Intelligent logistics path optimization system based on big data

Abstract

The invention discloses an intelligent logistics path optimization system based on big data, and relates to the technical field of logistics, the system comprises a data acquisition module, a data analysis module, a path planning module, a feedback adjustment module and a user interface module; according to the method, the driving style and behavior characteristics of each driver can be deeply analyzed by comprehensively collecting the historical driving data of the driver, such as the driving speed, the braking frequency and the turning habit, and by means of the detailed driver driving habit analysis, the path planning better fits the personal preference of the driver, for example, for the driver with aggressive driving style, the driving habit of the driver can be better optimized. The system intelligently recommends routes with excellent road conditions and less traffic restrictions, so that not only can a driver give full play to the driving speed advantage, but also the driving experience that the driver pursues speed and passion can be met to a certain extent, and for drivers with careful driving styles, the system tends to recommend routes with small traffic flow and high road safety.

Description

Technical Field

[0001] The present invention relates to the field of logistics technology, and in particular to an intelligent logistics path optimization system based on big data. Background Art

[0002] With the rapid development of big data and artificial intelligence technologies, intelligent logistics path optimization systems have gradually become an important means to improve logistics transportation efficiency and reduce transportation costs. The system aims to achieve more accurate and personalized path planning by collecting and analyzing drivers' historical driving data and real-time traffic information. This data-based path optimization method can not only improve the timeliness of logistics transportation, but also ensure the driver's driving safety and comfort to a certain extent.

[0003] Although traditional technology has been able to achieve personalized route recommendations based on driver behavior data to a certain extent, there are still some shortcomings. First, in terms of driver driving habit analysis, traditional technology often only focuses on a single driving behavior data, such as driving speed or braking frequency, and fails to fully and deeply explore the driver's driving style and behavioral characteristics. This leads to the inability to provide drivers with route recommendations that truly meet their driving habits during route planning. Secondly, traditional technology does not make full use of real-time traffic information during route planning, and can often only make predictions based on historical traffic data, and cannot timely reflect the current road congestion and real-time conditions of traffic accidents. In addition, traditional technology also lacks comprehensive consideration of logistics and transportation needs, such as the impact of cargo type, weight, and volume factors on route selection, which to a certain extent limits the effect of route optimization.

[0004] Therefore, the development of an intelligent logistics path optimization system based on big data can comprehensively collect and analyze drivers' historical driving data and real-time traffic information, deeply explore drivers' driving styles and behavioral characteristics, and provide drivers with route recommendations that truly meet their driving habits and transportation needs based on the actual needs of logistics transportation. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the prior art and provide an intelligent logistics path optimization system based on big data. It can collect drivers' historical driving data and real-time traffic information, conduct in-depth analysis and build personalized path recommendation strategies. It can recommend the most suitable driving routes for different drivers based on their driving styles, such as aggressive, steady or cautious, while taking into account the specific needs of logistics transportation, such as cargo type, weight and volume. In addition, it can continuously monitor traffic conditions while the driver is driving, dynamically adjust recommended routes, and ensure driving safety and efficiency.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent logistics path optimization system based on big data, the system comprising: a data acquisition module, a data analysis module, a path planning module, a feedback adjustment module and a user interface module;

[0007] The data collection module: uses vehicle-mounted equipment and mobile phone applications to collect historical driving data on the driver's driving speed, acceleration, braking frequency, turning angle and speed, and idling time, and records the driver's daily driving route preferences and rest point selection information. Through cooperation with the data interface of the traffic management department, the satellite positioning system and third-party traffic data providers, it obtains real-time road congestion, traffic accident information, traffic control measures, construction section information, and weather conditions.

