Intersection average travel speed analysis method, system, and storage medium

Abstract

The application relates to the field of driving speed analysis, and discloses a method and system for analyzing average driving speed at intersections and a storage medium. The method for analyzing average driving speed at intersections comprises the following steps: step 1, acquiring map data of an analysis area and analyzing road information from the map data; step 2, identifying intersections in the road information and acquiring driving speed information within a preset range of each intersection; step 3, learning the driving speed information to obtain an average driving speed prediction model at intersections; and step 4, predicting average driving speeds at the intersections through the average driving speed prediction model at intersections and recommending an optimal route according to the average driving speeds at the intersections. The application can accurately predict average driving speeds at intersections, thereby improving the accuracy of optimal route acquisition.

Description

Technical Field

[0001] This invention relates to the field of driving speed analysis, and more specifically to a method, system, and storage medium for analyzing average driving speed at intersections. Background Technology

[0002] In the development of urban civilization, transportation is one of the most prominent symbols of a city's vitality. A city with convenient transportation and advanced vehicles exhibits high levels of dynamism. As the "main artery" of urban operation, transportation plays a crucial role in urban development. The Internet of Vehicles (IoV) is an interactive wireless network built based on vehicle location, speed, and route information. Through devices such as GPS, RFID, sensors, and camera image processing, the IoV collects information about the vehicle's environment and status. This information is then analyzed and processed using the internet and computer technology to calculate the optimal route for the vehicle, promptly report road conditions and weather, and schedule traffic light cycles, achieving organic interaction between cars, roads, and people, and realizing the intelligentization of vehicles and transportation.

[0003] However, simply selecting the optimal route based on current road conditions is not very effective during peak traffic periods, especially holidays or rush hours when traffic is severely congested. When a vehicle is in a congested area, all roads around it are blocked, making it impossible to change routes. Furthermore, road conditions are not static; they change in real time during road planning and driving, resulting in low accuracy in predicting travel time using current technology, further reducing the accuracy of the optimal route. Intersections are crucial points for changing routes, and the average speed at intersections plays a decisive role in the vehicle's overall speed. Summary of the Invention

[0004] The present invention aims to provide a method, system and storage medium for analyzing the average driving speed at intersections, so as to accurately predict the average driving speed at intersections and improve the accuracy of obtaining the optimal path.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] Methods for analyzing average driving speed at intersections include:

[0007] Step 1: Obtain map data for the analysis area and extract road information from the map data;

[0008] Step 2: Identify intersections in the road information and obtain driving speed information within a preset range for each intersection;

[0009] Step 3: Learn from the driving speed information to obtain the intersection average driving speed prediction model;

[0010] Step 4: Predict the average speed at each intersection using the intersection average speed prediction model, and recommend the optimal route based on the average speed at each intersection.

[0011] The principle and advantages of this scheme are as follows: In practical applications, map data of the analysis area is acquired, and road information is parsed from the map data; intersections in the road information are identified, and driving speed information within a preset range for each intersection is obtained; intersections are the merging and diverging points of vehicles, and also key locations for choosing and changing routes. By using driving speed information, the traffic flow in each direction can be grasped, thereby obtaining the optimal path in a timely and accurate manner; the driving speed information is learned to obtain an average driving speed prediction model for intersections; the average driving speed prediction model for intersections is used to predict the average driving speed of each intersection, and the optimal route is recommended based on the average driving speed of each intersection.

[0012] Preferably, as an improvement, the map information also parses building information, including building location, building name, and building purpose; the road information includes road structure diagram, number of lanes, driving direction, traffic lights, lane type, lane slope, and road surface smoothness.

[0013] Technical benefits: By utilizing information about surrounding buildings and roads, it is easier to analyze the factors affecting the average driving speed at intersections, thereby enabling maintenance and improvement.

[0014] Preferably, as an improvement, step 2 includes:

[0015] Step 21: Identify intersections in the road information;

[0016] Step 22: Determine the range for calculating the average driving speed at each intersection;

[0017] Step 23: Obtain the average driving speed of vehicles within the area of ​​the intersection for a preset time period. The average driving speed includes the average driving speed in one direction and the overall average driving speed.

[0018] Technical benefits: Due to different destinations, although passing through the same intersection, the congestion situation and average driving speed vary. By obtaining the average driving speed in one direction and the overall average driving speed, more accurate route navigation can be provided based on the destination. At the same time, the overall service level of the intersection can be grasped, which is beneficial for subsequent adjustments and maintenance.

[0019] Preferably, as an improvement, step 22 further includes:

[0020] Step 221: Assess the complexity of the intersections based on the conflict points and merging points at each intersection. The specific scores are as follows:

[0021]

[0022] Among them, C i Let i be the number of conflict points at intersection i. H represents the weight corresponding to the number of conflict points x; i Let δ be the number of merging points at intersection i. y The weight corresponding to the number of merging points y; D iz γ represents the number of lanes at the z-th exit of intersection i. j ε represents the weight value corresponding to the number of lanes j; ε is the complexity correction constant.

