Big data processing method and system for smart traffic, storage medium and equipment

Abstract

The invention discloses a smart traffic big data processing method and system, a storage medium and equipment, and relates to the technical field of data processing. The method comprises the following steps: acquiring activity reservation information of a target area in a preset time period, wherein the activity reservation information comprises an activity place, an activity estimated number of people and an activity time range; determining a scheduling strategy of a target vehicle set based on the activity estimated number of people and the activity time range; predicting a traffic information graph of the target area in the activity time range, wherein the traffic information graph comprises traffic information of all traffic roads with the activity place as the center and the preset length as the radius; determining a driving route and a standby route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and a scheduling strategy; and generating a comprehensive scheduling map of the target vehicle set in the target time range based on the driving route and the standby route corresponding to each target vehicle. By implementing the technical scheme provided by the invention, the effectiveness of vehicle scheduling during large-scale activities is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and specifically to a big data processing method, system, storage medium and device for smart transportation. Background Art

[0002] With the acceleration of urbanization, large-scale events are frequently held, which has brought tremendous pressure to urban traffic. Especially during large-scale events such as sports games and concerts, a large number of people flock to a specific area in a short period of time, which can easily cause traffic congestion, affecting citizens' travel and urban operation efficiency. In order to cope with this situation, it is usually necessary to dispatch a large number of vehicles for personnel evacuation.

[0003] At present, traffic guarantee plans for large-scale events are mainly formulated based on manual experience. Traffic management departments usually pre-arrange a certain number of vehicles to run at fixed times and fixed routes based on the scale and location of the event. However, due to the uncertainty of the event and the fluctuation in the number of participants, as well as the lack of accurate prediction of traffic conditions during the event, it is easy for vehicle scheduling to not match actual demand, resulting in low effectiveness of vehicle scheduling during large-scale events. Summary of the invention

[0004] The present application provides a big data processing method, system, storage medium and device for smart transportation, which improves the effectiveness of vehicle scheduling during large-scale events.

[0005] In a first aspect, the present application provides a method for processing big data of smart transportation, the method comprising: Obtaining event reservation information in a target area during a preset time period, wherein the event reservation information includes the event location, the estimated number of participants in the event, and the event time range; Determine a scheduling strategy for a target vehicle set based on the estimated number of people at the activity and the time range of the activity; Predicting a traffic information map of the target area within the activity time range, the traffic information map including traffic information of all traffic roads with the activity location as the center and a preset length as the radius; Determine the driving route and the backup route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and the dispatching strategy; Based on the driving routes and backup routes corresponding to each of the target vehicles, a comprehensive dispatch map of the target vehicle set within the target time range is generated.

[0006] By adopting the above technical solution, by obtaining the activity reservation information of the target area in the preset time period, key information such as the activity location, the estimated number of people for the activity, and the activity time range can be mastered in advance, and then the scheduling strategy of the target vehicle set can be formulated based on the estimated number of people for the activity and the activity time range, so as to achieve the precise matching of vehicle scheduling with actual needs. At the same time, by predicting the traffic information map centered on the activity location in the target area within the activity time range, combining the scheduling strategy to plan the driving route and alternative routes for each target vehicle, and finally generating a comprehensive scheduling map, the vehicle scheduling plan has forward-looking and flexibility, effectively avoiding the problem of inefficient vehicle scheduling caused by the uncertainty of the activity and the fluctuation of the number of participants. This solution realizes the scientific and systematic vehicle scheduling by obtaining the activity information in advance and accurately predicting the traffic conditions, and significantly improves the effectiveness of vehicle scheduling during large-scale events.

[0007] In a second aspect of the present application, a big data processing system for smart transportation is provided, the system comprising: An activity information acquisition module is used to acquire activity reservation information in a target area during a preset time period, wherein the activity reservation information includes the activity location, the estimated number of people in the activity, and the activity time range; A scheduling strategy determination module, used to determine the scheduling strategy of the target vehicle set based on the estimated number of people in the activity and the time range of the activity; A traffic information prediction module, used to predict a traffic information map of the target area within the activity time range, wherein the traffic information map includes traffic information of all traffic roads with a radius of a preset length and the activity location as the center; A vehicle route determination module, used to determine the driving route and alternate route corresponding to each target vehicle in the target vehicle set based on the traffic information map and the dispatching strategy; The dispatch map generation module is used to generate a comprehensive dispatch map of the target vehicle set within the target time range based on the driving routes and backup routes corresponding to each of the target vehicles.

[0008] In a third aspect of the present application, a computer storage medium is provided, wherein the computer storage medium stores a plurality of instructions, wherein the instructions are suitable for being loaded by a processor and executing the above method steps.

[0009] In a fourth aspect of the present application, an electronic device is provided, comprising: a processor and a memory; wherein the memory stores a computer program, and the computer program is suitable for being loaded by the processor and executing the above-mentioned method steps.

[0010] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By obtaining the activity reservation information of the target area in the preset time period, this application can grasp the key information such as the activity location, the estimated number of people for the activity, and the activity time range in advance, and then formulate the scheduling strategy of the target vehicle set based on the estimated number of people for the activity and the activity time range, so as to achieve the precise matching of vehicle scheduling with actual needs. At the same time, by predicting the traffic information map centered on the activity location in the target area within the activity time range, combining the scheduling strategy to plan the driving route and backup route for each target vehicle, and finally generating a comprehensive scheduling map, the vehicle scheduling plan has forward-looking and flexibility, and effectively avoids the problem of inefficient vehicle scheduling caused by the uncertainty of the activity and the fluctuation of the number of participants. This solution realizes the scientific and systematic vehicle scheduling through the early acquisition of activity information and accurate prediction of traffic conditions, and significantly improves the effectiveness of vehicle scheduling during large-scale events. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 It is a flowchart of a big data processing method for smart transportation provided by an embodiment of the present application; Figure 2 This is a module diagram of a big data processing system for smart transportation provided by an embodiment of the present application; Figure 3 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application.