[0008] The data analysis module cleans and preprocesses the collected historical driving data of the driver, removes outliers, noise data and standardizes the data, extracts characteristic data reflecting the driver's average driving speed, braking frequency, number of sudden accelerations and sharp turning angles from the preprocessed data, analyzes driving route preferences and rest time patterns, and uses the driver behavior comprehensive index to classify the driver's behavior characteristics. The calculation formula is: Among them, V avg is the average driving speed, V l imit is the road speed limit, F b rake is the braking frequency, T total is the total driving time, N accel is the number of rapid accelerations, A turn The comprehensive index of turning amplitude w1, w2, w3, and w4 are used as weight coefficients, and drivers are divided into aggressive, stable, and cautious types. The collected real-time traffic data is quickly processed and analyzed, key information is extracted, and the congestion index of each road section is calculated to determine the degree of congestion. The congestion index is: Among them, L congested is the length of the congested road section, L total is the total section length, N vehicles is the number of vehicles on the road section, A road is the road section area, w 5、 w6 is the weight coefficient. At the same time, by mining historical traffic data, the time prediction formula is used to predict the travel time of each road section in the future. The formula is: ETT = Where D is the length of the road section, V effective is the effective driving speed, T delay For possible delay time;

[0009] The path planning module: loads detailed electronic map data, uses the map data to build a road network model, preliminarily determines the shortest path from the departure point to the destination through the path potential index, recommends a path based on the driver's driving style through a path recommendation strategy, optimizes the recommended path in combination with real-time traffic conditions, and further optimizes the path selection according to the needs of logistics transportation. During the driver's driving process, the vehicle's position, driving status, and changes in road traffic conditions are continuously monitored through the on-board equipment and satellite positioning system. When changes in traffic conditions are found and the driver deviates from the recommended path, dynamic adjustments are made based on real-time data;

[0010] The feedback adjustment module: provides multiple channels for drivers to give feedback on their opinions and suggestions on the recommended routes, records the feedback information of drivers, extracts valuable data from the collected feedback information of drivers, calculates the route adjustment index according to the feedback information, provides specific adjustment directions for the route planning module according to the route adjustment index, establishes a regular data update mechanism, continuously learns the changes in drivers' behavior and the dynamic changes in traffic conditions, and automatically adjusts the algorithm parameters and recommendation strategies;

[0011] The user interface module provides the driver with an intuitive and clear user interface, displays recommended routes, real-time traffic conditions, estimated arrival times, and fuel consumption estimates, uses map visualization technology to present route and traffic information to the driver, allows the driver to accept or reject recommended routes, set preferences, view historical driving records and feedback records through the user interface, and provides voice interaction functions.

[0012] Furthermore, the data analysis module determines the driving style type of the driver by the DBI value, performs statistical analysis on the DBI values ​​of all drivers, obtains their distribution, and determines the threshold value according to the percentile of the distribution. The drivers with DBI values ​​in the top x% are defined as aggressive, the drivers with DBI values ​​in the bottom y% are defined as cautious, and the drivers in the middle are defined as robust. The threshold values ​​are determined as T and T respectively. aggressive and T moderate , when DBI ≥ T a ggressive, the driver is aggressive; when T moderate ≤DBI <T aggressive , the driver is a stable type; when DBI <T moderate , the driver is cautious.

[0013] Furthermore, the data analysis module collects statistics on the drivers' night and peak hours T peak Number of driving times N night and N peakAs well as driving characteristics, when classifying driving styles, the classification threshold is adjusted according to the driving characteristics of different time periods. For drivers who often drive at night, the night driving adjustment factor w is added when calculating the driver behavior comprehensive index DBI. night ×f(N night ), where f(N night ) is a function of the number of nighttime driving times: where λ is a tuning parameter.

[0014] Furthermore, the path planning module preliminarily determines the shortest path from the departure point to the destination through the path potential index. Let G = (V, E) be a directed graph, where V is a vertex set and E is an edge set. For the starting point s and the end point t, the calculation formula of the path potential index is defined as: Where u is any vertex in the graph, d(u,s) represents the currently known shortest distance from vertex u to the starting point s, d(u,t) represents the estimated distance from vertex u to the end point t, α, β, γ are weight coefficients that can be adjusted according to actual conditions to balance the importance of the starting point distance, the end point distance and the path quality, F quality (u) is the path quality function of vertex u, and the function is: Where V l imit(u) is the speed limit of the road where vertex u is located, N vehicles (u) is the number of vehicles on the road, w 1、 w2 is the corresponding weight coefficient.

[0015] Furthermore, the path planning module selects a path recommendation strategy according to the driver's driving style type: for aggressive drivers, priority is given to routes with good road conditions, high speed limits and fewer traffic restrictions; for cautious drivers, routes with small traffic flow and high road safety are selected; for stable drivers, a balanced path recommendation strategy is selected by comprehensively considering multiple factors such as speed, safety and comfort.