[0023] Step 222: Divide the road length between the two intersections according to the complexity ratio. The area within the ratio range is the range for calculating the average driving speed.

[0024] Technical effect: The more conflict points and merging points there are at an intersection, the more interference vehicles will experience from other lanes during their journey. The more lanes traveling in the same direction, the greater the risk of lane-changing interference and the greater the impact on the speed at the intersection. Dividing the calculation range of average speed using the above method is beneficial for obtaining sufficient vehicle data for analysis at intersections with high complexity, thereby making the prediction results more accurate.

[0025] Preferably, as an improvement, the preset time period includes morning peak, evening peak, daytime and nighttime off-peak, with the morning peak from 7:30 to 9:30, the evening peak from 17:00 to 19:00, the daytime from 8:00 to 20:00, and the nighttime from 20:00 to 8:00 the next day. Specifically, the average vehicle speed for any fixed duration is obtained within the preset time period.

[0026] Technical benefits: Obtaining the average vehicle speed throughout the day is a huge workload. By dividing the data into time periods and selecting representative data, the acquisition of redundant data can be reduced.

[0027] Preferably, as an improvement, the method for obtaining the average driving speed in step 23 includes: stopwatch speed measurement, speed measuring instrument measurement, and vehicle sensor speed measurement.

[0028] Technical benefits: Based on the actual situation, select the measurement method to quickly and conveniently obtain the average vehicle speed.

[0029] Preferably, as an improvement, step 3 includes:

[0030] Step 31: Clean the average driving speed information to obtain data in a unified format;

[0031] Step 32: Add time and intersection labels to the uniform format data to obtain the dataset, and divide the dataset into training set and test set;

[0032] Step 33: Substitute the training set into the neural network model for training, and use the test set to test the neural network model to obtain the intersection driving speed prediction model.

[0033] Technical effect: By predicting the speed of vehicles at intersections using the intersection speed prediction model, the optimal route for vehicle travel can be provided more accurately.

[0034] Preferably, as an improvement, step 5 is also included, which uses cluster analysis to analyze the relationship between building information and the predicted average driving speed at the intersection;

[0035] Step 6: Recommend auxiliary traffic diversion routes based on the relationship between building information and the predicted average driving speed at intersections.

[0036] Technical effect: By recommending auxiliary road clearing solutions, it helps to promote smooth traffic flow and improve the efficiency of intersections.

[0037] The intersection average driving speed analysis system uses the aforementioned intersection average driving speed analysis method.

[0038] A storage medium storing a computer program that, when run on a computer, causes the computer to execute the intersection average driving speed analysis method. Attached Figure Description

[0039] Figure 1 This is a flowchart illustrating the method for analyzing average driving speed at intersections. Detailed Implementation

[0040] The following detailed description illustrates the specific implementation method:

[0041] The basic implementation examples are as follows: Figure 1 As shown:

[0042] Methods for analyzing average driving speed at intersections include:

[0043] Step 1: Obtain map data for the analysis area and extract road information from it. Specifically, obtain map data for the analysis area from multi-source map software, such as Gaode Map, Baidu Map, and Beidou Satellite Map. Perform coordinate system transformation on the map data obtained from the multi-source map software and calibrate it so that the same location in different map data overlaps. Then, extract road information from the multi-source map data. When different results are obtained for the same location, the latest updated map data shall prevail. When the map update time is the same, the data with the most results for the same location shall prevail.

[0044] The road information includes road structure diagrams, number of lanes, driving direction, traffic lights, lane type, lane gradient, road surface smoothness, etc.

[0045] Step 2: Identify intersections in the road information and obtain driving speed information within a preset range for each intersection; Step 2 specifically includes:

[0046] Step 21: Identify intersections in the road information; the intersections include U-turn intersections, cross intersections, X-shaped intersections, T-shaped intersections, Y-shaped intersections, roundabouts, etc.

[0047] Step 22, determining the range for calculating the average driving speed at each intersection; step 22 also includes:

[0048] Step 221: Assess the complexity of the intersections based on the conflict points and merging points at each intersection. The specific scores are as follows:

[0049]

[0050] Among them, C i Let i be the number of conflict points at intersection i. H represents the weight corresponding to the number of conflict points x; i Let δ be the number of merging points at intersection i. y The weight corresponding to the number of merging points y; D iz γ represents the number of lanes at the z-th exit of intersection i. j ε represents the weight value corresponding to the number of lanes j; ε is the complexity correction constant.

[0051] Different preset time periods correspond to different δ y γ j And the ε value, so that the range of average driving speed calculation at each intersection changes over time, to better reflect the actual situation. δ y γ j The ε value is obtained through training with historical data. Specifically, the historical average speed at the intersection, along with the corresponding number of abrupt changes, merging points, and lanes, is acquired. The system then trains to learn the historical average speed and the corresponding number of abrupt changes, merging points, and lanes for different time periods to obtain the values ​​corresponding to each time period. δ y γ j and the ε value.

