A logistics trajectory prediction and optimization system and method based on big data

Abstract

The present application provides a logistics trajectory prediction and optimization system and method based on big data, which obtains weather data, time data and traffic flow data of logistics transportation; based on the weather data, time data and traffic flow data, an ant colony algorithm is used to comprehensively predict the logistics trajectory to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory; the optimal path trajectory is pushed according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and the driving preference feature score is collected during the logistics transportation process; the comprehensive pheromone concentration corresponding to each logistics trajectory is corrected based on the driving preference feature score, and the optimal path trajectory push is updated in real time; the above scheme can be used to update and optimize the optimal path push trajectory according to the driving preference feature score during the logistics transportation process, thereby avoiding factors that affect transportation efficiency such as frequent deceleration and detours, thereby improving the stability of logistics transportation.

Description

Technical Field

[0001] The present application relates to the technical field of logistics trajectory prediction, and more specifically, to a logistics trajectory prediction optimization system and method based on big data. Background Art

[0002] Logistics trajectory prediction based on big data is a technology that uses data analysis and machine learning to predict the location and status of vehicles, goods, etc. in the logistics transportation process. Its core goal is to predict the specific location of logistics objects in the future through analysis and modeling of historical logistics trajectory data, traffic information, meteorological data, transportation time and other factors, to help logistics companies optimize distribution routes, improve timeliness and reduce transportation costs.

[0003] The existing logistics trajectory prediction methods mainly use machine learning based on historical logistics transmission data to obtain logistics trajectories and push distribution routes. However, logistics transportation usually involves many different types of roads. The existing prediction methods do not record the driving preferences of logistics transportation based on the real-time transportation information of logistics. Therefore, it is difficult to avoid factors that affect transportation efficiency, such as frequent deceleration and detours, and cannot reduce the risk of accidents caused by complex road conditions. The safety of drivers and goods is difficult to guarantee. Summary of the invention

[0004] The present application provides a logistics trajectory prediction and optimization system and method based on big data, which can update and optimize the optimal path push trajectory according to the driving preference feature score during the logistics transportation process, thereby avoiding factors that affect transportation efficiency such as frequent deceleration and detours, and improving the stability of logistics transportation.

[0005] In a first aspect, the present application provides a logistics trajectory prediction optimization method based on big data, the optimization method comprising the following steps:

[0006] Obtain weather data, time data and traffic flow data for logistics transportation;

[0007] Based on the weather data, the time data and the traffic flow data, an ant colony algorithm is used to comprehensively predict the logistics trajectory to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory;

[0008] The optimal path trajectory is pushed according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and the driving preference feature score is collected during the logistics transportation process;

[0009] Based on the driving preference characteristic score, the pheromone comprehensive concentration corresponding to each logistics track is corrected, and based on the corrected pheromone comprehensive concentration, the optimal path track push is updated in real time.

[0010] In this embodiment, the ant colony algorithm is used to comprehensively predict the logistics trajectory, and the comprehensive pheromone concentration corresponding to each logistics trajectory is obtained, which specifically includes:

[0011] Normalizing the weather data, the time data, and the traffic flow data to obtain a pheromone weight value;

[0012] Prune the city map of the target logistics transportation area to obtain the city sections, and perform initial pheromone assignment based on the traffic flow data corresponding to each city section;

[0013] Defining the heuristic information of the ant colony algorithm according to the pheromone weight value, performing path selection according to the heuristic information and the initial pheromone assignments corresponding to each urban road section, and locally updating the initial pheromone assignments of the selected urban road sections;

[0014] Multiple rounds of path selection and local update of pheromones in urban road sections are continuously performed. Through multiple rounds of iterations, multiple combinations of urban road sections are finally converged and used as logistics trajectories respectively, so as to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory.

[0015] In this embodiment, the heuristic information defining the ant colony algorithm is determined according to the following formula:

[0016]

[0017] in, is the inspiration information of the ant colony algorithm, is the length of the nth urban road section, N is the total number of urban road sections, is the weather weight, is the time weight, is the average value of the traffic flow weights corresponding to each urban road section.