[0016] Furthermore, the path planning module is combined with traffic conditions. When recommending a route for a driver, if a certain route suits the driver's driving style but is currently in congestion, other relatively unobstructed routes will be selected for recommendation based on traffic forecast results. At the same time, considering the dynamic changes in traffic conditions, the traffic conditions are continuously monitored while the driver is driving, and the recommended route is adjusted in a timely manner.

[0017] Furthermore, the route planning module takes into account the needs of logistics transportation, and quantifies the suitability of the route for fragile goods through the cargo safety index when transporting fragile goods. The formula is: CSI = w fragility ×S roadCondition +w vibration ×V vibration, where w fragoility and w vibration is the weight coefficient, S roadConditiom Indicates the road condition quality score of the road section, which can be V vibration It indicates the vibration amplitude of the vehicle during driving. When choosing a route for transporting fragile goods, routes with higher CSI values ​​are preferred.

[0018] Furthermore, the path planning module takes into account the demand for logistics transportation. For large-scale cargo transportation, the route feasibility index is used to measure the suitability of the route for large-scale cargo. The formula is: RFI = w height ×H feasibility +w width ×W feasibility , where w height and w width is the weight coefficient, H feasibility Indicates the high feasibility of all sections on the route. If the section highly meets the cargo requirements, then H feasibility =1, otherwise 0, W feasibility Indicates the feasibility of the width of all sections on the route. Similarly, if the width of the section meets the cargo requirements, then W feasibility =1, otherwise it is 0. When planning a route, the route with an RFI value of 1 will be selected. If there is no route that fully meets the requirements, a route with a higher RFI value will be selected, and warning information will be provided when necessary to remind the driver to pay attention to possible restricted areas.

[0019] Furthermore, the dynamic adjustment of the recommended route in the path planning module continuously monitors the vehicle's position and driving status as well as changes in road traffic conditions through the on-board equipment and satellite positioning system during the driver's driving process. The on-board equipment uploads the vehicle's position information and driving speed data in real time, and the satellite positioning system provides high-precision positioning services while continuously receiving real-time traffic data. When it is found that the traffic conditions have changed and the driver deviates from the recommended route, a path adjustment decision is made. If the new situation has a greater impact on the current route, a better route will be re-planned, and path adjustment prompts will be sent to the driver in a timely manner through voice prompts of the on-board navigation system and push messages from mobile phone applications.

[0020] Furthermore, the feedback adjustment module calculates the path adjustment index to provide a specific adjustment direction for the path planning module, and the formula is: Among them, T a ctual is the actual driving time, T e xpected is the estimated driving time, F a ctual is the actual fuel consumption, F e xpected is the estimated fuel consumption satisfaction is the driver satisfaction score, w10、 w 11、 w 12 is the weight coefficient. When the RAI value is large, it indicates that the path planning module needs to be adjusted.

[0021] Compared with the existing technology, this intelligent logistics path optimization system based on big data has the following beneficial effects:

[0022] 1. The present invention can deeply analyze the driving style and behavioral characteristics of each driver by comprehensively collecting the driver's historical driving data, such as driving speed, braking frequency, and turning habits. This meticulous analysis of the driver's driving habits makes the route planning more in line with the driver's personal preferences. For example, for drivers with aggressive driving styles, the system intelligently recommends routes with superior road conditions and fewer traffic restrictions, which not only allows the driver to give full play to his driving speed advantage, but also satisfies his pursuit of speed and passion in driving experience to a certain extent. For drivers with cautious driving styles, the system is more inclined to recommend routes with small traffic flow and high road safety. Such personalized route recommendations greatly reduce the driving pressure of cautious drivers and improve their comfort and overall safety during driving.

[0023] 2. The present invention realizes personalized customization of route recommendations by accurately analyzing the driver's driving behavior. This customized route planning not only meets the driver's driving preferences, but also invisibly optimizes the efficiency and cost of logistics transportation. For example, for drivers who need to transport fragile and large goods, the system will intelligently screen out routes with high road quality, small vehicle vibration amplitude, or road width and height that meet the requirements of the goods according to the characteristics of the goods and the driver's driving style, thereby ensuring the safety and integrity of the goods. In addition, by real-time monitoring of traffic conditions and dynamically adjusting recommended routes, congested sections can be effectively avoided, unnecessary waiting time can be reduced, and the overall efficiency of logistics transportation can be further improved, reducing transportation costs.