[0012] Description of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. DETAILED DESCRIPTION

[0013] In order to enable technicians in this field to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0014] In the description of the embodiments of the present application, words such as "for example" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "for example" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "for example" or "for example" is intended to present related concepts in a specific way.

[0015] In the description of the embodiments of the present application, the meaning of the term "multiple" refers to two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "include", "comprise", "have" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0016] The following will provide a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments.

[0017] Please refer to Figure 1 , a flowchart of a method for processing big data of smart transportation is proposed. The method can be implemented by a computer program, can be implemented by a single-chip microcomputer, or can be run on a big data processing system for smart transportation. The computer program can be integrated in a computer device or can be run as an independent tool application. Specifically, the method includes steps 10 to 50, and the steps are as follows: Step 10: Obtain activity reservation information for the target area during a preset time period, the activity reservation information including the activity location, estimated number of people for the activity, and the activity time range.

[0018] In the embodiment of the present application, the target area refers to a specific urban area where traffic scheduling is required, and the area includes one or more places where large-scale events can be held, such as a stadium, a convention center, a concert hall, etc.

[0019] In the embodiment of the present application, the preset time period refers to a fixed time period used for statistics and planning of vehicle scheduling, which may be a specific time period such as a day, a week or a month, during which one or more large-scale events may be held.

[0020] In the embodiment of the present application, event reservation information refers to the activity information pre-registered at various activity venues in the target area within a preset time period, including the location of the event, the expected number of participants, and the specific start and end time of the event, etc., which is used for subsequent vehicle scheduling planning.

[0021] Specifically, since large-scale events often require advance application and approval, event reservation information can be obtained through the event management system of the target area. The event management system will receive event applications reported by various event venues (such as stadiums, convention centers, concert halls, etc.), which include basic information such as event location, expected number of participants, and event time. The system first classifies these event applications into large-scale event applications and small-scale event applications, and focuses on those event applications where the estimated number of participants exceeds the preset number of participants (for example, 1,000 people) or the event venue is located in a preset congestion area. For these key target events, the system will further obtain their detailed event reservation information, including specific event venue information (such as venue capacity, entrance and exit locations), detailed event time arrangements (such as opening time, end time, peak flow prediction), and more accurate number of people prediction (such as time-based attendance prediction). The event reservation information obtained in this way is more comprehensive and accurate, providing a reliable data basis for the subsequent formulation of targeted vehicle scheduling strategies, avoiding the information bias that may be caused by relying solely on experience-based predictions, and thus better meeting the traffic evacuation needs during the event.

[0022] Based on the above embodiment, as an optional embodiment, the step of obtaining the activity reservation information of the target area in the preset time period may further include the following steps: Step 101: Receive activity applications reported by various activity venues in the target area.

[0023] Specifically, the activity management system receives activity applications submitted by various activity venues in the target area. The activity venue managers need to fill in the activity-related information through the system's preset application interface, including basic data such as the activity name, activity type, venue information, expected number of participants, and activity time. The system will standardize these application information to ensure that the data format is unified and complete, which is convenient for subsequent classification processing.

[0024] Step 102: Classify the activity applications to obtain large-scale activity applications and small-scale activity applications, and determine the number of participants and activity locations for each large-scale activity.

[0025] Specifically, the collected event applications are intelligently classified by first setting classification standards. For example, an event with an estimated number of participants exceeding 1,000 people is initially classified as a large event application, and an event with an estimated number of participants below 1,000 people is classified as a small event application. At the same time, the system will also consider other characteristics of the event for comprehensive judgment, such as the duration of the event, the type of event (such as sports events, concerts, exhibitions, etc.), the capacity of the venue, and other factors, so as to determine the number of participants and specific event location information for each large event.

[0026] Step 103: An activity with a larger number of participants than a preset number of participants and / or an activity location within a preset congestion area is taken as a target activity, and activity reservation information corresponding to the target activity is obtained.

[0027] Specifically, after completing the initial classification, the system will further screen and determine the target activities that need to be focused on. The system will automatically mark activities with more than a preset number of participants (such as 2,000 people) as target activities. At the same time, the system has a preset list of congested areas. When the activity location is located in these congested areas, even if the number of participants does not reach the preset number, it will be marked as a target activity. For these identified target activities, the system will further obtain more detailed activity reservation information, including in-depth information such as the site layout, crowd flow forecasts by time period, and the distribution of surrounding transportation facilities. This multi-level screening and information acquisition mechanism ensures that the system can prioritize the allocation of transportation resources to activities that most need transportation guarantees, thereby improving the accuracy of traffic scheduling and the efficiency of resource utilization.

[0028] Step 20: Determine the scheduling strategy for the target vehicle set based on the estimated number of people participating in the activity and the time range of the activity.

[0029] The target vehicle set in this embodiment of the application refers to a collection of vehicles that can be used to provide capacity support for large-scale events, including but not limited to: bus fleets of transportation companies that have signed event capacity support agreements in advance, flexibly deployed taxi fleets, chartered vehicle service fleets that cooperate with event organizers, etc. These vehicles are dispatchable, that is, they can be flexibly deployed as needed during the event.

[0030] In the embodiment of this application, the dispatch strategy refers to a detailed operation plan formulated for the target vehicle set, including but not limited to: the number of vehicles that need to be dispatched (such as 20 buses and 50 taxis that need to be dispatched based on the estimated number of people at the event), the time arrangement of various types of vehicles (such as arriving at the designated area in batches 2 hours and 1 hour before the event), the vehicle assembly location (such as parking lots, temporary sites, etc.), the task allocation plan (such as some vehicles are responsible for connecting the event location to the subway station, and some vehicles are responsible for cross-regional transportation), etc. The dispatch strategy will make differentiated arrangements based on the capacity characteristics and dispatch flexibility of different types of vehicles to achieve the optimal configuration of capacity resources.

