic accidents or ongoing construction and maintenance on a certain road segment. The RSUs on that road segment can record these emergencies, and once the emergencies on that road segment are resolved, the corresponding emergency information recorded by the RSUs is also deleted.

[0052] The preset time period is set to 2 years. The specific value of the preset time period can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0053] Step S2: Select any logistics vehicle as the target logistics vehicle. Based on the number of times the target logistics vehicle has selected the same transportation route in each historical transportation process and the historical transportation duration, obtain the current transportation route of the target logistics vehicle. During the transportation of the target logistics vehicle on the current transportation route, based on the number of times the roadside units of the road segment that the target logistics vehicle has passed through at the current time appear in the transportation routes selected in the historical transportation process, as well as the traffic flow and emergency event information of the roadside units of the road segments that have not been passed, obtain the route feasibility index of the target logistics vehicle at the current time. Based on the route feasibility index, select the logistics vehicles to be adjusted from all logistics vehicles.

[0054] In the actual transportation process of logistics vehicles, the first step is to select a suitable transportation route. Since different logistics vehicles have different requirements for transportation routes, this embodiment of the invention first takes any logistics vehicle as the target logistics vehicle. The more times the target logistics vehicle selects the same transportation route in each historical transportation process, and the shorter the historical transportation time on the same transportation route, the more suitable the transportation route is for the target logistics vehicle. Therefore, the current transportation route of the target logistics vehicle can be initially selected based on the number of times the target logistics vehicle selects the same transportation route in each historical transportation process and the historical transportation time, thereby ensuring that the transportation efficiency of the target logistics vehicle on the current transportation route is relatively high.

[0055] Preferably, in one embodiment of the present invention, the method for obtaining the current transportation route of the target logistics vehicle specifically includes:

[0056] The ratio of the number of times the target logistics vehicle selected the same transportation route in all historical transportation processes is used as the numerator, and the number of all historical transportation processes of the target logistics vehicle is used as the denominator. The ratio is used as the selection frequency value of the target logistics vehicle for each transportation route. The higher the selection frequency value of a transportation route, the more frequently the target logistics vehicle selects that transportation route, and thus the more suitable that transportation route is for the target logistics vehicle.

[0057] The shorter the historical transport time of the target logistics vehicle on the transport route, the higher the transport efficiency of the target logistics vehicle on that transport route, and the more suitable the transport route is for the target logistics vehicle. Therefore, the average historical transport time of the target logistics vehicle on the same transport route in all historical transport processes can be negatively correlated to obtain the transport timeliness value of the target logistics vehicle on each transport route.

[0058] Furthermore, the selection frequency value and transportation timeliness value can be combined to obtain the optimality of the target logistics vehicle on each transportation route. The higher the optimality of a transportation route, the more suitable the transportation route is for the target logistics vehicle. Therefore, the target logistics vehicle should prioritize the transportation route for cargo transportation. Thus, the transportation route corresponding to the maximum optimality can be used as the current transportation route of the target logistics vehicle.

[0059] In embodiments of the present invention, the sum or product of the selected frequency value and the transportation timeliness value can be calculated to achieve the integration of the two, which is not limited here. Furthermore, the same method can be used in subsequent steps to achieve the integrated processing of more than two data, which will not be elaborated further.

[0060] As an example, in one embodiment of the present invention, the expression for the degree of preference of the target logistics vehicle on each transportation route can be specifically as follows:

[0061]

[0062] Among them, A i This indicates the optimality of the target logistics vehicle on the i-th transportation route; b i B represents the number of times the target logistics vehicle selected the i-th transportation route in all historical transportation processes; B represents the number of all historical transportation processes of the target logistics vehicle. μ represents the frequency with which the target logistics vehicle selects the i-th transportation route. i This represents the average historical transport time of the target logistics vehicle on the i-th transport route throughout all historical transport processes; This represents the delivery time value of the target logistics vehicle on the i-th transportation route.

[0063] It should be noted that negative correlation mapping can also be achieved through other basic mathematical operations in other embodiments of the present invention, which will not be elaborated here.