[0024] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1Optimize the system process for intelligent logistics routing based on big data;

[0027] Figure 2 is the flowchart of the data analysis module;

[0028] Figure 3 Flowchart of the path planning module. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0030] Example 1: Transport of fragile items:

[0031] Data collection: Driver Xiao Li is responsible for transporting a batch of fragile glass products. Before the transportation, the system collects his historical driving data, including the average driving speed V, through the on-board equipment and Xiao Li’s mobile phone application. avg , Braking frequency F brake At the same time, through cooperation with the data interface of the traffic management department, the satellite positioning system and the third-party traffic data provider, real-time data on road congestion and the impact of weather conditions on traffic are obtained.

[0032] Data analysis, after cleaning and preprocessing Xiao Li’s historical driving data, the system calculates his driver behavior comprehensive index (DBl), according to the formula: Assume that Xiao Li's relevant parameters make the DBI value conform to the range of a robust driver, such as Xiao Li's average driving speed V avg Moderate, braking frequency F brake Normal, rapid acceleration times N accel Less, comprehensive index of turning range A t urn is also within a reasonable range, and the weight coefficients w1, w2, w3, and w4 are appropriate values. The road speed limit V limit is a reasonable value, the total travel time T total For a reasonable time, it is calculated that Xiao Li's DBI value meets the judgment criteria of a robust driver. For real-time traffic data, the congestion index (Cl) of each road section is calculated according to the formula: For example, for a main road leading to a destination, due to the heavy traffic volume, the relevant parameters make the calculated Cl value higher, which is consistent with the description of the road congestion level.

[0033] Route planning: The system loads electronic map data to build a road network model and preliminarily determines some possible routes from the departure point to the destination through the path potential index. Since Xiao Li is a steady driver, the system comprehensively considers and selects routes with good road conditions and moderate traffic flow. However, combined with logistics and transportation needs, since it is a fragile product, the cargo safety index (CSI) needs to be considered. For each possible route, according to the formula: CSI = w fragility ×S roadCondition +w vibration ×V vibration Calculate the CSI value. For example, if a route is short but has poor road surface flatness, the vehicle vibration amplitude may be large. Let w fragility w vibration For a reasonable weight, the road condition quality score S of the road section caused by poor road surface flatness is roadComditiom Low, vehicle driving vibration amplitude V vibration The calculated CSI value is lower. Although the other route is slightly longer, the road condition is good and the vibration amplitude is small. fragility、 w vibration The road condition quality score S of the road section is a reasonable weight. roadCondition Higher, vehicle driving vibration amplitude V vibration If it is lower, the CSI value is higher, and the system will eventually recommend routes with higher CSI values.

[0034] Feedback adjustment During the transportation process, the system continuously monitors the vehicle position and traffic conditions. If Xiao Li deviates from the recommended route for some reason, the system will re-plan the route according to the new position and traffic conditions and notify Xiao Li in time. After the transportation is completed, the system will record Xiao Li’s feedback on the recommended route, such as the actual driving time T actual 、Fuel consumption actual And Xiao Li’s satisfaction with the path S satisfaction Based on these feedback information, the system will calculate the path adjustment index (RAl) according to the formula: Assume the relevant weight coefficient w 10 、w 11 、w 12 is a reasonable value, if the actual driving time T actual Estimated time T expected There is a difference, the actual fuel consumption F actual Estimated fuel consumption F expected There is a difference. Xiao Li’s satisfaction with the path is S satisfaction The calculated RAI value is a reasonable value, which is consistent with the judgment of whether the path planning needs to be adjusted.

[0035] To sum up, in the fragile goods transportation embodiment, the various modules of the system work together, and the data collection collects the driving data and real-time traffic information of the driver Xiao Li. The data analysis module determines that Xiao Li is a stable driver by calculating DBI, and at the same time obtains the road congestion index CI. When planning the route, due to Xiao Li's stable style and the demand for fragile goods transportation, the road conditions and cargo safety index CSI are comprehensively considered to select the route, and the route with a high CSI value is recommended first. The system continuously monitors during the transportation process. If the driver deviates from the route, the route can be re-planned. After the transportation is completed, Xiao Li's feedback information is recorded through the feedback adjustment module, and the RAI value is calculated to provide a basis for optimizing the route planning for subsequent similar transportation, thereby ensuring the efficiency and safety of fragile goods transportation.