[0031] Specifically, based on the estimated number of people in the event, the required capacity allocation requirements can be calculated. The estimated number of people in the event can be allocated according to the proportion of different travel modes through the preset capacity allocation model. For example, if it is estimated that 30% of the people in an event of 1,000 people need to be transported by special vehicles, the specific number of people who need to be transported is 300. Then, based on the passenger capacity of different types of vehicles (such as 40 people / bus, 4 people / taxi) and the feasibility of scheduling, the number of various types of vehicles that need to be dispatched is calculated, and a certain proportion of mobile capacity is reserved for emergency situations. Then, based on the time range of the event, a specific vehicle scheduling schedule is formulated. For example, the peak hours of passenger flow before and after the event are first analyzed. For example, for a concert starting at 19:30, there may be a peak in entry at 18:00-19:00 and a peak in departure at 22:30-23:30. Based on these time nodes, the system will formulate batch scheduling plans for the target vehicle set, such as arranging 60% of the transport capacity to arrive at the designated area 30 minutes before the peak of entry, and the remaining 40% of the transport capacity will be supplemented in batches to ensure that the transport capacity supply matches the flow of people. At the same time, the system will also plan specific assembly locations and operation routes for the target vehicle set based on the geographical characteristics of the event venue. For example, the system will select a parking lot or temporary station at an appropriate distance from the event venue as the vehicle assembly location, and plan the optimal operation route based on road conditions.

[0032] Based on the above embodiment, as another optional embodiment, the step of determining the scheduling strategy of the target vehicle set based on the estimated number of people in the activity and the activity time range may also include the following steps: Step 201: Obtain historical vehicle dispatch data for the same type of activities, and determine the peak period within the activity time range based on the historical vehicle dispatch data.

[0033] Specifically, historical vehicle dispatch data of the same type as the current event is obtained from the historical database. These historical data include information such as event scale, time distribution, and vehicle dispatch records. For example, for a concert, the system will extract the dispatch data of concerts held in the same or similar venues in the past six months. The system uses data analysis algorithms to extract the peak time points of vehicle usage from these historical data, thereby identifying the peak time periods during the event when vehicle demand is most likely to surge.

[0034] Step 202: Calculate the number of target vehicles required for each peak period and the departure information of each target vehicle according to the estimated number of people attending the activity.

[0035] Specifically, after determining the peak time period, the system calculates the target number of vehicles required for each peak time period based on the estimated number of people in the event. When calculating specifically, first allocate the estimated number of people in the event to each peak time period according to the time period distribution ratio in the historical data. For example, if historical data shows that 40% of the audience usually needs to be transported one hour before the concert starts, and 60% of the audience needs to be transported at the end, then the system will calculate the actual vehicle demand for each time period according to this ratio. Then, based on the passenger capacity of different types of target vehicles, the system calculates the number of various types of vehicles required to meet the capacity demand. At the same time, the system will also generate specific departure information for each target vehicle, including departure time, estimated arrival time, driving route, etc. The generation of these departure information will take into account actual factors such as the vehicle's operating speed and road conditions.

[0036] Step 203: Integrate the number of target vehicles and the departure information of each target vehicle into a scheduling strategy for the target vehicle set.

[0037] Specifically, the calculated target vehicle quantity information and the specific departure information of each vehicle are finally integrated to form a complete scheduling strategy. This scheduling strategy includes both the macro-level vehicle quantity configuration plan and the micro-level specific vehicle scheduling arrangements. For example, the scheduling strategy will clearly stipulate that 15 buses will be dispatched to assembly point A 90 minutes before the start of the concert, and another 10 buses will be dispatched to assembly point B 60 minutes before the start of the concert, and the specific departure time and route of each vehicle will be listed in detail. Through this precise calculation and overall arrangement based on historical data, the system can more accurately predict and meet the demand for vehicles during the event, and improve the accuracy and efficiency of vehicle scheduling.

[0038] Step 30: Predict a traffic information map of the target area within the activity time range, the traffic information map including traffic information of all traffic roads with the activity location as the center and a preset length as the radius.

[0039] Specifically, the prediction range is drawn with the geographic coordinates of the activity location as the center and a preset length (for example, 3 kilometers) as the radius, and all traffic road information within the range is retrieved, including infrastructure information such as road grade, number of lanes, and traffic light distribution. Subsequently, multiple data sources are integrated to predict traffic conditions, including: historical traffic data for the same period (such as regular traffic flow from 18:00 to 20:00 on weekdays), weather forecast data (such as the impact of rainfall on traffic speed), real-time road conditions data in the surrounding area (collected through electronic police, surveillance cameras and other equipment), historical traffic impact data of similar activities, etc. The system uses machine learning algorithms to input these data into a preset prediction model to generate traffic information prediction results at various time points within the activity time range. The prediction results include key indicators such as expected road traffic flow, average driving speed, and congestion level.

[0040] In the embodiment of the present application, a spatiotemporal sequence prediction model based on deep learning is used to predict traffic conditions. The prediction model adopts a graph neural network structure to construct the road network of the target area as a directed graph, in which road nodes and road sections are used as nodes of the graph, and the connection relationship between roads is used as the edge of the graph. Each node contains multidimensional feature information, such as road grade, number of lanes, historical traffic data, etc.; each edge contains attribute information such as turn permission and signal light duration. The input layer of the prediction model receives the node feature matrix and adjacency matrix, and extracts the spatial correlation characteristics of the road network through multi-layer graph convolution operations. At the same time, the model also includes a temporal feature extraction module, which uses a long short-term memory network (LSTM) structure to process the historical traffic data sequence of each node to capture the time evolution law of traffic flow. The output layer of the model fuses the spatial features and the temporal features through a fully connected layer to generate traffic status prediction values ​​for each road section within the target time range. During the training process of the prediction model, the real traffic data collected during the historical activities is used as training samples, and the model parameters are optimized through the back propagation algorithm. The model also sets an attention mechanism, which can adaptively adjust the weights of different input features and highlight the impact of key factors on the prediction results. Through this deep learning-based prediction method, the system can accurately capture the complex spatiotemporal dependencies in the road network and provide more reliable traffic prediction results.

