Big data analysis-based global intelligent route recommendation method and device, storage medium and server

Abstract

The invention discloses a global intelligent route recommendation method and device based on big data analysis, a storage medium and a server, and the method comprises the steps: obtaining transportation task information and an initial recommendation planning route corresponding to each vehicle type based on the transportation task information; according to the road network static influence factors and under the corresponding transportation tasks, obtaining a plurality of optimized recommended planning routes which are ranked from high to low according to the optimal cost under the optimal time condition and ranked from high to low according to the optimal time under the optimal cost condition from the initial recommended planning routes for a user to select; and performing real-time adjustment on the optimized recommended planning route selected by the user according to dynamic influence factors including the obtained real-time road condition and the loading and unloading estimated time to obtain the adjusted optimal recommended planning route for the user to perform real-time switching. The transportation time can be shortened, the vehicle turnover rate can be improved, the transportation cost can be saved, dangerous road sections can be avoided, and the distribution punctuality rate can be improved.

Description

Technical Field

[0001] This application relates to the field of logistics transportation route planning technology, and in particular to a method, device, storage medium and server for full-domain intelligent route recommendation based on big data analysis. Background Technology

[0002] Currently, freight drivers in the logistics sector mainly rely on driver experience or static map navigation to plan transportation routes. However, when faced with real-time traffic changes such as traffic congestion or unexpected events such as accidents, they often lack the ability to quickly and intelligently adjust routes. This can easily lead to delivery delays, vehicle damage, fuel waste, and increased costs. It can also negatively impact consumers' evaluation of on-time delivery, which is detrimental to the long-term development of transportation companies. Summary of the Invention

[0003] This application provides a method, device, storage medium, and server for intelligent route recommendation based on big data analysis. By centrally analyzing and processing various inherent and real-time factors affecting traffic safety, time, and cost, it recommends safer, more time-saving, and more cost-effective routes for users to choose from. The technical solution is as follows: In a first aspect, embodiments of this application provide a comprehensive intelligent route recommendation method based on big data analysis, characterized in that the method includes: Obtain transportation task information and initial recommended routes for each vehicle type based on the transportation task information. The transportation task information includes the starting point, waypoints, and destination. The initial recommended routes include routes based on human experience, historical trajectory routes, and electronic navigation routes determined based on several traffic strategies. Based on road physical constraints, and according to road network static influencing factors, several optimized recommended routes are obtained from the initial recommended routes under the corresponding transportation tasks. These routes are sorted from highest to lowest cost under the condition of optimal time, and from highest to lowest time under the condition of optimal cost. The road physical constraints include height, width, and weight restrictions for passing vehicles. The road network static influencing factors include road conditions and the number of lanes. For the optimized recommended route, the optimized recommended route selected by the user is adjusted in real time based on dynamic influencing factors such as real-time traffic conditions and estimated loading and unloading times, so as to obtain the adjusted optimal recommended route for the user to switch in real time.

[0004] Furthermore, the road conditions include at least the pavement condition, road slope, whether it is a narrow village road, the number of curves, and whether the road segment is a key safety concern section. Based on road physical constraints and according to static influencing factors of the road network, and under the corresponding transportation task, several optimized recommended routes are obtained from the initial recommended planned routes, sorted by cost from highest to lowest under optimal time conditions, and sorted by time from highest to lowest under optimal cost conditions, for the user to choose from. These include: Obtain information on road surface paving conditions, road slope, curve conditions, number of lanes, traffic hours, whether the road segment is a key safety concern section, and the weight of each information change on travel time and cost; Based on different vehicle types, the impact of changes in their respective weights on travel time and travel cost is obtained, and the impact on time is summed up separately, as is the impact on cost. Based on the combined effects of time and cost, the electronic navigation planning route is updated, and several optimized recommended routes are obtained again from the initial recommended planning routes, sorted from highest to lowest cost under the condition of optimal time, and sorted from highest to lowest time under the condition of optimal cost, for the user to choose from.

[0005] Furthermore, the method also includes issuing warnings for key safety-critical road sections, including long uphill and downhill sections, continuous curves, sections near water or cliffs, and accident hotspots, and increasing the weight of their impact on transportation time.

[0006] Furthermore, the real-time traffic conditions include at least real-time traffic flow, traffic accident information, weather data, road construction information, and temporary traffic control information; for the optimized recommended route, the optimized recommended route selected by the user is adjusted in real time based on dynamic influencing factors, including the acquired real-time traffic conditions and estimated loading and unloading times, to obtain the adjusted optimal recommended route for the user to switch between in real time, including: At regular intervals, obtain the change information of each influencing factor in real-time traffic conditions and the weight of each change information on the travel time. Obtain the impact of changes in each weight on travel time and travel cost, and then sum up the impact on time and the impact on cost respectively; The optimized recommended route is adjusted based on the sum of travel time and the corresponding cost, resulting in the optimal recommended route.

[0007] Furthermore, the method also includes storing the adjusted optimal recommended planning route, and training the historical adjusted optimal recommended planning route based on the same transportation task information and the same transportation task information using a machine learning algorithm to obtain updated historical trajectory routes, and updating the historical trajectory route database data.