[0064] The current transport route of each logistics vehicle can be determined using the same method described above. Each vehicle can then transport goods along its designated route. However, in actual transport, the conditions and environmental factors of the current transport route are difficult to predict accurately. For example, the target logistics vehicle may not be able to adapt to real-time traffic flow and unforeseen circumstances on some unfamiliar road sections during its current transport route. There may be excessive traffic flow on some unfamiliar road sections leading to congestion, or unforeseen events such as traffic accidents or road repairs, hindering the vehicle's continued progress. Furthermore, the roadside units on the sections the target logistics vehicle is currently traversing may have been affected by changes in its historical transport history. The more frequently a selected transportation route appears, the higher its feasibility for the target logistics vehicle. Therefore, by analyzing the frequency of roadside units on the road segments the target logistics vehicle has traveled to the current moment in the historical transportation routes, as well as the traffic flow and emergency information of roadside units on previously untraveled road segments, a route feasibility index for the target logistics vehicle at the current moment can be obtained. This route feasibility index can then be used to determine whether the current transportation route is still suitable for the target logistics vehicle to continue traveling. Subsequently, logistics vehicles that require route adjustments can be identified based on the route feasibility index, allowing for timely adjustments to their transportation routes and preventing delays in cargo arrival.

[0065] Preferably, in one embodiment of the present invention, the method for obtaining the path feasibility index of the target logistics vehicle at the current moment specifically includes:

[0066] First, among all the transportation routes selected by the target logistics vehicle in all historical transportation processes other than the current transportation route, multiple reference transportation routes are selected for the current transportation route. The starting point of the reference transportation route is the same as the starting point of the current transportation route, and the ending point of the reference transportation route is the same as the ending point of the current transportation route.

[0067] The sequence of roadside units formed by the roadside units along each reference transportation route within a preset time period is used as the reference roadside unit sequence for each reference transportation route.

[0068] During the current transportation route, the sequence of roadside units that transport the target logistics vehicle to the road segment it passes through at the current moment is taken as the current roadside unit sequence of the target logistics vehicle at the current moment.

[0069] Take the current roadside unit sequence or any reference roadside unit sequence as the target sequence, and extract all continuous subsequences of the target sequence. The number of elements in the continuous subsequence is greater than 1. For example, if the target sequence is [RSU1,RSU2,RSU3,RSU4], then the continuous subsequences of the target sequence are: [RSU1,RSU2], [RSU1,RSU2,RSU3], [RSU1,RSU2,RSU3,RSU4], [RSU2,RSU3], [RSU2,RSU3,RSU4], [RSU3,RSU4].

[0070] The numerator is the number of times each continuous subsequence of the current roadside unit sequence appears in each continuous subsequence of the reference roadside unit sequence, and the denominator is the number of each continuous subsequence of the reference roadside unit sequence. The ratio is used as the repeatability parameter of the current roadside unit sequence in each reference roadside unit sequence. The larger the repeatability parameter, the higher the consistency between the road segments traversed by the target logistics vehicle on the current transportation route and the transportation routes selected in the historical transportation process. In this case, the current transportation route is more feasible for the target logistics vehicle. Therefore, the average value of the repeatability parameter of the current roadside unit sequence in all reference roadside unit sequences can be used as the first feasibility coefficient of the target logistics vehicle at the current moment.

[0071] During the transport of the target logistics vehicle along the current transport route, the number of roadside units on the road segments that the target logistics vehicle has not yet passed at the current time and that have information on emergencies is used as the reference number of the target logistics vehicle at the current time. The average traffic flow of all roadside units on all road segments that the target logistics vehicle has not yet passed at the current time is used as the reference traffic flow of the target logistics vehicle at the current time. The smaller the number of parameters and the reference traffic flow, the higher the feasibility of the current transport route for the target logistics vehicle. Therefore, the reference number and the reference traffic flow can be combined and negatively correlated to obtain the second feasibility coefficient of the target logistics vehicle at the current time.

[0072] Then, the first feasibility coefficient and the second feasibility coefficient are combined and normalized to limit the calculation results to the range of [0,1], thereby obtaining the path feasibility index of the target logistics vehicle at the current moment.