[0018] In this embodiment, the optimal path trajectory is pushed according to the comprehensive concentration of pheromones corresponding to each logistics trajectory, specifically including:

[0019] Obtain the comprehensive pheromone concentration corresponding to each logistics track;

[0020] The comprehensive pheromone concentration corresponding to each logistics track is normalized, and all logistics tracks that are higher than the preset normalization threshold are pushed to the optimal path.

[0021] In this embodiment, collecting driving preference feature scores during logistics transportation specifically includes:

[0022] Obtain each city road section in the target logistics transportation area and classify the labels to obtain the labels of each city road section;

[0023] Obtain the average driving speed and speed standard deviation of vehicles in each city road section during logistics transportation;

[0024] The driving preference feature scores are performed based on the urban road segment labels corresponding to the urban road segments, the average driving speed and the speed standard deviation, so as to obtain the driving preference feature scores corresponding to the urban road segment labels.

[0025] In this embodiment, each city road section in the target logistics transportation area is obtained and label classification is performed. Before obtaining the label of each city road section, it also includes: obtaining all city road sections in the target logistics transportation area through an online map service API.

[0026] In this embodiment, the correction of the pheromone comprehensive concentration corresponding to each logistics track based on the driving preference characteristic score specifically includes:

[0027] Get the driving preference feature scores corresponding to each city road segment label;

[0028] Based on a preset mapping table, the driving preference feature scores corresponding to each city road section label are mapped to obtain the pheromone attenuation rate corresponding to each city road section label;

[0029] According to the pheromone attenuation rates corresponding to the labels of each urban road section, the local pheromone assignments of different urban road section types are corrected, and then after the correction, the comprehensive pheromone concentrations corresponding to each logistics track are re-determined according to the local pheromone assignments corresponding to each urban road section.

[0030] In this embodiment, in the process of re-determining the comprehensive pheromone concentration corresponding to each logistics track according to the local pheromone assignment corresponding to each urban road section after correction, the comprehensive pheromone concentration corresponding to each logistics track after correction = the sum of the local pheromone assignments corresponding to each urban road section within the logistics track.

[0031] In this embodiment, the real-time update of the optimal path trajectory push based on the corrected pheromone comprehensive concentration specifically includes:

[0032] The pheromone comprehensive concentration corresponding to each logistics track after correction is obtained and normalized, and the logistics track is selected according to the normalized threshold to re-push the optimal path track.

[0033] In a second aspect, the present application provides a logistics trajectory prediction and optimization system based on big data for executing a logistics trajectory prediction and optimization method based on big data, the logistics trajectory prediction and optimization system comprising:

[0034] Data collection module, used to obtain weather data, time data and traffic flow data for logistics transportation;

[0035] A logistics trajectory prediction module, used to use an ant colony algorithm to comprehensively predict the logistics trajectory based on the weather data, the time data and the traffic flow data, and obtain the comprehensive pheromone concentration corresponding to each logistics trajectory;

[0036] The logistics trajectory prediction module is also used to push the optimal path trajectory according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and collect the driving preference feature score during the logistics transportation process;

[0037] The logistics trajectory prediction module is also used to correct the pheromone comprehensive concentration corresponding to each logistics trajectory based on the driving preference feature score, and to push the optimal path trajectory for real-time update based on the corrected pheromone comprehensive concentration.

[0038] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects:

[0039] By acquiring weather data, time data and traffic flow data of logistics transportation; based on the weather data, the time data and the traffic flow data, using the ant colony algorithm to comprehensively predict the logistics trajectory, and obtaining the comprehensive pheromone concentration corresponding to each logistics trajectory; according to the comprehensive pheromone concentration corresponding to each logistics trajectory, the optimal path trajectory is pushed, and the driving preference feature score is collected during the logistics transportation process; based on the driving preference feature score, the comprehensive pheromone concentration corresponding to each logistics trajectory is corrected, and the optimal path trajectory push is updated in real time based on the corrected comprehensive pheromone concentration.