[0008] Furthermore, the method also includes performing data preprocessing, including cleaning and deduplication, on the acquired initial recommended route data after obtaining the initial recommended route data, including: The system performs abnormal data removal operations on manual experience route data and historical trajectory route data, including removing routes with empty latitude and longitude information, removing license plate numbers that do not match the preset information, removing routes with zero total mileage, and removing routes with total mileage less than a threshold or total time of zero. For manually experienced route data, historical trajectory route data, and planned route data generated by electronic maps according to vehicle type and traffic strategies, deduplication is performed on data with the same route, vehicle type, and trajectory; and... The deduplicated route data from each source is sorted according to the following rules: data with the same route, the same vehicle type, and the same trajectory are sorted and a unique route is retained when the cost and time are the same.

[0009] Furthermore, the method also includes: Real-time vehicle location information and optimal recommended route planning; Determine whether the shortest distance between the vehicle's location information and the optimal recommended route is greater than a preset threshold. If it is greater than the preset threshold, then determine that the vehicle has veered off course. If the vehicle deviates from its course, the system obtains the user's deviation starting point data and short-term road condition data within a preset distance ahead of the deviation starting point, including traffic congestion, traffic accidents, sudden abnormal weather conditions, road construction information, and temporary traffic control information. If such conditions are present, the system reports and displays the short-term road condition data to determine the reasonableness of the user's deviation.

[0010] Secondly, embodiments of this application provide a comprehensive intelligent route recommendation device based on big data analysis, comprising: The initial recommended route acquisition unit is used to acquire transportation task information and initial recommended routes corresponding to each vehicle type based on the transportation task information. The transportation task information includes the starting point, waypoints and the destination. The initial recommended route includes routes based on human experience, historical trajectory routes and electronic navigation planning routes determined based on several traffic strategies. The optimized recommended route acquisition unit is used to acquire several optimized recommended routes from the initial recommended routes based on road physical constraints and road network static influencing factors, and under the corresponding transportation task. These routes are sorted from highest to lowest cost under the condition of optimal time, and from highest to lowest time under the condition of optimal cost, for the user to choose from. The road physical constraints include height, width, and weight restrictions for passing vehicles, and the road network static influencing factors include road conditions and the number of lanes. The optimal recommended route adjustment unit is used to adjust the user-selected optimal recommended route in real time based on dynamic influencing factors, including real-time traffic conditions and estimated loading and unloading times, to obtain the adjusted optimal recommended route for the user to switch between in real time.

[0011] Thirdly, embodiments of this application provide a computer storage medium storing a plurality of instructions adapted for loading by a processor and executing the above-described method steps.

[0012] Fourthly, embodiments of this application provide a server that may include a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to execute the above-described method steps.

[0013] The beneficial effects of the technical solutions provided in some embodiments of this application: By acquiring transportation task information and initial recommended routes corresponding to each vehicle type based on the transportation task information, the transportation task information includes the starting point, waypoints, and destination. The initial recommended routes include routes based on human experience, historical trajectory routes, and electronic navigation routes determined based on several traffic strategies. Based on road physical constraints, and according to road network static influencing factors, several optimized recommended routes are obtained from the initial recommended routes under the corresponding transportation task, sorted from highest to lowest cost under the condition of optimal time, and sorted from highest to lowest time under the condition of optimal cost, for the user to choose from. The road physical constraints include height, width, and weight restrictions for passing vehicles, and the road network static influencing factors include road conditions and the number of lanes. For optimized recommended routes, the system adjusts the user's selected optimized recommended routes in real time based on dynamic influencing factors, including real-time road conditions and estimated loading and unloading times. The adjusted optimal recommended routes are then available for users to switch between in real time, which can shorten transportation time, increase vehicle turnover, save transportation costs, avoid dangerous road sections, and improve on-time delivery rate. Attached Figure Description

[0014] To more clearly illustrate the technical solutions in the embodiments of this application 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 this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0015] Figure 1 This is a schematic diagram of the network architecture provided in the embodiments of this application; Figure 2 This is a schematic diagram of the method flow provided in the embodiments of this application; Figure 3 This is a schematic diagram of the device provided in this application; Figure 4 This is a schematic diagram of the structure of the storage medium provided in this application; Figure 5 This is a schematic diagram of the server structure provided in this application. Detailed Implementation

[0016] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0017] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0018] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the scope of the application. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0019] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0020] The following detailed description of some embodiments of this application is provided in conjunction with the accompanying drawings. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0021] It should be noted that all data involved in this application was obtained with the permission of the relevant users, complies with relevant policies and regulations, and will not infringe on user privacy.

[0022] It should also be noted that the big data analysis-based intelligent route recommendation method provided in this application is generally executed by a server, and correspondingly, the big data analysis-based intelligent route recommendation device is generally installed in the server.

[0023] Figure 1 An exemplary network architecture is shown that can be applied to the big data analytics-based intelligent route recommendation method or device for intelligent route recommendation based on big data analytics in this application.

[0024] like Figure 1 As shown, the network architecture may include: terminal device 101 and server 102. Terminal device 101 and server 102 can communicate with each other via the network, which serves as the medium for providing communication links between the various units. The network may include various types of wired or wireless communication links, such as: wired communication links including fiber optic cables, twisted-pair cables, or coaxial cables; and wireless communication links including Bluetooth communication links, Wi-Fi communication links, or microwave communication links.