[0073] In one embodiment of the present invention, the normalization process can be specifically, for example, maximum and minimum value normalization. Furthermore, the normalization in subsequent steps can all adopt maximum and minimum value normalization. In other embodiments of the present invention, other normalization methods can be selected according to the specific range of the numerical values, which will not be elaborated further.

[0074] As an example, in one embodiment of the present invention, the expression for the path feasibility index of the target logistics vehicle at the current moment can be specifically as follows:

[0075]

[0076] Where C represents the path feasibility index of the target logistics vehicle at the current moment; d n D represents the number of times each of the continuous subsequences of the current roadside unit sequence appears in each of the continuous subsequences of the nth reference roadside unit sequence; n This represents the number of all consecutive subsequences in the nth reference roadside unit sequence; This represents the repeatability parameter of the current roadside unit sequence in the nth reference roadside unit sequence; The first feasibility coefficient of the target logistics vehicle at the current moment is represented by: N; the number of reference roadside unit sequences, i.e., the number of reference transportation routes; E; the reference number of the target logistics vehicle at the current moment; and Q; the reference traffic flow of the target logistics vehicle at the current moment. ε1 represents the second feasibility coefficient of the target logistics vehicle at the current moment; ε1 represents the preset first adjustment parameter, which is used to prevent the denominator from being 0. The value range of ε1 is [0.001, 0.01]. In one embodiment of the present invention, ε1 is set to 0.01. The specific value of ε1 can also be set by the implementer according to the specific implementation scenario, and is not limited here; norm() represents the normalization function, which is used for normalization processing.

[0077] It should be noted that negative correlation mapping can also be achieved through other basic mathematical operations in other embodiments of the present invention, which will not be elaborated here.

[0078] Using the same method described above, the route feasibility index of each logistics vehicle at the current moment can be obtained. The smaller the route feasibility index of a logistics vehicle at the current moment, the more unfavorable the current transportation route of the logistics vehicle is to the continued passage of the logistics vehicle. Therefore, the logistics vehicle needs to make route adjustments. Thus, based on the route feasibility index, logistics vehicles that need to be adjusted can be selected from all logistics vehicles.

[0079] Preferably, in one embodiment of the present invention, logistics vehicles with a route feasibility index less than a preset feasibility threshold are designated as logistics vehicles to be adjusted. The preset feasibility threshold is set to 0.5. The specific value of the preset feasibility threshold can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0080] Step S3: Select any one of the logistics vehicles to be adjusted as the target logistics vehicle to be adjusted. Based on the route feasibility index of the target logistics vehicle to be adjusted at the current moment, obtain multiple feasible transportation routes for the target logistics vehicle to be adjusted at the current moment. Based on the historical transportation time and length of each feasible transportation route, obtain the suitability index of each feasible transportation route. Based on the suitability index of each feasible transportation route and the number of feasible transportation routes, obtain the adjustment priority of the target logistics vehicle to be adjusted.

[0081] After obtaining the logistics vehicles that need route adjustments, it is necessary to adjust the transportation routes of each logistics vehicle. Since the specific locations of different logistics vehicles are different, the available road segments around them are also different. In order to avoid all logistics vehicles being concentrated on the same transportation route after adjustment, this embodiment of the invention obtains multiple feasible transportation routes for the target logistics vehicle at the current time based on the route feasibility index of the target logistics vehicle at the current time.

[0082] Preferably, in one embodiment of the present invention, the method for obtaining multiple feasible transportation routes of the target logistics vehicle to be adjusted at the current moment specifically includes:

[0083] This invention uses the ant colony algorithm to obtain the feasible transportation path of the target logistics vehicle to be adjusted at the current time. The pheromone concentration in the ant colony algorithm is its core mechanism, which directly affects the path selection of the ants. The ants tend to choose the path with higher pheromone concentration. Therefore, in order to increase the probability of a more feasible path being selected, the pheromone concentration in the ant colony algorithm is first adjusted according to the path feasibility index of the target logistics vehicle to be adjusted at the current time, so as to obtain the adjusted pheromone concentration of each segment in each transportation path.

[0084] Preferably, in one embodiment of the present invention, the method for obtaining the adjusted pheromone concentration for each segment of each transportation path specifically includes:

[0085] The product of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the path feasibility index of the target logistics vehicle at the current moment is used as the concentration adjustment amount for each segment in each transportation path. The sum of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the concentration adjustment amount is used as the adjusted pheromone concentration for each segment in each transportation path.