[0041] Based on the above embodiment, as another optional embodiment, the step of predicting the traffic information map of the target area within the activity time range may further include the following steps: Step 301: Obtain historical traffic information of a target area in each preset historical time period, and determine a target historical time period corresponding to an activity time range.

[0042] Specifically, first, based on the nature and time characteristics of the activity, the historical traffic information of the target area in the preset time period is obtained from the historical database. These preset time periods can include weekday time periods (such as the morning peak 7:00-9:00 and evening peak 17:00-19:00 from Monday to Friday), weekend time periods (such as 10:00-12:00 and 14:00-16:00 on Saturday and Sunday), and special holiday time periods (such as 9:00-21:00 on May 1st Labor Day and National Day). The historical traffic information includes data such as traffic volume, average speed, and congestion index in each preset time period. According to the specific time of the event to be held, the target historical time period closest to it is determined. For example, for a concert scheduled to be held at 19:30 on Friday night, the system will match it to the two historical time periods of "Friday evening peak 17:00-19:00" and "Friday night 19:00-21:00", because these time periods are closest to the event time in terms of periodicity and traffic characteristics. Through this time period matching, the system can use the traffic data of the target historical period as the basis for prediction.

[0043] Step 302: Divide an area with a preset length as a radius and the activity location as the center into a target traffic area.

[0044] Specifically, a circular target traffic area is constructed with the geographic coordinates of the activity location as the center and a preset length (such as 3 kilometers) as the radius. The system divides the circular area into multiple hexagonal grid units, each with a side length of 300 meters. This division method not only ensures the uniformity of coverage density, but also facilitates subsequent traffic analysis and path planning. Each hexagonal grid unit is assigned a unique area number, and records basic data such as road information and intersection information contained in the unit. For example, a grid unit numbered A001 may include a 500-meter main road section, a 300-meter secondary road section, and two traffic light intersections. Through this refined regional division, the system can more accurately analyze and predict the traffic conditions in local areas, providing a more detailed spatial reference for subsequent traffic forecasts and vehicle scheduling.

[0045] Step 303: Determine the initial traffic information of all traffic roads in the target traffic area based on the historical traffic information corresponding to the target historical period.

[0046] Specifically, the historical traffic information of the target historical period is extracted as the basis for determining the initial traffic information of each road in the target traffic area. The system performs statistical analysis on the historical traffic information and calculates key indicators such as the average traffic volume, average driving speed and congestion index of each road during the period. For example, for trunk road A, the system extracts its historical data during the peak hours on Friday night and obtains initial traffic information with an average traffic volume of 800 vehicles / hour and an average driving speed of 35 kilometers / hour.

[0047] Step 304: Acquire weather information and road construction information of the target traffic area within the target time range, and modify the initial traffic information of each traffic road based on the weather information and road construction information to generate a traffic information map.

[0048] Specifically, the weather forecast information and road construction information within the target time range are obtained. The weather information includes meteorological elements such as precipitation, visibility, and wind force level. The system adjusts the initial traffic information according to the preset weather influencing factors. For example, when the forecast shows that there will be moderate to heavy rain (rainfall of 15-25 mm per hour) on the day of the activity, the system will reduce the road capacity by 20% and the average driving speed by 30%. At the same time, the system obtains road construction information released by the traffic management department, including construction location, construction scope, lane occupancy, etc. When road construction is detected in the target traffic area, the system will adjust the capacity of the affected section according to the degree of construction impact. For example, if construction occupies one lane, the capacity of the section will be reduced by 40%. The corrected traffic information is integrated to generate a traffic information map, and the traffic conditions of each section are intuitively displayed in a graded coloring manner. For example, green is used to indicate smooth traffic (average speed greater than 40 km / h), yellow is used to indicate mild congestion (average speed 25-40 km / h), and red is used to indicate severe congestion (average speed less than 25 km / h). Through this dynamic correction and visual presentation method, the traffic information map can more accurately reflect the actual road traffic conditions during the event and provide a reliable basis for vehicle scheduling decisions.

[0049] Step 40: Determine the driving route and backup route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and the dispatching strategy.

[0050] Specifically, the improved Dijkstra algorithm is used for path planning, and the traffic information graph is converted into a weighted directed graph, in which factors such as segment length, predicted travel time, road grade and congestion level are integrated into segment weights. For each target vehicle, the system first calculates the optimal driving route that meets the time requirements based on its departure time and destination specified in the scheduling strategy. During the path search process, the system not only considers the static properties of the segment, but also conducts a comprehensive evaluation in combination with the dynamic traffic conditions in the traffic information graph. For example, when the system finds that a segment on the shortest distance route may be severely congested during the predicted period, it will automatically adjust the path selection and give priority to alternative routes that are slightly longer but have smoother traffic. At the same time, the system will also plan 2-3 backup routes for each optimal driving route. The overlap rate of these backup routes with the main driving route is controlled below 30%, ensuring that when an emergency occurs on the main route, it can quickly switch to the backup route. In order to improve the reliability of route planning, the system has also established a segment scoring mechanism. For each road section, the system scores it by comprehensively considering factors such as its historical traffic reliability, the distribution of rescue resources along the route, and the accessibility of alternative roads. For example, although a main road is the shortest, its score will be reduced due to the lack of available alternative roads along the route and the historical traffic records show that it is often congested, thereby reducing the probability of this road section being selected in route planning.

[0051] Based on the above embodiment, as another optional embodiment, the step of determining the driving route and the backup route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and the scheduling strategy may further include the following steps: Step 401: extracting the traffic volume, average speed and road grade of each traffic road from the traffic information map.

[0052] Specifically, basic information of traffic roads is extracted from the collected traffic information map, such as the traffic volume, average speed and road grade information of each traffic road. Traffic volume refers to the number of vehicles passing through the road per unit time, average speed refers to the average speed of vehicles on the road, and road grades include expressways, main roads, secondary roads and branch roads.