[0025] It should be noted that the terminal device 101 and the server 102 can be either hardware or software. When the terminal device 101 and the server 102 are hardware, they can be implemented as a distributed server cluster consisting of multiple servers, or as a single server. When the terminal device 101 and the server 102 are software, they can be implemented as multiple software programs or software modules (for example, to provide distributed services), or as a single software program or software module; no specific limitations are made here.

[0026] The terminal device of this application can be equipped with various communication client applications, such as video recording applications, video playback applications, voice interaction applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0027] A terminal device can be either hardware or software. When the terminal device is hardware, it can be various terminal devices with a display screen, including but not limited to smartphones, tablets, laptops, and desktop computers. When the terminal device is software, it can be installed on the terminal devices listed above. It can be implemented as multiple software programs or software modules (e.g., used to provide distributed services) or as a single software program or software module; no specific limitation is made here.

[0028] When the terminal device is hardware, it can also be equipped with a display device and a camera. The display device can be any device capable of displaying information, and the camera is used to capture video streams. For example, the display device can be a cathode ray tube display (CR), a light-emitting diode display (LED), an e-ink screen, a liquid crystal display (LCD), a plasma display panel (PDP), etc. Users can use the display device on the terminal device to view displayed text, images, videos, and other information.

[0029] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is for illustrative purposes only. Depending on implementation needs, there can be any number of terminal devices, networks, and servers.

[0030] The following will be combined with the appendix Figure 2 This paper provides a detailed description of the intelligent route recommendation method based on big data analysis provided in the embodiments of this application. Specifically, the intelligent route recommendation device based on big data analysis in the embodiments of this application can be... Figure 1 The server shown.

[0031] Please see Figure 2 This document presents a flowchart illustrating a comprehensive intelligent route recommendation method based on big data analysis, as provided in this embodiment of the application. Figure 2 As shown, the method described in this application embodiment may include the following steps: S201. Obtain transportation task information and initial recommended routes for each vehicle type based on the transportation task information. The transportation task information includes the starting point, waypoints, and destination. The initial recommended routes include routes based on human experience, historical trajectory routes, and electronic navigation routes determined based on several traffic strategies.

[0032] In the freight industry, vehicle types are categorized into seven types based on cargo weight: van, small truck, medium truck (2), large truck (5.2), large truck (7.6), large truck (9.6), and tractor-trailer. After a customer places an order, the cargo weight is determined based on the order details, and different vehicle types are matched accordingly. Furthermore, after obtaining the customer's pickup (loading) and delivery (unloading) points, the origin and destination information of the vehicles is obtained. Based on the vehicle type's cargo allocation and scheduling, several transit points (transfer points) can be set between the origin and destination. After obtaining the complete transportation task information, including vehicle type, origin, transit points, and destination, an initial recommended route is selected from manual experience routes, historical routes, and electronic navigation routes based on several traffic strategies. The system includes two main components: Manually drawn routes (manually marked on a map by drivers or maintenance personnel and stored in the server's routing backend) and historical routes (data from previous periods including routes with the same starting point, waypoints, and destination, for example, routes where all vehicle types, starting points, waypoints, and destinations are identical to the current vehicle type, starting point, waypoints, and destination within 30 days). Electronic navigation routes are planned by the electronic map according to the starting point, waypoints, and destination. In this embodiment, when planning routes on the electronic map, different vehicle types can be considered, and the following five strategies can be used: toll avoidance, no road conditions + avoid highways, highway priority, no road conditions + speed priority, and intelligent recommendation. For example, the planning strategy for small trucks is: small truck + no road conditions + speed priority; the planning strategy for large trucks (7.6L) is: large truck (7.6L) + no road conditions + avoid highways; and the planning strategy for vans is: van + toll avoidance, etc. Each vehicle type can select a suitable travel strategy based on its specific circumstances to plan a route appropriate for that vehicle type. However, when recommending actual routes, it is necessary to distinguish between highways, national roads, provincial roads, county roads, and rural roads, and to determine the appropriate vehicle type. For example, heavy vehicles generally do not travel on rural roads.

[0033] In some embodiments, after obtaining data including human experience routes, historical trajectory routes, and electronic navigation planning routes based on several traffic strategies, each route will have duplicate data or data lacking necessary conditions. The existence of this data will increase the amount of data processing and affect the accuracy of the data. Therefore, it is necessary to clean and deduplicatize the obtained initial recommended planning route data.

[0034] In some embodiments, after obtaining the initial recommended route planning data, data preprocessing, including cleaning and deduplication, is performed on the obtained initial recommended route planning data, including: The system performs deduplication on manually experienced route data and historical trajectory route data. Specifically, it removes routes with empty latitude and longitude information, vehicles with license plate numbers that do not match presets, vehicles with zero total mileage, vehicles with total mileage less than a threshold, or vehicles with zero total time. For example, license plates with the keywords "external" and "X" should be removed, and vehicles with a total mileage of less than 10km should also be removed.