[0086] As an example, in one embodiment of the present invention, the expression for adjusting the pheromone concentration for each segment in each transportation path can be specifically as follows:

[0087] τ′ (k,j) =τ (k,j) +C×τ (k,j)

[0088] Where, τ′ (k,j) τ represents the adjusted pheromone concentration in the j-th segment of the k-th transport route; (k,j) The pheromone concentration of the j-th segment in the k-th transportation path is calculated by the ant colony algorithm; C represents the path feasibility index of the target logistics vehicle at the current moment.

[0089] Then, the roadside units of each road segment are used as nodes, and the roadside unit of the target logistics vehicle to be adjusted at the current time is used as the initial node. Using the ant colony algorithm, and based on the adjustment pheromone concentration of each road segment in each transportation path, multiple feasible transportation paths of the target logistics vehicle to be adjusted at the current time are obtained. Since the ant colony algorithm is an iterative update process, the pheromone concentration of each road segment of each transportation path can be initialized to the value 1, and the ant colony algorithm is terminated when no new path is found for several consecutive times. In one embodiment of the present invention, the algorithm is terminated when no new path is found for 3 consecutive times. The ant colony algorithm is a well-known technical means in the art and will not be described in detail here.

[0090] Since there are multiple feasible transportation routes for the target logistics vehicle at the current moment, and each feasible transportation route is suitable for the target logistics vehicle to a different degree, for a certain feasible transportation route, within a preset time period, the shorter the historical transportation time of the logistics vehicle choosing that feasible transportation route and the shorter the length of the feasible transportation route, the more suitable the feasible transportation route is for the target logistics vehicle to be adjusted. Therefore, based on the historical transportation time and the length of each feasible transportation route, a suitability index can be obtained for each feasible transportation route. The suitability index is used to evaluate the suitability of each feasible transportation route for the target logistics vehicle to be adjusted. Subsequently, the optimal transportation route for the target logistics vehicle to be adjusted can be selected based on the suitability index to improve the route adjustment effect.

[0091] Preferably, in one embodiment of the present invention, the method for obtaining the suitability indicators for each feasible transportation route specifically includes:

[0092] First, any feasible transportation path is taken as the target feasible transportation path. The higher the overall level of the adjustment pheromone concentration of all segments in the target feasible transportation path, the more suitable the target feasible transportation path is for the target logistics vehicle to be adjusted to pass through. Therefore, the average value of the adjustment pheromone concentration of all segments in the target feasible transportation path can be taken as the first suitability coefficient of the target feasible transportation path.

[0093] Then, the average historical transportation time of all logistics vehicles on the target feasible transportation path during all historical transportation processes within the preset time period and the length of the target feasible transportation path are combined and negatively correlated to obtain the second suitability coefficient of the target feasible transportation path.

[0094] The first and second suitability coefficients of the target feasible transportation route are combined and normalized, and the calculation results are limited to the range of [0,1] to obtain the suitability index of the target feasible transportation route.

[0095] As an example, in one embodiment of the present invention, the expression for the suitability index of the target feasible transportation route may specifically be as follows:

[0096]

[0097] Where W represents the suitability index of the target feasible transportation route; τ ′ h This represents the adjusted pheromone concentration in the h-th segment of the target feasible transportation path; The first suitability coefficient represents the target feasible transportation path; H represents the number of road segments included in the target feasible transportation path. This represents the average historical transportation time of all logistics vehicles on the target feasible transportation route during all historical transportation processes within the preset time period; S represents the length of the target feasible transportation route. The second suitability coefficient represents the feasible transportation path to the target; norm() represents the normalization function used for normalization.