[0040] It can be seen that in the present application, the collected driving preference feature scores reflect the driver's actual driving experience such as average speed, acceleration, detour frequency, etc. in the pheromone concentration, and dynamically adjust the pheromone concentration to reflect the driving adaptability of the road. After collecting the driving preference scores in real time, the scores are converted into corrections to the pheromone concentration, that is, the pheromone concentration is reduced for sections that do not meet the driving preferences. Through the iterative update mechanism of the ant colony algorithm, the pheromone concentration of paths with higher preferences increases, and the concentration of paths with lower preferences gradually decreases, avoiding the selection of paths with frequent deceleration and detours, thereby improving the stability of path selection. In summary, the technical solution adopted in the present application can update and optimize the optimal path push trajectory according to the driving preference feature scores in the logistics transportation process, thereby avoiding factors that affect transportation efficiency such as frequent deceleration and detours, and improving the stability of logistics transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0042] Figure 1 is an exemplary flow chart of a logistics trajectory prediction optimization method based on big data provided by this application;

[0043] Figure 2 is an exemplary flow chart for comprehensive prediction of logistics trajectories using ant colony algorithm provided in this application;

[0044] Figure 3 is an exemplary flow chart for performing optimal path trajectory according to the present application;

[0045] Figure 4 This is a module structure diagram of the logistics trajectory prediction and optimization system based on big data provided by this application. DETAILED DESCRIPTION

[0046] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0047] The embodiment of the present application provides a logistics trajectory prediction and optimization method based on big data, the core of which is to obtain weather data, time data and traffic flow data of logistics transportation; based on the weather data, the time data and the traffic flow data, use an ant colony algorithm to comprehensively predict the logistics trajectory to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory; according to the comprehensive pheromone concentration corresponding to each logistics trajectory, the optimal path trajectory is pushed, and the driving preference feature score is collected during the logistics transportation process; based on the driving preference feature score, the comprehensive pheromone concentration corresponding to each logistics trajectory is corrected, and the optimal path trajectory push is updated in real time based on the corrected comprehensive pheromone concentration; the above scheme can be used to update and optimize the optimal path push trajectory according to the driving preference feature score in the logistics transportation process, thereby avoiding factors that affect transportation efficiency such as frequent deceleration and detours, thereby improving the stability of logistics transportation.

[0048] Embodiment 1

[0049] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown, this figure is an exemplary flow chart of a logistics trajectory prediction optimization method based on big data shown in this embodiment of the present application, and the optimization method includes the following steps:

[0050] In step S1, weather data, time data and traffic flow data of logistics transportation are obtained.

[0051] In this embodiment, obtaining weather data for logistics transportation includes: obtaining weather information of the current and predicted areas (such as temperature, precipitation, wind speed, etc.), which can be obtained from a meteorological API or a real-time weather database during specific implementation.

[0052] In this embodiment, obtaining the time data of logistics transportation includes: determining the peak and non-peak time periods based on historical transportation records, and marking them after evaluating the impact on transportation efficiency respectively. For example, traffic may be congested during rush hour. In specific implementation, the congestion levels during peak and non-peak hours on weekdays and weekends are scored and marked respectively to obtain the time data of logistics transportation.

[0053] In this embodiment, obtaining the traffic flow data of logistics transportation includes: obtaining real-time and predicted traffic flow through the traffic flow API and map services. Areas with high traffic will increase the attenuation rate of pheromones.