[0035] For manually experienced route data, historical trajectory route data, and electronic navigation planned route data generated by electronic maps according to vehicle type and traffic strategies, deduplication is performed based on the similarity of routes, vehicle types, and trajectories. During deduplication, an overlap threshold can be set for each type of route. When the overlap meets this threshold, the route is considered duplicated, and one route is selected for selection. For example, for manually experienced route data, if the overlap of two or more routes is greater than 98%, it is considered duplicated. For historical trajectory routes, if the overlap of two or more routes is greater than 92%, it is considered duplicated. For electronic navigation planned routes, if the overlap of two or more routes is greater than 98%, it is considered duplicated, and one of the duplicated routes is selected for retention.

[0036] The deduplicated route data from each source is then merged and deduplicated again. Specifically, data with the same route, vehicle type, and trajectory are uniquely retained based on a ranking system: lowest cost, lowest time when costs are equal, and randomly selected route when costs and time are equal. This process yields several initial recommended routes with different route configurations. In other words, human experience route data, historical trajectory route data, and electronic navigation planned route data are placed in a route pool as a database source. From this database, routes with the same vehicle type, route, or trajectory are selected as a group. Within this group, routes are uniquely retained based on a ranking system: lowest cost, lowest time when costs are equal, and randomly selected route when costs and time are equal. The rest are discarded. For example, if a route in the route pool has the same route, vehicle type, or trajectory, and there is one route in the manual experience route pool, one in the historical trajectory route pool, and one in the electronic navigation planned route pool, then the cost of traversing these three routes is first determined. If the lowest cost route exists, it is selected and retained, while the other two are discarded. If the costs of the manual experience route, the historical trajectory route, and the electronic navigation planned route are all the same, then the time taken by the three routes is determined, and the route with the shortest time is retained. If both cost and time are the same, then one route is randomly selected and the other two are discarded. Following this method, through layers of filtering, it is ensured that only one route represents the same vehicle type, route, or trajectory. Ultimately, the route pool contains routes with different route types, i.e., several initially recommended planned routes. This statistical, processing, and deduplication method based on big data makes the basis for optimal route recommendations more objective, reliable, and accurate, and more suitable for actual needs.

[0037] S202. Based on road physical constraints, and according to the static influencing factors of the road network, several optimized recommended routes are obtained from the initial recommended routes under the corresponding transportation tasks. These routes are sorted from highest to lowest cost under the condition of optimal time, and from highest to lowest time under the condition of optimal cost, for the user to choose from. The road physical constraints include height, width, and weight restrictions for passing vehicles. The static influencing factors of the road network include road conditions and the number of lanes.

[0038] Road physical constraints are mandatory conditions that all vehicle types must adhere to. After meeting these constraints, the impact of static road network factors on time and cost is evaluated. The main function of optimized recommended routes is to provide users with more efficient and convenient route suggestions from origin to destination. Its core objective is to continue saving time and resources, while considering the impact of various static road network factors on transportation time and cost to ensure the rationality and efficiency of route selection. By obtaining information on the impact of these static road network factors on the planned route, the travel time and cost of vehicles can be more accurately determined.

[0039] In some embodiments, it is necessary to obtain the combined impact of various static factors of the road network, such as road conditions and number of lanes, on travel time and cost. The method of obtaining this information may include statistically analyzing the weights of the impact of various factors, such as road conditions and number of lanes, on travel time and cost, and then summing up their respective impacts on time and cost based on their respective weights to obtain the overall impact on time and cost.

[0040] In some embodiments, the road conditions include at least the pavement condition, road slope, curve condition, and whether the road segment is a key safety concern section. Based on road physical constraints and according to static influencing factors of the road network, several optimized recommended routes are obtained from the initial recommended routes under the corresponding transportation task, sorted by cost from highest to lowest under optimal time conditions, and sorted by time from highest to lowest under optimal cost conditions, for the user to choose from. These include: Obtain information on road surface paving conditions, road slope, curve conditions, number of lanes, traffic hours, whether the road segment is a key safety concern section, and the weight of each information change on travel time and cost; Based on different vehicle types, the impact of changes in their respective weights on travel time and travel cost is obtained, and the impact on time is summed up separately, as is the impact on cost. Based on the combined effects of time and cost, the electronic navigation planning route is updated, and several optimized recommended routes are obtained again from the initial recommended planning routes, sorted from highest to lowest cost under the condition of optimal time, and sorted from highest to lowest time under the condition of optimal cost, for the user to choose from.

[0041] Specifically, firstly, it is necessary to determine the baseline average speed. For example, the baseline average speed for highways is 100 km / h, for national highways it is 60 km / h, and for county roads it is 40 km / h. The average speed can be based on the speed limit set by the government for the corresponding road section under normal circumstances. At the average speed, the average travel cost can be correlated. For example, the unit fuel consumption at the average speed on national highways can be used as the standard for cost calculation. When encountering changes in road surface gradient, fuel consumption will increase or decrease accordingly. Simultaneously, changes in travel time can also directly affect costs. Additionally, relevant road condition information can be obtained through various public channels, such as professional websites related to highway resource management and publicly available testing information from highway bridge and pavement testing institutions. For instance, relevant management resource websites provide various highway pavement-related materials, including contract texts, production operation contracts, and construction specification atlases. By utilizing publicly available road information from professional websites, testing agencies, and traffic management departments, and through big data analysis, relevant information such as road surface paving, road slope, curves, and number of lanes is extracted and its changes are monitored regularly. In addition, traffic planning information for different time periods, reminders on whether a road segment is a key safety concern section, and its changes can be obtained from traffic management departments. Finally, different weights are assigned based on the changes.