[0053] Step 402: Calculate the congestion coefficient of each traffic road according to the traffic volume and the average vehicle speed, and set the road section weight of each traffic road in combination with the road grade.

[0054] Specifically, based on the extracted basic information, the congestion coefficient of each traffic road is calculated. The congestion coefficient can be calculated by the ratio of traffic volume to average speed. The specific calculation formula is: congestion coefficient = traffic volume / average speed. The larger the congestion coefficient, the more congested the road is and the more difficult it is to pass. The introduction of the congestion coefficient can objectively reflect the actual traffic conditions of the road and provide a basis for the subsequent establishment of the traffic cost matrix.

[0055] Combined with the road grade information, the road section weights of each traffic road are set. High-grade roads usually have greater traffic capacity, so they are given smaller weights; low-grade roads have relatively smaller traffic capacity and are given larger weights. For example, the weights of expressways, main roads, secondary roads, and branch roads can be set to 0.2, 0.4, 0.6, and 0.8, respectively. The introduction of road section weights can reflect the differences in traffic difficulty of roads of different grades.

[0056] Step 403: A road travel cost matrix is ​​established based on the congestion coefficient and the road section weight. The road travel cost matrix includes the travel time and travel difficulty of each traffic road.

[0057] Specifically, after obtaining the congestion coefficient and road section weight, a road travel cost matrix is ​​established. The travel cost matrix contains two dimensions: travel time and travel difficulty. The travel time can be calculated based on the road length and average vehicle speed. The travel difficulty is determined by the congestion coefficient and road section weight. The specific calculation formula is: travel difficulty = congestion coefficient × road section weight. By establishing the travel cost matrix, the travel cost of each traffic road can be fully reflected.

[0058] Step 404: According to the road traffic cost matrix, a driving route and an alternative route are planned for each target vehicle using the minimum cost principle.

[0059] Specifically, after obtaining the road traffic cost matrix, in order to scientifically and reasonably plan the driving route for the target vehicle, it is necessary to establish a road connectivity relationship diagram that reflects the actual road connectivity. This relationship diagram not only contains the connection relationship between each traffic road, but also contains the turning information at the intersection, such as whether left turn is allowed, whether U-turn is allowed, etc. By establishing a road connectivity relationship diagram, it can be ensured that the planned driving route meets the actual road traffic requirements.

[0060] Based on the established road connectivity graph, the minimum cost principle is used to plan the driving route for the target vehicle. Specifically, all feasible paths that meet the turning information requirements are searched in the road connectivity graph, and the total cost of each path is calculated. The total cost is composed of the travel time and difficulty of each section on the path. Selecting the path with the minimum total cost as the driving route can maximize the traffic efficiency while ensuring safe passage.

[0061] In order to prevent the impact of traffic congestion on driving in advance, it is necessary to conduct a risk assessment on the planned driving route. Specifically, the sections on the driving route with a congestion coefficient greater than the preset congestion coefficient threshold are marked as high-risk sections. These high-risk sections may be severely congested during actual driving, resulting in a significant decrease in traffic efficiency, so alternative routes need to be planned in advance.

[0062] After determining the high-risk sections, in order to ensure the feasibility of the alternative routes, parallel sections or adjacent sections are selected as alternative sections at the starting point of the high-risk sections. When selecting alternative sections, the difference in the travel cost between the alternative sections and the corresponding high-risk sections is required to be less than the preset value to ensure that the travel efficiency of the alternative route is not significantly lower than the original driving route. By selecting appropriate alternative sections, reliable section selection can be provided for the subsequent generation of alternative routes. After obtaining the alternative sections, at least two complete alternative routes are generated based on these alternative sections. These alternative routes need to meet two conditions: one is that they do not pass through the marked high-risk sections, and the other is that they constitute a complete path from the starting point to the end point. By generating multiple alternative routes, multiple detour options can be provided for the target vehicle, and the driving route can be switched in time when traffic congestion actually occurs to avoid being stuck in congested sections.

[0063] For example, assume that within the target area, a driving route needs to be planned for a target vehicle from point A to point B. The area contains multiple roads of different levels, including an east-west main road M1, two east-west secondary roads S1 and S2, and multiple connecting roads C1, C2 and C3. Extract the basic information of each road from the traffic information map. For example, the traffic volume of the main road M1 is 1,200 vehicles / hour, and the average speed is 40 kilometers / hour; the traffic volume of the secondary road S1 is 800 vehicles / hour, and the average speed is 35 kilometers / hour; the traffic volume of the secondary road S2 is 600 vehicles / hour, and the average speed is 30 kilometers / hour. The congestion coefficients of these roads are calculated as follows: M1 is 30 (1200 / 40), S1 is about 22.9 (800 / 35), and S2 is 20 (600 / 30). The weight of the road section is set according to the road grade. The weight of the main road M1 is set to 0.4, and the weight of the secondary roads S1 and S2 is set to 0.6. Based on this, the travel difficulty of each road is calculated: M1 is 12 (30×0.4), S1 is about 13.7 (22.9×0.6), and S2 is 12 (20×0.6). At the same time, the travel time is calculated based on the road length and average speed, so as to establish a complete road travel cost matrix.

[0064] A road connectivity graph is established based on the travel cost matrix. For example, left and right turns are allowed at the intersection of M1 and C1, while only right turns are allowed at the intersection of S1 and C2. Assuming that the congestion coefficient threshold is set to 25, the section of the main road M1 with a congestion coefficient of 30 is marked as a high-risk section.