[0054] In step S2, based on the weather data, the time data and the traffic flow data, an ant colony algorithm is used to comprehensively predict the logistics trajectory to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory;

[0055] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flow chart of using the ant colony algorithm to comprehensively predict the logistics trajectory in the embodiment of the present application. In this embodiment, the ant colony algorithm is used to comprehensively predict the logistics trajectory, and the comprehensive pheromone concentration corresponding to each logistics trajectory is obtained, which specifically includes:

[0056] In step S21, the weather data, the time data and the traffic flow data are numerically normalized to obtain a pheromone weight value;

[0057] In step S22, the city map of the target logistics transportation area is pruned to obtain each city road section, and the pheromone is initially assigned based on the traffic flow data corresponding to each city road section;

[0058] In step S23, the heuristic information of the ant colony algorithm is defined according to the pheromone weight value, the path selection is performed according to the heuristic information and the initial pheromone assignments corresponding to each urban road section, and the initial pheromone assignments of the selected urban road section are locally updated;

[0059] In step S24, multiple rounds of path selection and local update of pheromones of urban road sections are continuously performed, and multiple rounds of iterations are finally converged to obtain multiple urban road section combinations, which are respectively used as logistics trajectories, and then the comprehensive pheromone concentration corresponding to each logistics trajectory is obtained.

[0060] In a specific implementation, the weather data, the time data and the traffic flow data are numerically normalized to obtain the pheromone weight value. The weather, time and traffic flow data can be normalized and the numerical values ​​can be mapped to the interval [0,1] to obtain the corresponding pheromone weight value. For example, the weather weight is normalized according to the degree of weather influence (1 for a sunny day and 0.5 for a rainstorm), the time weight is from 0.6 during peak hours to 1 for non-peak hours, and the traffic flow weight is based on the traffic flow density. The denser the traffic flow on a road section, the lower the traffic flow weight, with a minimum of 0.4. The final pheromone weight value = weather weight × time weight × traffic flow weight.

[0061] It should be noted that pruning urban road sections in the target logistics transportation area can exclude some sections that are blocked or difficult to use, thereby retaining the core path network suitable for transportation and improving the efficiency of logistics trajectory prediction.

[0062] In this embodiment, in the process of performing initial pheromone assignment based on the traffic flow data corresponding to each urban road section, the initial pheromone assignment of the road section = the traffic flow weight of the road section × the comprehensive pheromone weight / the road section length.

[0063] In this embodiment, the heuristic information of the ant colony algorithm is set to be determined according to the following formula:

[0064]

[0065] in, is the inspiration information of the ant colony algorithm, is the length of the nth urban road section, N is the total number of urban road sections, is the weather weight, is the time weight, is the average value of the traffic flow weights corresponding to each urban road section.

[0066] In this embodiment, the probability of each ant in the ant colony algorithm to select a path based on the initial pheromone assignment and heuristic information is determined according to the following formula:

[0067]

[0068] in, is the probability of the k-th city road segment being selected, is the inspiration information of the ant colony algorithm, Assign the initial value of the pheromone corresponding to the k-th city road section, is the pheromone adjustment coefficient, which is used to control the relative influence of pheromone and heuristic information, and appropriately reduce The value can make the heuristic information more effective under the influence of weather, time, and traffic flow. In specific implementation, the pheromone adjustment coefficient is calibrated as a constant as needed.

[0069] In this embodiment, during the process of partially updating the pheromone initial assignment of the selected urban road section, the updated pheromone initial assignment of the urban road section is determined according to the following formula:

[0070]

[0071] in, is the initial assignment of the pheromone corresponding to the k-th city road section after the update, Assign a value to the local pheromone corresponding to the k-th city road section before updating, is the pheromone attenuation ratio built into the ant colony algorithm, is the pheromone environment deviation reference amount corresponding to the k-th urban road section. In this embodiment, the pheromone environment deviation reference amount=environmental weight×the pheromone initial assignment corresponding to the k-th urban road section.

[0072] It should be noted that the logistics trajectory includes multiple urban road sections and connecting nodes between the road sections, and the comprehensive pheromone concentration of the logistics trajectory is the sum of the local pheromone values ​​corresponding to all urban road sections.