[0042] The impact of each factor must be considered, taking into account both its weight on cost and its weight on time. Based on the average speed of different road segments, the weight of the number of lanes versus the number of lanes on transportation time differs. The impact on transportation time can be adjusted by setting weights for the number of lanes and their respective effects. For example, using an average of 4 lanes as a baseline, when the number of lanes increases to 8, the weight of the impact on travel time in the following segment is determined. For instance, it might reduce the baseline travel time for that segment by 6%. When the number of lanes increases to 2, the travel time might increase by 8%, and fuel consumption might increase by 5%. Another example is segmenting the travel time into peak hours, holidays, and other time periods, and considering each segment separately. The weight of the impact of this time period on travel time and fuel consumption; as for the impact of road slope on travel time, for example, if the road slope is 5% higher than the original road surface, the speed should be reduced to 80% of the original driving speed, and the fuel consumption will increase by 5% accordingly. Regarding the road paving conditions, for example, uneven gravel or dirt roads will increase transportation time compared to asphalt roads. The weight of the impact of uneven gravel or dirt roads on time is different from that of asphalt roads. The impact of different road materials on transportation time and fuel consumption can be obtained, and the weight of the impact of different road materials on transportation time and fuel consumption can be set according to the impact. The impact of curves on transportation time varies. The weighting of these impacts on transportation time and cost can be adjusted based on the complexity of the curve. For example, a single curve on a road segment might have a 10% weighting on time and a 5% weighting on fuel consumption. However, if there are two serpentine curves, the weighting on time might increase to 20%, and the weighting on fuel consumption might increase to 10%. Adjusting the weighting of time and cost impacts based on curve complexity allows for more accurate estimations of transit time and toll costs. In this embodiment, even on highly complex road segments, the impact on transportation time and cost can be accurately estimated. Regarding the impact of this, it should be noted that whether a road segment is a key safety concern segment and the impact of changes in this information on time should also be considered. For example, the weight of the impact on time differs between straight sections near water and curved sections near water; the weight of the impact on time for curved sections near water is greater than that for straight sections near water. In addition, the weight of the impact of the aforementioned static road network factors on transportation time also differs depending on the vehicle type. Based on different vehicle types, adjustments should be made according to the multi-dimensional static road network factors and the impact of their changes on travel time and cost, thereby optimizing the recommended planned route.

[0043] As described above, at regular intervals, such as every 3 days or 1 week, it is determined whether the static influencing factors have changed. Based on the combined effects of these changes on time and cost, the electronic navigation route is updated. Several optimized recommended routes are then obtained from the initial recommended routes, sorted by cost from highest to lowest under optimal time conditions, and by time from highest to lowest under optimal cost conditions, for the user to choose from. During this process, users can set preferences according to their individual needs, such as avoiding toll roads, highways, or specific types of road conditions through personalized filtering and settings. They can also specify departure or arrival times to optimize their trip arrangements.

[0044] S203. For the optimized recommended route, the optimized recommended route selected by the user is adjusted in real time based on dynamic influencing factors such as real-time traffic conditions and estimated loading and unloading time, so as to obtain the adjusted optimal recommended route for the user to switch in real time.

[0045] Real-time traffic conditions include at least real-time traffic flow, traffic accident information, weather data, road construction information, and temporary traffic control information. Real-time traffic flow, traffic accident information, road construction information, temporary traffic control information, and hazardous road conditions such as landslides and rockfalls can be obtained from traffic cameras, sensors, and real-time traffic data released by traffic management departments. Weather data can be obtained from connected weather forecast software, and environmental factors can be referenced from data released by environmental protection departments.

[0046] Step S202 of this application, based on road physical constraints, comprehensively statistically analyzes and considers big data on static influencing factors of the road network, and estimates and adjusts the transportation time for different vehicle types. However, these static influencing factors are based on the inherent physical properties of the road, while uncontrollable dynamic influencing factors during transportation can directly affect the total transportation time and cost. Unexpected situations can lead to delayed arrivals. Furthermore, the loading and unloading time at transit points also needs to be estimated based on the cargo volume. To achieve optimal time control, this embodiment uses big data to acquire dynamic factors covering all time-influencing factors during transportation, and performs precise calculations and reasonable avoidance of these dynamic factors. By deeply integrating real-time traffic data, such as congestion, slow traffic, and road closures due to construction, into the planned route calculation, and dynamically adjusting the estimated travel time for road segments, more accurate estimates of travel time and cost can be made, thus making the recommended planned route more reliable and controllable.

[0047] In some embodiments, the process of adjusting the user-selected optimized recommended route in real time based on dynamic influencing factors, including real-time traffic conditions and estimated loading and unloading times, to obtain an adjusted optimal recommended route for the user to switch between in real time includes: At regular intervals, obtain the change information of each influencing factor in real-time traffic conditions and the weight of each change information on the travel time. Obtain the impact of changes in each weight on travel time and travel cost, and then sum up the impact on time and the impact on cost respectively; The optimized recommended route is adjusted based on the sum of travel time and the corresponding cost, resulting in the optimal recommended route.