[0065] When planning the driving route, the system finds that there are multiple feasible paths from point A to point B: Path 1 is "A-M1-C2-B", Path 2 is "A-S1-C2-B", and Path 3 is "A-S2-C3-B". By calculating the total cost of each path, assuming that the total cost of path 1 is the smallest, it is selected as the preferred driving route. Since path 1 contains a high-risk section (a section of M1), an alternative section needs to be selected. The system finds that the secondary trunk road S1 is parallel to M1, and the difference between its cost and M1 is within the preset range, so S1 is selected as the alternative section. Two alternative routes are generated based on S1: Alternative Route 1 is "A-S1-C2-B", and Alternative Route 2 is "A-S1-C3-B". In the actual driving process, if M1 is detected to be severely congested, the vehicle can switch to Alternative Route 1 or Alternative Route 2 before reaching the high-risk section to avoid the congested section and continue driving. For example, when the vehicle reaches the C1 section and finds that the M1 ahead is congested, it can turn to S1 via C1 and then continue along the alternative route 1 to the destination B.

[0066] Step 50: Based on the driving routes and backup routes corresponding to each target vehicle, a comprehensive dispatch map of the target vehicle set within the target time range is generated.

[0067] Specifically, after planning the driving routes and backup routes for each target vehicle, in order to achieve the coordinated dispatch of multiple vehicles, a comprehensive dispatch map within the target time range needs to be generated. This comprehensive dispatch map not only contains the route information of each target vehicle, but also needs to consider the temporal and spatial relationship between vehicles to avoid path conflicts or aggravate road congestion.

[0068] First, determine the set of vehicles within the target time range. For example, in the morning peak time range of 7:00-9:00, the system obtains the travel demand of 100 target vehicles, each of which has its planned departure time, expected arrival time, and planned driving route and alternate route. This information constitutes the basic data of the comprehensive dispatch map. Then divide the target time range into several time segments, such as a time segment of 5 minutes. In each time segment, count the expected number of vehicles on each road. Specifically, according to the driving route and time schedule of each target vehicle, calculate their road position in each time segment. For example, in the time segment of 7:30-7:35, there may be 15 target vehicles driving on the main road M1, of which 10 vehicles drive along the original route and 5 vehicles choose alternate routes due to road congestion. In order to avoid some roads being too crowded in a specific time period, the system will set a road capacity threshold. When the expected number of vehicles on a road in a certain time segment exceeds the threshold, the system will automatically adjust the driving time of some vehicles or suggest them to choose an alternate route. For example, when the system predicts that the traffic volume on the main road M1 between 8:00 and 8:05 will exceed the road capacity threshold, it will recommend that some vehicles planning to pass through M1 during this period depart earlier or later, or choose alternative routes.

[0069] In the process of generating a comprehensive dispatch map, the system also needs to consider the actual capacity of each road section and the historical congestion patterns. For example, a certain intersection is often congested during the morning rush hour. The system will reserve a certain amount of time during dispatching to avoid chain delays of subsequent vehicles due to minor delays. At the same time, the system will also pay attention to the load of the backup route to ensure that when the main route is congested, the backup route still has sufficient capacity to accommodate the transferred traffic. The final generated comprehensive dispatch map is a dynamic, multi-dimensional information carrier. It not only shows the distribution of each target vehicle in different time segments, but also includes the real-time load status of the road network and potential congestion risks. Dispatchers can make traffic control decisions based on this map, such as notifying relevant vehicles in advance to activate backup routes when it is predicted that a certain section of the road is about to be congested.

[0070] Based on the above embodiment, as another optional embodiment, the big data processing method of smart transportation may also include the following process: Specifically, in order to ensure the execution effect of the planned route and respond to changes in road conditions in a timely manner, the system needs to monitor and dynamically adjust the actual driving status of the target vehicle in real time. Specifically, the real-time location information of each target vehicle can be obtained through the vehicle-mounted equipment or mobile terminal, and then the actual driving trajectory of the vehicle is generated. The system compares and analyzes the actual driving trajectory with the pre-planned driving route and calculates the trajectory deviation value.

[0071] When the system detects that the actual driving trajectory of the target vehicle deviates from the planned driving route, and the deviation distance exceeds the first preset distance (for example, 500 meters), it is necessary to send route deviation warning information to the vehicle in time. The warning information may include current location information, deviation distance, recommended return route, etc. For example, when a vehicle originally planned to travel along the main road M1, but the actual driving trajectory shows that it has entered the parallel secondary road S1, and the deviation distance reaches 300 meters, the system will send a warning message to the vehicle, prompting it that it has deviated from the planned route and provide navigation suggestions to return to M1. At the same time, the system will monitor the traffic conditions of the driving section where the target vehicle is in real time. When it is detected that the real-time congestion coefficient of a certain section exceeds the first preset threshold (for example, the congestion coefficient is greater than 25), the system will actively push the backup route information to the target vehicle on the section. For example, when the system detects that the real-time congestion coefficient of a certain section of the main road M1 rises to 30, it will push the pre-planned backup route (such as suggesting to turn to the secondary road S1 to continue driving) to the vehicle on the section to help the vehicle avoid the congested section in time.

[0072] Furthermore, the actual traffic conditions of the target vehicles are statistically analyzed, and the actual traffic time, actual driving route, actual traffic difficulty and other information of each vehicle are specifically recorded. These actual traffic information are compared with the traffic information expected in the comprehensive dispatch map to generate deviation information. For example, if it is found that the actual traffic time of most vehicles on a certain section of road is 20% longer than the expected time, or if the section that was originally expected to be unobstructed is actually often congested, these deviation information will be recorded. Based on the collected deviation information, the system corrects and updates the road traffic cost matrix. For example, if the statistical data shows that the actual congestion level of a certain section of road in a specific time period continues to be higher than expected, the system will increase the traffic difficulty weight of the section in that time period accordingly; if the actual traffic effect of a certain alternative route is better than expected, its priority in route planning may be adjusted. Through this dynamic update mechanism, the road traffic cost matrix can more accurately reflect the actual road conditions, thereby providing more reasonable route planning suggestions.