[0036] Embodiment 2:

[0037] Large cargo transportation:

[0038] Data collection: Driver Lao Wang drives a large truck to transport a batch of large mechanical equipment. The system also collects Lao Wang’s historical driving data and real-time traffic-related data.

[0039] After analyzing the data and calculating Lao Wang’s DBI value, we determined that he is an aggressive driver. According to the formula: DBI = Assume that Mr. Wang’s relevant parameters make the DBI value meet the criteria for determining an aggressive driver, such as Mr. Wang’s average driving speed V avg Faster, braking frequency F brake Relatively low number of rapid accelerations N accel More, the comprehensive index of turning range is A turn Moderate, weight coefficients w1, w2, w3, w4 are appropriate values, and the road speed limit V limit is a reasonable value, the total travel time T total For a reasonable time, we calculated that Lao Wang's DBI value meets the criteria for being an aggressive driver. We analyzed the real-time traffic data to obtain the Cl value and estimated travel time (ETT) of each road section. According to the formula: CI = w5× and Assume that the relevant parameters make the calculated Cl value and ETT value conform to the description of road congestion degree and estimated travel time. For example, the relevant parameters of a certain road section make w 5、 w6 is a reasonable weight, and the length of the congested road section is L congested , total section length L total , the number of vehicles on the road section N v ehicles and road area A r The oad parameter is consistent with the actual situation, and the calculated CI value is consistent with the description of the road congestion degree. Assuming that the length of the road section D is a reasonable value, the effective driving speed V effective According to the relevant formula, the possible delay time T delayis a reasonable value, and the calculated ETT value meets the description of the expected travel time.

[0040] Route planning: The system preliminarily determines some routes from the departure point to the destination. Since Lao Wang is an aggressive driver, he gives priority to roads with good conditions, high speed limits, and correct practices. He assigns reasonable parameter values ​​according to the actual situation and performs calculations and judgments based on the logic of the formula. This is the core of the entire embodiment. Considering that it is a large-scale cargo transportation, the appropriate route is selected based on the route feasibility index (RFI). For each possible route, according to the formula: RFI = w height ×H feasibility +w width ×W feasibility Calculate the RFI value. If the height limit of some sections of a route does not meet the cargo requirements, set w height , w width For a reasonable weight, if the height limit of some sections on the route does not meet the requirements, then H feasibility =0, the road section width meets the requirements, then W feasibility =1, the calculated RFI value meets the judgment of route feasibility; while all sections of the other route meet the height and width restrictions, let w height , W width is a reasonable weight, then H feasibility =1,W feasibility =1, the calculated RFI value meets the judgment of route feasibility. The system will give priority to routes with an RFI value of 1. If there is no route that fully meets the requirements, the system will choose a route with a higher RFI value and remind Lao Wang to pay attention to possible restricted areas.

[0041] Feedback adjustment: During the transportation process, if there are changes in traffic conditions, such as construction on the road ahead, the system will re-plan the route based on real-time data and notify Mr. Wang. After the transportation is completed, Mr. Wang’s policy and feedback will be collected to calculate the RAI value according to the formula: Assume the relevant weight coefficient w 10 、w 11 、w 12 is a reasonable value, if the actual driving time T a ctual and estimated driving time T e There are differences in expected and actual fuel consumption. actual Estimated fuel consumption F expected There is a difference. Mr. Wang’s satisfaction with the path is S satisfaction The calculated RAI value is a reasonable value, which is consistent with the judgment of whether the path planning needs to be adjusted.

[0042] To sum up, for the large-scale cargo transportation implementation example, the effectiveness of the system is also reflected. Data collection obtains the relevant data and traffic conditions of the driver Lao Wang. After data analysis, Lao Wang is judged as an aggressive driver. At the same time, the CI value and ETT of the road section are determined. The path planning takes into account Lao Wang’s driving style and large-scale cargo transportation requirements, and selects the route based on the route feasibility index RFI. The route with an RFI value of 1 is given priority. The route can be replanned if traffic changes occur during transportation. After the transportation is completed, the feedback adjustment module calculates the RAI value, and adjusts and optimizes the path planning algorithm based on Lao Wang’s feedback information to improve the accuracy and rationality of large-scale cargo transportation path planning and ensure smooth transportation.