[0048] Specifically, it is first necessary to obtain the travel time under normal traffic flow conditions, clear weather conditions, no traffic accidents, no road construction conditions, no temporary traffic control, and no waypoints. Then, it is necessary to obtain the weights of different congestion conditions on time, the types and number of traffic accidents on time, the weights of different weather conditions such as light rain, heavy rain, snow, freezing, and heavy fog on time, the weights of road construction length and quantity on time, and the weights of temporary traffic control and the weights of temporarily controlled road sections on time. For example, the weights of the same road segment and time period on time during light rain are different from those during snow. It is also possible to obtain the weights of the weight or quantity of loaded / unloaded goods and the number of waypoints on time. When planning routes, for transportation tasks with multiple waypoints, the Vehicle Routing Problem (VRP) algorithm can be used to automatically optimize the access order, significantly reducing total mileage, time, and empty mileage.

[0049] Once all uncontrollable dynamic influencing factors and their weighted impact on time are obtained, their respective weights are calculated and then summed to obtain the total time and cost of the entire recommended route based on these dynamic factors. It's important to note that cost calculations require precise calculations based on the travel time of each road segment, combined with vehicle fuel / electricity consumption models and the degree of influence of both static and dynamic factors. This includes accurately calculating the toll fees for highways, bridges, and tunnels to find the most time-efficient, most cost-effective, or a balance between these two factors. By analyzing and calculating the impact of dynamic factors, including real-time traffic conditions and estimated loading / unloading times, on transportation time and cost based on big data, the recommended routes can be more realistic, safer, more accurate, and faster, significantly reducing transportation costs.

[0050] In some embodiments, the method further includes storing the adjusted optimal recommended planning route, and training the historical adjusted optimal recommended planning route based on the same transportation task information and the same transportation task information using a machine learning algorithm to obtain updated historical trajectory routes, and updating the historical trajectory route database data.

[0051] When providing the optimal recommended route to users for navigation, monitoring deviations can immediately detect abnormal driving behavior by the driver. It can also detect if there are other reasons for the deviation. If no other reasons are found, the driver is reminded to return to the correct route, thereby reducing additional fuel consumption and time loss caused by deviations and directly lowering operating costs. If the optimal route is unreasonable due to untimely information acquisition by the system, or if other reasons exist, further investigation is needed to determine the cause of the deviation in order to make an objective evaluation of it.

[0052] In some embodiments, the big data analytics-based intelligent route recommendation method further includes: Real-time vehicle location information and optimal recommended route planning; Determine whether the shortest distance between the vehicle's location information and the optimal recommended route is greater than a preset threshold. If it is greater than the preset threshold, then determine that the vehicle has veered off course. If the vehicle deviates from its course, the system obtains the user's deviation starting point data and short-term road condition data within a preset distance ahead of the deviation starting point, including traffic congestion, traffic accidents, sudden abnormal weather conditions, road construction information, and temporary traffic control information. If such conditions are present, the system reports and displays the short-term road condition data to determine the reasonableness of the user's deviation.

[0053] The system acquires the user's yaw start point data and data within a preset distance range ahead of the yaw start point. This preset distance range should not be too far and can be selected according to the actual situation. For example, it can be set to allow yaw to avoid traffic congestion 1 kilometer ahead, or to allow appropriate yaw to detour when there is road construction 500 meters ahead. If the distance exceeds the preset range, by the time the user arrives at the location, the influencing factors may have already been eliminated, thus losing reference value and making it impossible to make a reasonable evaluation of the yaw.

[0054] In some embodiments, the big data-based intelligent route recommendation method further includes: the method also includes issuing warnings for key safety-critical road sections, including long uphill and downhill sections, continuous curves, sections near water or cliffs, and accident hotspots, increasing their weight on the impact on transportation time. The adjusted optimal recommended route is then readjusted. During the readjustment, the optimal recommended route is determined again starting from the vehicle's location point, following the methods described above for both optimized and optimal route planning.

[0055] These methods significantly reduce operating costs by avoiding congestion, minimizing detours and idling, effectively reducing fuel consumption, vehicle maintenance costs, and overall transportation costs. They also substantially improve timeliness, enhancing customer satisfaction and corporate reputation. Furthermore, they enable efficient vehicle and driver scheduling, increasing asset utilization, reducing reliance on additional capacity, and strengthening emergency response capabilities. This allows for rapid response to unforeseen circumstances, automatic planning of alternative routes, and ensures the stability and reliability of the supply chain.