[0073] See also Figure 2 , is a module diagram of a big data processing system for smart transportation provided in an embodiment of the present application, wherein the system includes: An activity information acquisition module is used to acquire activity reservation information in a target area during a preset time period, wherein the activity reservation information includes the activity location, the estimated number of people in the activity, and the activity time range; A scheduling strategy determination module, used to determine the scheduling strategy of the target vehicle set based on the estimated number of people in the activity and the time range of the activity; A traffic information prediction module, used to predict a traffic information map of the target area within the activity time range, wherein the traffic information map includes traffic information of all traffic roads with a radius of a preset length and the activity location as the center; A vehicle route determination module, used to determine the driving route and alternate route corresponding to each target vehicle in the target vehicle set based on the traffic information map and the dispatching strategy; The dispatch map generation module is used to generate a comprehensive dispatch map of the target vehicle set within the target time range based on the driving routes and backup routes corresponding to each of the target vehicles.

[0074] Optionally, the activity information acquisition module is further used to receive activity applications reported by various activity venues in the target area; Classifying the activity applications to obtain large-scale activity applications and small-scale activity applications, and determining the number of participants and activity locations of each large-scale activity; The number of people in the activity is greater than the preset number and / or the activity location is within the preset congestion area. The activity is taken as the target activity, and activity reservation information corresponding to the target activity is obtained.

[0075] Optionally, the scheduling strategy determination module is further used to obtain historical vehicle scheduling data of the same type of activities, and determine the peak period within the activity time range based on the historical vehicle scheduling data; Calculate the number of target vehicles required for each peak period according to the estimated number of people attending the activity, as well as the departure information of each target vehicle; The number of the target vehicles and the departure information of each of the target vehicles are integrated into a scheduling strategy for the target vehicle set.

[0076] Optionally, the traffic information prediction module is further used to obtain historical traffic information of the target area in each preset historical period, and determine the target historical period corresponding to the activity time range; Divide an area with a preset length as a radius and the activity location as the center into a target traffic area; Determining initial traffic information of all traffic roads in the target traffic area based on the historical traffic information corresponding to the target historical period; The weather information and road construction information of the target traffic area within the target time range are obtained, and the initial traffic information of each of the traffic roads is corrected based on the weather information and the road construction information to generate the traffic information map.

[0077] Optionally, the vehicle route determination module is further used to extract the traffic volume, average vehicle speed and road grade of each of the traffic roads from the traffic information map; Calculating the congestion coefficient of each of the traffic roads according to the traffic volume and the average vehicle speed, and setting the road section weight of each of the traffic roads in combination with the road grade; Establishing a road traffic cost matrix based on the congestion coefficient and the road section weight, wherein the road traffic cost matrix includes the travel time and travel difficulty of each of the traffic roads; According to the road traffic cost matrix, a driving route and an alternate route are planned for each target vehicle using the minimum cost principle.

[0078] Optionally, the vehicle route determination module is further used to establish a road connectivity relationship diagram based on the road traffic cost matrix, wherein the road connectivity relationship diagram includes connection relationships and turning information of each of the traffic roads; Selecting a candidate path with the minimum travel cost and satisfying the turning information in the road connectivity relationship diagram as a driving route, and marking a section on the driving route with a congestion coefficient greater than a congestion coefficient threshold as a high-risk section; Selecting a parallel road section or an adjacent road section as an alternative road section at the starting point of the high-risk road section, wherein the difference in the travel cost between the alternative road section and the corresponding high-risk road section is less than a preset value; At least two complete paths that do not pass through the high-risk road section are generated based on the alternative road section as alternative routes.

[0079] Optionally, the system further includes a correction and update module, which is further used to obtain the actual driving trajectory of each target vehicle in the target vehicle set, and perform deviation analysis between the actual driving trajectory and the corresponding driving route; When it is detected that the target vehicle deviates from the driving route and the deviation distance is greater than a first preset distance, a route deviation warning message is sent to the target vehicle; When it is detected that the real-time congestion coefficient of the driving section where the target vehicle is located is greater than a first preset threshold, a corresponding backup route is pushed to the target vehicle; The actual traffic information of each target vehicle is counted, and the deviation information between the actual traffic information and the corresponding estimated traffic information in the comprehensive dispatch map is recorded, and the road traffic cost matrix is ​​corrected and updated based on the deviation information.

[0080] It should be noted that: when the system provided in the above embodiment realizes its functions, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the system and method embodiments provided in the above embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0081] An embodiment of the present application also provides a computer storage medium, which can store multiple instructions. The instructions are suitable for being loaded by a processor and executing a big data processing method for smart transportation in the above embodiment. The specific execution process can be found in the specific description of the above embodiment, which will not be repeated here.

[0082] Please refer to Figure 3 , the application also discloses an electronic device. Figure 3 The electronic device 300 may include: at least one processor 301 , at least one network interface 304 , a user interface 303 , a memory 305 , and at least one communication bus 302 .

[0083] The communication bus 302 is used to realize the connection and communication between these components.

[0084] The user interface 303 may include a display screen (Display) and a camera (Camera). Optionally, the user interface 303 may also include a standard wired interface and a wireless interface.

[0085] The network interface 304 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0086] Among them, the processor 301 may include one or more processing cores. The processor 301 uses various interfaces and lines to connect various parts in the entire server, and executes various functions of the server and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 305, and calling data stored in the memory 305. Optionally, the processor 301 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 301 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 301, and it can be implemented separately through a chip.

[0087] Among them, the memory 305 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory). Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 305 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 a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned method embodiments, etc.; the data storage area may store data involved in the above-mentioned method embodiments, etc. The memory 305 may optionally be at least one storage device located away from the aforementioned processor 301. Refer to Figure 3 , the memory 305 as a computer storage medium may include an operating system, a network communication module, a user interface module and an application program of a big data processing method for smart transportation.

[0088] exist Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 301 can be used to call the application program of a big data processing method for smart transportation stored in the memory 305. When executed by one or more processors 301, the electronic device 300 executes one or more of the methods described in the above embodiments. It should be noted that for the aforementioned method embodiments, for the sake of simple description, they are all expressed as a series of action combinations, but those skilled in the art should know that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for the present application.