[0073] In step S3, the optimal path trajectory is pushed according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and the driving preference feature score is collected during the logistics transportation process.

[0074] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flow chart of performing the optimal path trajectory in an embodiment of the present application. In this embodiment, the optimal path trajectory is pushed according to the comprehensive concentration of pheromones corresponding to each logistics trajectory, which specifically includes:

[0075] In step S31, the comprehensive concentration of pheromones corresponding to each logistics track is obtained;

[0076] In step S32, the comprehensive pheromone concentrations corresponding to the respective logistics trajectories are normalized, and all logistics trajectories that are higher than a preset normalization threshold are pushed along the optimal path.

[0077] In this embodiment, the normalized threshold is calibrated as a constant according to demand. In specific implementation, the average of the normalized pheromone comprehensive concentrations corresponding to each logistics track can also be used as the normalized threshold.

[0078] It should be noted that by integrating driving preference characteristics, the logistics system can give priority to recommending routes that are more in line with driving preferences, avoiding congestion and sections with frequent deceleration, making logistics transportation routes more in line with driving needs and improving driving efficiency. Recommending routes with higher driving preferences can help reduce unnecessary deceleration, parking, etc., thereby reducing fuel consumption or electricity consumption and reducing transportation costs. The routes pushed according to driving preference characteristics can also give priority to avoiding sharp turns and areas with large slopes, reducing accident risks and improving driving safety.

[0079] In this embodiment, collecting driving preference feature scores during logistics transportation specifically includes:

[0080] Obtain each city road section in the target logistics transportation area and classify the labels to obtain the labels of each city road section;

[0081] Obtain the average driving speed and speed standard deviation of vehicles in each city road section during logistics transportation;

[0082] The road condition score is performed based on the urban road segment labels corresponding to the urban road segments, the average driving speed and the speed standard deviation, and the driving preference feature score corresponding to each urban road segment label is obtained.

[0083] In this embodiment, after obtaining all urban road sections in the target logistics transportation area through the online map service API, the curves and straight roads in each urban road section are marked through the map data or the path geometry information of the navigation system, and the curves can also be classified by angle (such as sharp bends, medium bends, and slight bends) for label classification.

[0084] In this embodiment, in the process of scoring the road condition based on the urban road segment labels corresponding to the urban road segments, the average driving speed and the speed standard deviation, the road condition score corresponding to the urban road segment label = the preset basic score + the speed weight coefficient × the average driving speed of all urban road segments corresponding to the urban road segment label + the standard deviation weight coefficient × the speed standard deviation of all urban road segments corresponding to the urban road segment label.

[0085] It should be noted that the prediction and push system that integrates driving preference feature scores can adapt to real-time dynamic data such as weather and traffic flow at any time, respond flexibly to changes, and make route planning more flexible and adaptable.

[0086] In step S4, the pheromone comprehensive concentrations corresponding to the various logistics trajectories are corrected based on the driving preference characteristic scores, and the optimal path trajectory push is updated in real time based on the corrected pheromone comprehensive concentrations.

[0087] In this embodiment, the correction of the pheromone comprehensive concentration corresponding to each logistics track based on the driving preference characteristic score specifically includes:

[0088] Get the driving preference feature scores corresponding to each city road segment label;

[0089] Based on a preset mapping table, the driving preference feature scores corresponding to each city road section label are mapped to obtain the pheromone attenuation rate corresponding to each city road section label;

[0090] According to the pheromone attenuation rates corresponding to the labels of each urban road section, the local pheromone assignments of different urban road section types are corrected, and then after correction, the comprehensive pheromone concentrations corresponding to each logistics track are determined according to the local pheromone assignments corresponding to each urban road section.

[0091] In a specific implementation, different driving preference characteristic scores are mapped according to the score intervals in which they are located to obtain different pheromone decay rates, and the pheromone decay rates are used to correct the local pheromone assignment for the same type of driving preference sections.