[0056] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0057] Please see Figure 3 This illustration shows a schematic diagram of a comprehensive intelligent route recommendation device based on big data analysis provided in an exemplary embodiment of this application, hereinafter referred to as device 3. Device 3 can be implemented as all or part of a server through software, hardware, or a combination of both. Device 4 includes: 301. Initial recommended route acquisition unit, used to acquire transportation task information and initial recommended routes corresponding to each vehicle type based on the transportation task information. The transportation task information includes the starting point, waypoints and the destination. The initial recommended route includes human experience routes, historical trajectory routes and electronic navigation planning routes determined based on several traffic strategies. 302. An optimized recommended planning route acquisition unit is used to acquire, based on road physical constraints and according to road network static influencing factors, several optimized recommended planning routes from the initial recommended planning routes under the condition of optimal time and optimal cost from high to low, and under the condition of optimal cost and optimal time from high to low, for the user to choose from. The road physical constraints include height, width and weight restrictions on passing vehicles, and the road network static influencing factors include road conditions and number of lanes. 303. Optimal Recommended Route Adjustment Unit, used to adjust the optimized recommended route selected by the user in real time based on dynamic influencing factors including real-time road conditions and estimated loading and unloading times, to obtain the adjusted optimal recommended route for the user to switch between in real time.

[0058] It should be noted that the device 3 provided in the above embodiments, when executing the big data-based intelligent route recommendation method, is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the above functions. Furthermore, the big data-based intelligent route recommendation device and the big data-based intelligent route recommendation method embodiments provided in the above embodiments belong to the same concept, and their implementation process is detailed in the method embodiments, which will not be repeated here.

[0059] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0060] See Figure 4 The diagram shown is a schematic of a computer storage medium provided in an embodiment of this application. The computer storage medium 400 can store multiple instructions (i.e., Figure 4 The computer program 401 shown above, the instructions of which are adapted to be loaded and executed by a processor as described above. Figure 2 The method steps of the illustrated embodiment can be found in the following documentation for detailed execution. Figure 2 The specific details of the illustrated embodiments will not be elaborated here.

[0061] This application also provides a computer program product that stores at least one instruction, which is loaded and executed by the processor to implement the big data analysis-based intelligent route recommendation method as described in the above embodiments.

[0062] Please see Figure 5 This provides a schematic diagram of a server structure for an embodiment of this application. For example... Figure 5 As shown, the server 102 may include: at least one processor 1021, at least one network interface 1024, a user interface 1023, a memory 1025, and at least one communication bus 1022.

[0063] The communication bus 1022 is used to realize the connection and communication between these components.

[0064] The user interface 1023 may include input units such as a mouse and a keyboard.

[0065] The network interface 1024 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0066] The processor 1021 may include one or more processing cores. The processor 1021 connects to various parts of the server 102 via various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1025, and by calling data stored in the memory 1025. Optionally, the processor 1021 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1021 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 1021 and may be implemented as a separate chip.

[0067] The memory 1025 may include random access memory (RAM) or read-only memory. Optionally, the memory 1025 may include a non-transitory computer-readable storage medium. The memory 1025 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1025 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1025 may also be at least one storage device located remotely from the aforementioned processor 1025. Figure 5 As shown, the memory 1025, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and application programs.

[0068] exist Figure 5In the server 102 shown, the user interface 1023 is mainly used to provide an input interface for the user and obtain the user input data; while the processor 1021 can be used to call the application program stored in the memory 1025 and specifically execute, such as Figure 2 The method shown can be referred to for details. Figure 2 As shown, it will not be elaborated further here.

[0069] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory, or random access memory, etc.

[0070] The above-disclosed embodiments are merely preferred embodiments of this application and should not be construed as limiting the scope of this application. Therefore, any equivalent variations made in accordance with the claims of this application shall still fall within the scope of this application.

Claims

1. A global intelligent route recommendation method based on big data analysis, characterized in that, The method comprises: acquiring transportation task information and initial recommended planning routes corresponding to each vehicle model based on the transportation task information, the transportation task information including a starting point, passing points and a terminal point, and the initial recommended planning routes including an artificial experience route, a historical trajectory route and an electronic navigation planning route determined based on a plurality of traffic strategies; based on road physical constraint conditions, according to road network static influence factors and in the corresponding transportation task, acquiring a plurality of optimization recommended planning routes from the initial recommended planning routes, the optimization recommended planning routes being sorted in descending order of cost optimality under time optimality and in descending order of time optimality under cost optimality for user selection, the road physical constraint conditions including height, width and weight limits for passing vehicles, and the road network static influence factors including road conditions and the number of lanes; for the optimization recommended planning routes, real-time adjustment is made to the optimization recommended planning route selected by the user according to the acquired real-time road conditions and dynamic influence factors including estimated loading and unloading time, to obtain an adjusted optimal recommended planning route for real-time switching by the user.