[0089] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0091] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0092] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0093] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various embodiments of the present application. The aforementioned memory includes: various media that can store program codes, such as USB flash drives, mobile hard drives, magnetic disks or optical disks.

[0094] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification and the truth of practice, those skilled in the art will easily think of other embodiments of the present disclosure.

[0095] This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art not described in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A big data processing method for smart transportation, characterized in that: The method comprises: Obtaining activity reservation information in a target area during a preset time period, wherein the activity reservation information includes the activity location, the estimated number of people in the activity, and the activity time range; Determining a dispatch strategy for a target vehicle set based on the estimated number of people at the activity and the time range of the activity; Predicting a traffic information map of the target area within the activity time range, the traffic information map including traffic information of all traffic roads with the activity location as the center and a preset length as the radius; Determine the driving route and the backup route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and the dispatching strategy; Based on the driving routes and backup routes corresponding to each of the target vehicles, a comprehensive dispatch map of the target vehicle set within the target time range is generated.

2. The big data processing method for smart transportation according to claim 1 is characterized in that: The step of obtaining the activity reservation information of the target area in the preset time period includes: Receive activity applications reported by various activity venues in the target area; Classifying the activity applications to obtain large-scale activity applications and small-scale activity applications, and determining the number of participants and activity locations of each large-scale activity; The number of people in the activity is greater than the preset number and / or the activity location is within the preset congestion area. The activity is taken as the target activity, and activity reservation information corresponding to the target activity is obtained.

3. The big data processing method for smart transportation according to claim 1 is characterized in that: The step of determining a dispatching strategy for a target vehicle set based on the estimated number of people in the activity and the time range of the activity includes: Acquire historical vehicle dispatch data of similar activities, and determine a peak time period within the activity time range based on the historical vehicle dispatch data; Calculate the number of target vehicles required for each peak period according to the estimated number of people attending the activity, as well as the departure information of each target vehicle; The number of the target vehicles and the departure information of each of the target vehicles are integrated into a scheduling strategy for the target vehicle set.

4. The big data processing method for smart transportation according to claim 1 is characterized in that: The traffic information map of the target area predicted within the activity time range includes: Acquire historical traffic information of the target area in each preset historical time period, and determine the target historical time period corresponding to the activity time range; Divide an area with a preset length as a radius and the activity location as the center into a target traffic area; Determining initial traffic information of all traffic roads in the target traffic area based on the historical traffic information corresponding to the target historical period; The weather information and road construction information of the target traffic area within the target time range are obtained, and the initial traffic information of each of the traffic roads is corrected based on the weather information and road construction information to generate the traffic information map.

5. The big data processing method for smart transportation according to claim 1 is characterized in that: The determining of the driving route and the backup route corresponding to each target vehicle in the target vehicle set based on the traffic information graph and the dispatching strategy includes: Extracting the traffic volume, average speed and road grade of each of the traffic roads from the traffic information map; Calculating the congestion coefficient of each of the traffic roads according to the traffic volume and the average vehicle speed, and setting the road section weight of each of the traffic roads in combination with the road grade; Establishing a road traffic cost matrix based on the congestion coefficient and the road section weight, wherein the road traffic cost matrix includes the travel time and travel difficulty of each of the traffic roads; According to the road traffic cost matrix, a driving route and an alternate route are planned for each target vehicle using the minimum cost principle.

6. The big data processing method for smart transportation according to claim 5 is characterized in that: The method of planning a driving route and an alternate route for each target vehicle based on the road traffic cost matrix and using the minimum cost principle includes: Establishing a road connectivity relationship diagram based on the road traffic cost matrix, wherein the road connectivity relationship diagram includes connection relationships and turn information of each of the traffic roads; Selecting a candidate path with the minimum travel cost and satisfying the turning information in the road connectivity relationship diagram as a driving route, and marking a section on the driving route with a congestion coefficient greater than a congestion coefficient threshold as a high-risk section; Selecting a parallel road section or an adjacent road section as an alternative road section at the starting point of the high-risk road section, wherein the difference in the travel cost between the alternative road section and the corresponding high-risk road section is less than a preset value; At least two complete paths that do not pass through the high-risk road section are generated based on the alternative road section as alternative routes.

7. The big data processing method for smart transportation according to claim 1 is characterized in that: The method further comprises: Acquire the actual driving trajectory of each target vehicle in the target vehicle set, and perform deviation analysis between the actual driving trajectory and the corresponding driving route; When it is detected that the target vehicle deviates from the driving route and the deviation distance is greater than a first preset distance, a route deviation warning message is sent to the target vehicle; When it is detected that the real-time congestion coefficient of the driving section where the target vehicle is located is greater than a first preset threshold, a corresponding backup route is pushed to the target vehicle; The actual traffic information of each target vehicle is counted, and the deviation information between the actual traffic information and the corresponding estimated traffic information in the comprehensive dispatch map is recorded, and the road traffic cost matrix is ​​corrected and updated based on the deviation information.

8. A big data processing system for smart transportation, characterized in that: The system comprises: An activity information acquisition module is used to acquire activity reservation information in a target area during a preset time period, wherein the activity reservation information includes the activity location, the estimated number of people in the activity, and the activity time range; A scheduling strategy determination module, used to determine the scheduling strategy of the target vehicle set based on the estimated number of people in the activity and the time range of the activity; A traffic information prediction module, used to predict a traffic information map of the target area within the activity time range, wherein the traffic information map includes traffic information of all traffic roads with a radius of a preset length and the activity location as the center; A vehicle route determination module, used to determine the driving route and alternate route corresponding to each target vehicle in the target vehicle set based on the traffic information map and the dispatching strategy; The dispatch map generation module is used to generate a comprehensive dispatch map of the target vehicle set within the target time range based on the driving routes and backup routes corresponding to each of the target vehicles.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method as described in any one of claims 1-7.

Images