[0092] In this embodiment, during the process of calibrating the comprehensive pheromone concentrations for different types of urban road sections, the comprehensive pheromone concentrations corresponding to different types of urban road sections after calibration are determined according to the following formula:

[0093]

[0094] in, is the local assignment of pheromone corresponding to the a-th urban road section after correction, is the pheromone attenuation rate corresponding to the c-th type urban road section label corresponding to the urban road section, is the local assignment of pheromone corresponding to the a-th urban road section before correction, is the reference value of pheromone environment deviation corresponding to the a-th urban road section.

[0095] In this embodiment, in the process of determining the comprehensive pheromone concentration corresponding to each logistics track according to the local pheromone assignment corresponding to each urban road section after correction, the comprehensive pheromone concentration corresponding to each logistics track after correction = the sum of the local pheromone assignments corresponding to each urban road section within the logistics track.

[0096] In this embodiment, the real-time update of the optimal path trajectory push based on the corrected pheromone comprehensive concentration specifically includes:

[0097] The pheromone comprehensive concentrations corresponding to each logistics track after correction are obtained and normalized, and the logistics track is selected according to the normalized threshold to re-push the optimal path track. In specific implementation, the logistics track higher than the normalized threshold can be pushed as the optimal path track.

[0098] To sum up, the technical solution adopted in this application can update the optimal path push trajectory according to the driving preference feature score during the logistics transportation process, thereby avoiding factors that affect transportation efficiency such as frequent deceleration and detours, and improving the stability of logistics transportation.

[0099] Embodiment 2

[0100] This application provides a logistics trajectory prediction and optimization system based on big data, referring to Figure 4 As shown, this figure is a module structure diagram of the logistics trajectory prediction and optimization system shown in this embodiment of the present application, and the logistics trajectory prediction and optimization system includes:

[0101] The data collection module 100 is used to obtain weather data, time data and traffic flow data of logistics transportation;

[0102] The logistics trajectory prediction module 200 is used to use an ant colony algorithm to comprehensively predict the logistics trajectory based on the weather data, the time data and the traffic flow data, and obtain the comprehensive pheromone concentration corresponding to each logistics trajectory;

[0103] The logistics trajectory prediction module 200 is also used to push the optimal path trajectory according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and collect the driving preference feature score during the logistics transportation process;

[0104] The logistics trajectory prediction module 200 is further used to correct the pheromone comprehensive concentration corresponding to each logistics trajectory based on the driving preference feature score, and to push the optimal path trajectory for real-time update based on the corrected pheromone comprehensive concentration.

[0105] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1A device that provides the functions specified in a block or multiple blocks.