[0043] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. Intelligent logistics path optimization system based on big data, characterized by: The system includes: a data acquisition module, a data analysis module, a path planning module, a feedback adjustment module and a user interface module; The data collection module: uses vehicle-mounted equipment and mobile phone applications to collect historical driving data on the driver's driving speed, acceleration, braking frequency, turning angle and speed, and idling time, and records the driver's daily driving route preferences and rest point selection information. Through cooperation with the data interface of the traffic management department, the satellite positioning system and third-party traffic data providers, it obtains real-time road congestion, traffic accident information, traffic control measures, construction section information, and weather conditions. The data analysis module cleans and preprocesses the collected historical driving data of the driver, removes outliers, noise data and standardizes the data, extracts characteristic data reflecting the driver's average driving speed, braking frequency, number of sudden accelerations and sharp turning angles from the preprocessed data, analyzes driving route preferences and rest time patterns, and uses the driver behavior comprehensive index to classify the driver's behavior characteristics. The calculation formula is: Among them, V avg is the average driving speed, V l imit is the road speed limit, F b rake is the braking frequency, T total is the total driving time, N accel is the number of rapid accelerations, A turn The comprehensive index of turning amplitude w1, w2, w3, and w4 are used as weight coefficients, and drivers are divided into aggressive, stable, and cautious types. The collected real-time traffic data is quickly processed and analyzed, key information is extracted, and the congestion index of each road section is calculated to determine the degree of congestion. The congestion index is: Among them, L congested is the length of the congested road section, L total is the total section length, N vehicles is the number of vehicles on the road section, A road is the road section area, w 5、 w6 is the weight coefficient. At the same time, by mining historical traffic data, the time prediction formula is used to predict the future travel time of each road section. The formula is: D× Veffe 1 ctive +T delay , where D is the length of the road section, V effective is the effective driving speed, T delay For possible delay time; The path planning module: loads detailed electronic map data, uses the map data to build a road network model, preliminarily determines the shortest path from the departure point to the destination through the path potential index, recommends a path based on the driver's driving style through a path recommendation strategy, optimizes the recommended path in combination with real-time traffic conditions, and further optimizes the path selection according to the needs of logistics transportation. During the driver's driving process, the vehicle's position, driving status, and changes in road traffic conditions are continuously monitored through the on-board equipment and satellite positioning system. When changes in traffic conditions are found and the driver deviates from the recommended path, dynamic adjustments are made based on real-time data; The feedback adjustment module: provides multiple channels for drivers to give feedback on their opinions and suggestions on the recommended routes, records the feedback information of drivers, extracts valuable data from the collected feedback information of drivers, calculates the route adjustment index according to the feedback information, provides specific adjustment directions for the route planning module according to the route adjustment index, establishes a regular data update mechanism, continuously learns the changes in drivers' behavior and the dynamic changes in traffic conditions, and automatically adjusts the algorithm parameters and recommendation strategies; The user interface module provides the driver with an intuitive and clear user interface, displays recommended routes, real-time traffic conditions, estimated arrival times, and fuel consumption estimates, uses map visualization technology to present route and traffic information to the driver, allows the driver to accept or reject recommended routes, set preferences, view historical driving records and feedback records through the user interface, and provides voice interaction functions.

2. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The data analysis module determines the driving style type of the driver by DBI value, performs statistical analysis on the DBI values ​​of all drivers, obtains their distribution, and determines the threshold value according to the percentile of the distribution. The drivers with DBI values ​​in the top x% are defined as aggressive, the drivers with DBI values ​​in the bottom y% are defined as cautious, and the drivers in the middle are defined as robust. The threshold values ​​are determined as T and T respectively. aggressive and T moderate , when DBI ≥ T a ggressive, the driver is aggressive; when T moderate ≤DBI <T aggressive , the driver is a stable type; when DBI <T moderate , the driver is cautious.

3. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The data analysis module counts the number of drivers in the night time period T night and peak hours T peak Number of driving times N night and N peak As well as driving characteristics, when classifying driving styles, the classification threshold is adjusted according to the driving characteristics of different time periods. For drivers who often drive at night, the night driving adjustment factor w is added when calculating the driver behavior comprehensive index DBI. night ×f(N night ), where f(N night ) is a function of the number of nighttime driving times: where λ is a tuning parameter.

4. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The path planning module preliminarily determines the shortest path from the departure point to the destination through the path potential index. Let G = (V, E) be a directed graph, where V is a vertex set and E is an edge set. For the starting point s and the end point t, the calculation formula of the path potential index is defined as: Where u is any vertex in the graph, d(u,s) represents the currently known shortest distance from vertex u to the starting point s, d(u,t) represents the estimated distance from vertex u to the end point t, α, β, γ are weight coefficients that can be adjusted according to actual conditions to balance the importance of the starting point distance, the end point distance and the path quality, F quality (u) is the path quality function of vertex u, and the function is: Where V l imit(u) is the speed limit of the road where vertex u is located, N vehicles (u) is the number of vehicles on the road, w 1、 w2 is the corresponding weight coefficient.

5. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The path planning module selects a path recommendation strategy according to the driver's driving style type: for aggressive drivers, priority is given to routes with good road conditions, high speed limits and fewer traffic restrictions; for cautious drivers, routes with small traffic flow and high road safety are selected; for stable drivers, a balanced path recommendation strategy is selected by comprehensively considering multiple factors such as speed, safety and comfort.

6. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The path planning module is combined with traffic conditions. When recommending a route for a driver, if a certain route suits the driver's driving style but is currently in congestion, other relatively unobstructed routes will be selected for recommendation based on traffic forecast results. At the same time, considering the dynamic changes in traffic conditions, the traffic conditions are continuously monitored while the driver is driving, and the recommended route is adjusted in a timely manner.

7. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The path planning module takes into account the needs of logistics transportation. When transporting fragile goods, the cargo safety index is used to quantify the suitability of the route for fragile goods. The formula is: CSI = w fragility ×S roadCondition +w vibration ×V vibration , where w fragoility and w vibration is the weight coefficient, S roadConditiom Indicates the road condition quality score of the road section, which can be V vibration It indicates the vibration amplitude of the vehicle during driving. When choosing a route for transporting fragile goods, routes with higher CSI values ​​are preferred.

8. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The path planning module takes into account the demand for logistics transportation. For large cargo transportation, the route feasibility index is used to measure the suitability of the route for large cargo. The formula is: RFI = w height ×H feasibility +w width ×W feasibility , where w height and w width is the weight coefficient, H feasibility Indicates the high feasibility of all sections on the route. If the section highly meets the cargo requirements, then H feasibility =1, otherwise 0, W feasibility Indicates the feasibility of the width of all sections on the route. Similarly, if the width of the section meets the cargo requirements, then W feasibility =1, otherwise it is 0. When planning a route, the route with an RFI value of 1 will be selected. If there is no route that fully meets the requirements, a route with a higher RFI value will be selected, and warning information will be provided when necessary to remind the driver to pay attention to possible restricted areas.

9. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The dynamic adjustment of the recommended route in the path planning module is that during the driver's driving, the vehicle's position and driving status as well as changes in road traffic conditions are continuously monitored through the on-board equipment and the satellite positioning system. The on-board equipment uploads the vehicle's position information and driving speed data in real time, and the satellite positioning system provides high-precision positioning services while continuously receiving real-time traffic data. When it is found that the traffic conditions have changed and the driver has deviated from the recommended route, a path adjustment decision is made. If the new situation has a greater impact on the current route, a better route will be re-planned, and path adjustment prompts will be sent to the driver in a timely manner through voice prompts of the on-board navigation system and push messages of mobile phone applications.

10. The intelligent logistics path optimization system based on big data according to claim 1 is characterized in that: The feedback adjustment module calculates the path adjustment index to provide a specific adjustment direction for the path planning module. The formula is: Among them, T a ctual is the actual driving time, T e xpected is the estimated driving time, F a ctual is the actual fuel consumption, F e xpected is the estimated fuel consumption satisfaction is the driver satisfaction score, w 10、 w 11、 w 12 is the weight coefficient. When the RAI value is large, it indicates that the path planning module needs to be adjusted.

Images