[0098] Using the same method described above, the appropriate indicators for each feasible transportation route of the target logistics vehicle to be adjusted, as well as the appropriate indicators for each feasible transportation route of each logistics vehicle to be adjusted, can be obtained. Furthermore, to avoid increased congestion after route adjustments, different priorities need to be assigned to each logistics vehicle. The fewer feasible transportation routes a logistics vehicle has at the current moment, and the lower the appropriate indicators for each feasible route, the more alternative routes the vehicle can take, and therefore, the higher its priority should be. Thus, the adjustment priority of the target logistics vehicle can be obtained based on the appropriate indicators of each feasible transportation route and the number of feasible transportation routes. Subsequently, by combining the adjustment priority of the logistics vehicle to be adjusted with the appropriate indicators of each feasible transportation route at the current moment, the transportation routes of each logistics vehicle to be adjusted can be more accurately matched and adjusted, thereby improving the effectiveness of route planning and matching.

[0099] Preferably, in one embodiment of the present invention, the method for obtaining the adjustment priority of the target logistics vehicle to be adjusted specifically includes:

[0100] The smaller the number of feasible transportation routes for the target logistics vehicle at the current moment relative to the overall number of feasible transportation routes for all logistics vehicles to be adjusted at the current moment, the fewer alternative routes the target logistics vehicle can take. Therefore, the target logistics vehicle should have a higher priority. Thus, the average number of feasible transportation routes for all logistics vehicles to be adjusted at the current moment can be used as the numerator, and the number of feasible transportation routes for the target logistics vehicle to be adjusted at the current moment can be used as the denominator. The ratio can be used as the first priority of the target logistics vehicle to be adjusted.

[0101] The difference between the planned arrival time and the current time of the target logistics vehicle to be adjusted is taken as the remaining time of the order for the target logistics vehicle to be adjusted. The planned arrival time is the time when the target logistics vehicle to be adjusted is scheduled to arrive at the destination during this transportation. The shorter the remaining time of the order, the more urgent the transportation, and the higher the priority of the target logistics vehicle to be adjusted should be. The average of the suitability indicators of all feasible transportation routes of the target logistics vehicle to be adjusted at the current time is taken as the overall suitability indicator of the target logistics vehicle to be adjusted. The smaller the remaining time of the order and the overall suitability indicator of the target logistics vehicle to be adjusted, the higher the priority of the target logistics vehicle to be adjusted should be. Therefore, the remaining time of the order and the overall suitability indicator can be combined and negatively correlated to obtain the second priority of the target logistics vehicle to be adjusted.

[0102] Then, the first and second priorities can be combined and normalized to obtain the adjustment priority of the target logistics vehicle to be adjusted.

[0103] As an example, in one embodiment of the present invention, the expression for the adjustment priority of the target logistics vehicle to be adjusted can be specifically as follows:

[0104]

[0105] Where U represents the adjustment priority of the target logistics vehicle to be adjusted; R represents the average number of feasible transportation routes for all logistics vehicles to be adjusted at the current time; and r represents the number of feasible transportation routes for the target logistics vehicle to be adjusted at the current time. Δt represents the first priority of the target logistics vehicle to be adjusted; Δt represents the remaining order duration for the target logistics vehicle to be adjusted. This indicates the overall suitability indicators for the logistics vehicles that need to be adjusted to meet the target requirements. ε2 represents the second priority of the target logistics vehicle to be adjusted; ε2 represents the preset second adjustment parameter, which is used to prevent the denominator from being 0. The value range of ε2 is [0.001, 0.01]. In one embodiment of the present invention, ε2 is set to 0.01. The specific value of ε2 can also be set by the implementer according to the specific implementation scenario, and is not limited here.

[0106] The adjustment priority of each logistics vehicle to be adjusted can be obtained by using the same method described above.

[0107] Step S4: Match and adjust the transportation route of each logistics vehicle to be adjusted according to the adjustment priority of each logistics vehicle to be adjusted and the appropriate indicators of each feasible transportation route of each logistics vehicle to be adjusted at the current time.

[0108] The higher the adjustment priority of a logistics vehicle to be adjusted, the more priority it needs to have its route adjusted. At the same time, the higher the suitability index of a feasible transportation route for that logistics vehicle, the more suitable that feasible transportation route is for that logistics vehicle. Therefore, the transportation routes of each logistics vehicle to be adjusted can be matched and adjusted according to its adjustment priority and the suitability index of each feasible transportation route at the current moment, so as to avoid congestion after adjustment and improve the effectiveness of logistics vehicle route planning and matching.