[0106] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0107] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A logistics trajectory prediction and optimization method based on big data, characterized in that: The optimization method comprises the following steps: Obtain weather data, time data and traffic flow data for logistics transportation; Based on the weather data, the time data and the traffic flow data, an ant colony algorithm is used to comprehensively predict the logistics trajectory to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory; The optimal path trajectory is pushed according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and the driving preference feature score is collected during the logistics transportation process; Based on the driving preference characteristic score, the pheromone comprehensive concentration corresponding to each logistics track is corrected, and based on the corrected pheromone comprehensive concentration, the optimal path track push is updated in real time; Among them, the driving preference feature scores collected during logistics transportation specifically include: Obtain each city road section in the target logistics transportation area and classify the labels to obtain the labels of each city road section; Obtain the average driving speed and speed standard deviation of vehicles in each city road section during logistics transportation; Perform driving preference feature scoring based on the urban road segment labels corresponding to the urban road segments, the average driving speed and the speed standard deviation, to obtain driving preference feature scores corresponding to the urban road segment labels; Obtaining each city road section in the target logistics transportation area and classifying the labels specifically includes: after obtaining all city road sections in the target logistics transportation area through the online map service API, marking the curves in each city road section through the path geometry information of the navigation system, and classifying the curves by label according to the angle; Correcting the comprehensive pheromone concentrations corresponding to each logistics track based on the driving preference characteristic score specifically includes: Get the driving preference feature scores corresponding to each city road segment label; Based on a preset mapping table, the driving preference feature scores corresponding to each city road section label are mapped to obtain the pheromone attenuation rate corresponding to each city road section label; According to the pheromone attenuation rates corresponding to the labels of each urban road section, the local pheromone values ​​of different urban road section types are corrected, and then after the correction, the comprehensive pheromone concentrations corresponding to each logistics track are re-determined according to the local pheromone values ​​corresponding to each urban road section; Among them, the ant colony algorithm is used to comprehensively predict the logistics trajectory, and the comprehensive pheromone concentration corresponding to each logistics trajectory is obtained, including: Normalizing the weather data, the time data, and the traffic flow data to obtain a pheromone weight value; Prune the city map of the target logistics transportation area to obtain the city sections, and perform initial pheromone assignment based on the traffic flow data corresponding to each city section; Defining the heuristic information of the ant colony algorithm according to the pheromone weight value, performing path selection according to the heuristic information and the initial pheromone assignments corresponding to each urban road section, and locally updating the initial pheromone assignments of the selected urban road sections; Multiple rounds of path selection and local update of pheromones in urban road sections are continuously performed. Through multiple rounds of iterations, multiple combinations of urban road sections are finally converged and used as logistics trajectories respectively, so as to obtain the comprehensive pheromone concentration corresponding to each logistics trajectory.

2. A logistics trajectory prediction and optimization method based on big data as claimed in claim 1, characterized in that: The heuristic information that defines the ant colony algorithm is determined according to the following formula: in, is the inspiration information of the ant colony algorithm, is the length of the nth urban road section, N is the total number of urban road sections, is the weather weight, is the time weight, is the average value of the traffic flow weights corresponding to each urban road section.

3. The logistics trajectory prediction and optimization method based on big data as claimed in claim 1 is characterized in that: According to the comprehensive concentration of pheromones corresponding to each logistics track, the optimal path track push is specifically including: Obtain the comprehensive pheromone concentration corresponding to each logistics track; The comprehensive pheromone concentration corresponding to each logistics track is normalized, and all logistics tracks that are higher than the preset normalization threshold are pushed to the optimal path.

4. The logistics trajectory prediction and optimization method based on big data as claimed in claim 1, characterized in that: In the process of re-determining the comprehensive pheromone concentration corresponding to each logistics track according to the local pheromone assignment corresponding to each urban road section after correction, the comprehensive pheromone concentration corresponding to each logistics track after correction is the sum of the local pheromone assignment corresponding to each urban road section within the logistics track.

5. The method for predicting and optimizing logistics trajectories based on big data according to claim 1, characterized in that: The real-time update of the optimal path trajectory push based on the corrected pheromone comprehensive concentration includes: The pheromone comprehensive concentration corresponding to each logistics track after correction is obtained and normalized, and the logistics track is selected according to the normalization threshold to re-push the optimal path track.

6. A logistics trajectory prediction and optimization system based on big data, used to execute a logistics trajectory prediction and optimization method based on big data as described in any one of claims 1 to 5, characterized in that: The logistics trajectory prediction and optimization system includes: Data collection module, used to obtain weather data, time data and traffic flow data for logistics transportation; A logistics trajectory prediction module, used to use an ant colony algorithm to comprehensively predict the logistics trajectory based on the weather data, the time data and the traffic flow data, and obtain the comprehensive pheromone concentration corresponding to each logistics trajectory; The logistics trajectory prediction module is also used to push the optimal path trajectory according to the comprehensive pheromone concentration corresponding to each logistics trajectory, and collect the driving preference feature score during the logistics transportation process; The logistics trajectory prediction module is also used to correct the pheromone comprehensive concentration corresponding to each logistics trajectory based on the driving preference feature score, and to push the optimal path trajectory for real-time update based on the corrected pheromone comprehensive concentration.

Images