2. The global intelligent route recommendation method based on big data analysis according to claim 1, characterized in that, The road conditions at least include road pavement conditions, road slope, whether it is a narrow village road, bend conditions and whether the road section is in a key safety attention road section; based on the road physical constraint conditions, according to the road network static influence factors and in the corresponding transportation task, acquiring a plurality of optimization recommended planning routes from the initial recommended planning routes, the optimization recommended planning routes being sorted in descending order of cost optimality under time optimality and in descending order of time optimality under cost optimality for user selection, comprises: acquiring road pavement conditions, road slope, bend conditions, the number of lanes, traffic periods, information whether the road section is in a key safety attention road section and the weight of the change of each information on the passing time and cost; based on different vehicle models, acquiring the influence of the change of each weight on the passing time and cost, and respectively superimposing the influence on time and the influence on cost; according to the superimposed results of the influence on time and the superimposed results of the influence on cost, updating the electronic navigation planning route, and again acquiring a plurality of optimization recommended planning routes from the initial recommended planning routes, the optimization recommended planning routes being sorted in descending order of cost optimality under time optimality and in descending order of time optimality under cost optimality for user selection. 3.The global intelligent route recommendation method based on big data analysis of claim 2, wherein: The method further comprises warning the key safety attention road sections including long uphill and downhill road sections, continuous bends, water and cliff areas and accident black spots in the road conditions, and increasing the weight of their influence on transportation time. 4.The global intelligent route recommendation method based on big data analysis of claim 1, wherein, The real-time road conditions at least include real-time traffic flow, traffic accident conditions, weather data, road construction information and temporary regulation information; for the optimization recommended planning routes, real-time adjustment is made to the optimization recommended planning route selected by the user according to the acquired real-time road conditions and dynamic influence factors including estimated loading and unloading time, to obtain an adjusted optimal recommended planning route for real-time switching by the user, comprising: acquiring the change information of each influence factor in the real-time road conditions and the weight of the change information of each influence factor on the passing time every certain time interval; Obtain the influence of respective weight changes on the passing time and the passing cost, and superimpose the influence on the time and the influence on the cost respectively; Adjust the optimal recommended planning route according to the superimposed results of the passing time and the superimposed results of the corresponding cost, to obtain the optimal recommended planning route. 5.The global intelligent route recommendation method based on big data analysis of claim 4, wherein, The method further comprises: Storing the adjusted optimal recommended planning route, and training the same transportation task information and the historical adjusted optimal recommended planning route based on the same transportation task information by a machine learning algorithm to obtain an updated historical trajectory route, and updating the historical trajectory route library data. 6.The global intelligent route recommendation method based on big data analysis of claim 1, wherein, After obtaining the initial recommended planning route data, the obtained initial recommended planning route data is preprocessed, including cleaning and deduplication, including: The artificial experience route data, historical trajectory route data are subjected to an abnormal data elimination operation including elimination of empty route latitude and longitude information, elimination of vehicle license plate number not matching the preset, elimination of zero total mileage, and elimination of total mileage less than a threshold value or total time consumption being zero; The artificial experience route data, historical trajectory route data and planning route data generated by the electronic map according to the vehicle type and the passing strategy are subjected to respective source trajectory coincidence degree deduplication operation according to the same route, the same vehicle type and the same trajectory; and The route data after deduplication in each source is subjected to a fusion operation of retaining only one unique route by sorting the data with the same route, the same vehicle type and the same trajectory according to the rule of minimum cost, minimum time consumption when the cost is the same, and randomly retaining one when the cost and the time consumption are the same. 7.The global intelligent route recommendation method based on big data analysis of claim 1, wherein, The method further comprises: Real-time acquisition of the positioning information of the vehicle and the optimal recommended planning route; Judging whether the shortest distance between the positioning information of the vehicle and the optimal recommended planning route is greater than a preset threshold value, and when it is greater than the preset threshold value, it is judged that the vehicle has deviated; If the vehicle deviates, obtain the deviation starting point data of the user and the short-term road condition data within a preset distance range in front of the deviation starting point, including whether it includes traffic congestion, traffic accident situation, sudden abnormal weather situation, road construction information, temporary control information, if it includes, report and display the short-term road condition data to judge the rationality of the user's deviation. 8.A global intelligent route recommendation device based on big data analysis, characterized in that, Comprise: An initial recommended planning route acquisition unit is configured to acquire transportation task information and initial recommended planning routes corresponding to each vehicle type based on the transportation task information, the transportation task information including a starting point, a passing point and a terminal point, and the initial recommended planning routes including artificial experience routes, historical trajectory routes and electronic navigation planning routes determined based on a plurality of passing strategies; An initial recommended planning route acquisition unit is configured to acquire transportation task information and initial recommended planning routes corresponding to each vehicle type based on the transportation task information, the transportation task information including a starting point, a passing point and a terminal point, and the initial recommended planning routes including artificial experience routes, historical trajectory routes and electronic navigation planning routes determined based on a plurality of passing strategies; The optimization recommended planning route obtaining unit is configured to obtain, based on road physical constraint conditions, a plurality of optimization recommended planning routes from the initial recommended planning routes according to road network static influence factors and under corresponding transportation tasks, the optimization recommended planning routes being sorted in descending order of cost optimality under time optimality and in descending order of time optimality under cost optimality for user selection, the road physical constraint conditions including height, width and weight limits for passing vehicles, and the road network static influence factors including road conditions and lane numbers; The optimal recommended planning route adjusting unit is configured to adjust, for the optimization recommended planning routes, the optimization recommended planning route selected by the user in real time according to obtained dynamic influence factors including real-time road conditions and loading / unloading estimated time, to obtain an adjusted optimal recommended planning route for real-time switching by the user.

9. A computer storage medium, characterized in that The computer storage medium stores a plurality of instructions adapted to be loaded and executed by the processor to perform the method steps of any one of claims 1-7.

10. A server, characterized by The computer storage medium stores a plurality of instructions adapted to be loaded and executed by the processor to perform the method steps of any one of claims 1-7. The computer storage medium stores a plurality of instructions adapted to be loaded and executed by the processor to perform the method steps of any one of claims 1-7.

Images