[0109] Preferably, in one embodiment of the present invention, the method for matching and adjusting the transportation route of each logistics vehicle to be adjusted specifically includes:

[0110] The adjustment priorities of each logistics vehicle to be adjusted are sorted in descending order. Starting from the highest adjustment priority, each logistics vehicle to be adjusted is moved to the feasible transportation route corresponding to the highest value of the appropriate index of that logistics vehicle.

[0111] One embodiment of the present invention provides a data matching system for a logistics freight platform based on big data. The system includes a memory, a processor, and a computer program. The memory is used to store the corresponding computer program, and the processor is used to run the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1 to S4.

[0112] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0113] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A data matching method for a logistics freight platform based on big data, characterized in that, The method includes: The system obtains the transportation route selected by each logistics vehicle in each historical transportation process within a preset time period and the historical transportation duration on the transportation route. The roadside unit of each segment of the transportation route records traffic flow and emergency information in real time. Taking any logistics vehicle as the target logistics vehicle, the current transportation route of the target logistics vehicle is obtained based on the number of times the target logistics vehicle has selected the same transportation route in each historical transportation process and the historical transportation duration. During the transportation of the target logistics vehicle on the current transportation route, the route feasibility index of the target logistics vehicle at the current moment is obtained based on the number of times the roadside units of the road segment that the target logistics vehicle has passed through in the historical transportation process appeared in the selected transportation routes, as well as the traffic flow and emergency event information of the roadside units of the road segments that have not been passed. Based on the route feasibility index, logistics vehicles that need to be adjusted are selected from all logistics vehicles. Take any one of the logistics vehicles to be adjusted as the target logistics vehicle to be adjusted. Based on the route feasibility index of the target logistics vehicle to be adjusted at the current time, obtain multiple feasible transportation routes for the target logistics vehicle to be adjusted at the current time. Based on the historical transportation time and length of each feasible transportation route, obtain the suitability index of each feasible transportation route. Based on the suitability index of each feasible transportation route and the number of feasible transportation routes, obtain the adjustment priority of the target logistics vehicle to be adjusted. The transportation route of each logistics vehicle to be adjusted is matched and adjusted according to the adjustment priority of each logistics vehicle to be adjusted and the suitability index of each feasible transportation route of each logistics vehicle to be adjusted at the current time. The multiple feasible transportation routes for the target logistics vehicle to be adjusted at the current moment include: Based on the path feasibility index of the target logistics vehicle to be adjusted at the current moment, the pheromone concentration in the ant colony algorithm is adjusted to obtain the adjusted pheromone concentration for each segment of each transportation path. Using the roadside units of each road segment as nodes, and the roadside unit of the current road segment where the target logistics vehicle to be adjusted is transported as the initial node, the ant colony algorithm is used, and based on the adjustment pheromone concentration of each road segment in each transportation path, multiple feasible transportation paths of the target logistics vehicle to be adjusted at the current time are obtained. The process of obtaining the adjusted pheromone concentration for each segment of each transportation path includes: The product of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the path feasibility index of the target logistics vehicle at the current moment is used as the concentration adjustment amount for each segment in each transportation path. The sum of the pheromone concentration of each segment in each transportation path calculated by the ant colony algorithm and the concentration adjustment amount is used as the adjusted pheromone concentration of each segment in each transportation path.

2. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The current transportation route of the target logistics vehicle is obtained as follows: The ratio of the number of times the target logistics vehicle selected the same transportation route in all historical transportation processes is used as the numerator, and the number of times the target logistics vehicle selected the same transportation route in all historical transportation processes is used as the denominator. The ratio is used as the frequency value of the target logistics vehicle's selection of each transportation route. By performing a negative correlation mapping on the average historical transportation time of the target logistics vehicle on the same transportation route in all historical transportation processes, the transportation timeliness value of the target logistics vehicle on each transportation route can be obtained. By combining the selection frequency value and the transportation timeliness value, the optimal selection degree of the target logistics vehicle on each transportation route is obtained; The transportation path corresponding to the maximum value of the optimization degree is taken as the current transportation path of the target logistics vehicle.

3. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The feasibility indicators for obtaining the target logistics vehicle's path at the current moment include: Among all the transportation routes selected by the target logistics vehicle in all historical transportation processes other than the current transportation route, multiple reference transportation routes are selected for the current transportation route. The starting point of the reference transportation route is the same as the starting point of the current transportation route, and the ending point of the reference transportation route is the same as the ending point of the current transportation route. The sequence of roadside units formed by the roadside units of the target logistics vehicle in each reference transportation route within a preset time period is used as the reference roadside unit sequence for each reference transportation route. In the current transportation route, the sequence of roadside units that transport the target logistics vehicle to the road segment it passes through at the current moment is taken as the current roadside unit sequence of the target logistics vehicle at the current moment. Take the current roadside unit sequence or any reference roadside unit sequence as the target sequence, and extract all continuous subsequences of the target sequence, wherein the number of elements in the continuous subsequence is greater than the value 1; The numerator is the number of times each continuous subsequence of the current roadside unit sequence appears in each continuous subsequence of the reference roadside unit sequence, and the denominator is the number of each continuous subsequence of the reference roadside unit sequence. The ratio is used as the repeatability parameter of the current roadside unit sequence in each reference roadside unit sequence. The average of the repeatability parameters of the current roadside unit sequence in all reference roadside unit sequences is used as the first feasibility coefficient of the target logistics vehicle at the current moment. During the transportation of the target logistics vehicle along the current transportation route, the number of roadside units on the road segment that the target logistics vehicle has not yet passed at the current time and that have the information of the sudden event is used as the reference number of the target logistics vehicle at the current time. The average traffic flow of the roadside units on all road segments that the target logistics vehicle has not yet passed at the current time is used as the reference traffic flow of the target logistics vehicle at the current time. The reference number and the reference traffic flow are combined and negatively correlated to obtain the second feasibility coefficient of the target logistics vehicle at the current time. The first feasibility coefficient and the second feasibility coefficient are combined and normalized to obtain the path feasibility index of the target logistics vehicle at the current moment.

4. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The process of selecting logistics vehicles to be adjusted from all logistics vehicles includes: Logistics vehicles whose route feasibility index is less than the preset feasibility threshold are designated as logistics vehicles to be adjusted.

5. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The appropriate indicators for obtaining each feasible transportation route include: Any feasible transportation route is taken as the target feasible transportation route, and the average value of the adjusted pheromone concentration of all segments in the target feasible transportation route is taken as the first suitability coefficient of the target feasible transportation route. The average historical transportation time of all logistics vehicles on the target feasible transportation route during all historical transportation processes within the preset time period and the length of the target feasible transportation route are combined and negatively correlated to obtain the second suitability coefficient of the target feasible transportation route. The first suitability coefficient and the second suitability coefficient of the target feasible transportation route are combined and normalized to obtain the suitability index of the target feasible transportation route.

6. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The adjustment priority of the target logistics vehicle to be adjusted includes: The numerator is the average of the number of feasible transportation routes for all the logistics vehicles to be adjusted at the current moment, and the denominator is the number of feasible transportation routes for the target logistics vehicle to be adjusted at the current moment. The ratio is used as the first priority of the target logistics vehicle to be adjusted. The difference between the planned arrival time and the current time of the target logistics vehicle to be adjusted is used as the remaining time of the order for the target logistics vehicle to be adjusted. The average value of the suitability index of all feasible transportation routes of the target logistics vehicle to be adjusted at the current time is used as the overall suitability index of the target logistics vehicle to be adjusted. The remaining time of the order and the overall suitability index are combined and negatively correlated to obtain the second priority of the target logistics vehicle to be adjusted. The first priority and the second priority are combined and normalized to obtain the adjustment priority of the target logistics vehicle to be adjusted.

7. The data matching method for a logistics freight platform based on big data according to claim 1, characterized in that, The process of matching and adjusting the transportation route for each logistics vehicle to be adjusted includes: The adjustment priorities of each logistics vehicle to be adjusted are sorted in descending order. Starting from the maximum adjustment priority, each logistics vehicle to be adjusted is moved to the feasible transportation route corresponding to the maximum value of the appropriate index of that logistics vehicle.

8. A data matching system for a logistics freight platform based on big data, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

Images