[0052] A conflict point is a location where vehicles from different directions intersect at a large angle; a merging point is a location where vehicles from different directions converge in the same direction at a smaller angle. For example, a three-way intersection such as a T-junction or Y-junction contains 3 conflict points and 3 merging points; a four-way intersection such as a crossroads or X-junction contains 16 conflict points and 8 merging points; and a five-way intersection contains 50 conflict points and 8 merging points. The more conflict points and merging points there are, the lower the driving safety. Conflict points are more dangerous than merging points. Using methods such as traffic channelization can limit conflict points to a smaller area.

[0053] Step 222: Divide the road length between two intersections according to the complexity ratio. The area within the ratio range is the calculation range for the average driving speed. The more complex the road, the slower the vehicle speed and the fewer vehicles pass through in the same amount of time. By dividing the road length between two intersections according to the complexity ratio, it is beneficial to obtain sufficient vehicle data for analysis at intersections with high complexity, thereby making the prediction results more accurate.

[0054] Step 23: Obtain the average driving speed of vehicles within the area of ​​the intersection for a preset time period. The average driving speed includes the average driving speed in one direction and the overall average driving speed.

[0055] The average speed in one direction is the average speed of vehicles traveling in each direction at an intersection. If the intersection is a three-way intersection, each side is a two-way lane and there are no special signs, then there are 6 directions of traffic, which means there are 6 average speeds in one direction. The comprehensive average speed is the average of the 6 average speeds in one direction.

[0056] The preset time period includes morning peak hours, evening peak hours, daytime off-peak hours, and nighttime off-peak hours. Morning peak hours are 7:30-9:30, evening peak hours are 17:00-19:00, daytime hours are 8:00-20:00, and nighttime hours are 20:00-8:00 the next day. Specifically, the average vehicle speed for any fixed duration is obtained within the preset time period. For example, if the sampling time is 1 hour, the average speed for any 1 hour is obtained within the morning peak, evening peak, daytime off-peak, and nighttime off-peak periods. Methods for obtaining the average speed include: stopwatch speed measurement, speed measuring instrument measurement, and vehicle sensor speed measurement.

[0057] The stopwatch speed measurement method is a manual method. First, the measurement distance L is determined. A stopwatch is used to measure the time it takes for various vehicles to pass both ends of distance L. The distance L, vehicle type, and time t are recorded. The average speed v = 1 / t × 3.6. The measurement distance L is related to vehicle speed. To facilitate reading, the time t for each vehicle to pass should be no less than 1.5 seconds; in this embodiment, 2 seconds is preferred. The average speed over one hour is obtained. When the average speed is less than 40 km / h, the minimum value of L is 25 m; when the average speed is between 40 and 60 km / h, the minimum value of L is 50 m; and when the average speed is greater than 65 km / h, the minimum value of L is 75 m.

[0058] When using a speed measuring instrument to determine average driving speed, the speed measuring instrument is a radar speed measuring instrument. The speed is determined by the different vibration frequencies of the radio waves reflected by the moving object as the object moves. The instantaneous speed of the vehicle passing by can be directly measured at the speed measuring location, and the speed data can be directly recorded and printed. It is an ideal tool for measuring location speed. However, it is difficult to measure low-speed vehicles, and when two vehicles are detected at the same time, only the speed of the high-speed vehicle is displayed.

[0059] When using vehicle sensor speed measurement to determine average driving speed, the instrument uses a vehicle sensor to measure speed through electromagnetic induction or ultrasonic reflection, simultaneously sensing the distance and time it takes for a vehicle to pass, thereby calculating the vehicle's speed. However, when a disabled or accident-damaged vehicle is parked on the sensor, the speed record will show anomalies.

[0060] Step 3 involves learning from the driving speed information to obtain a prediction model for the average driving speed at the intersection; Step 3 includes:

[0061] Step 31: Clean the average driving speed information to obtain data in a unified format. The average driving speed information of different intersections obtained by different methods has differences in expression and storage format. Cleaning helps to unify the data and can reduce the possibility of errors in subsequent calculations.

[0062] Step 32: Label the uniform format data with time and intersection labels to obtain the dataset, and divide the dataset into training set and test set. The average driving speed at each intersection is different at different times. For example, during the morning and evening rush hours, there are more vehicles and the congestion is more serious, so the average driving speed at the same intersection is relatively slow. For different intersections, the congestion situation of lanes in different directions at the same intersection is also different because the vehicles are going to different destinations. For example, during the morning rush hour, the lanes heading towards the industrial park are more congested and the average driving speed is slow. During the evening rush hour, the lanes heading towards the residential area are more congested and the average driving speed is slow.

[0063] Step 33: Substitute the training set into the neural network model for training, and use the test set to test the neural network model to obtain the intersection driving speed prediction model.

[0064] Step 4: Predict the average speed at each intersection using the intersection average speed prediction model, and recommend the optimal route based on the average speed at each intersection.

[0065] The map information also extracts building information, including building location, building name, and building purpose;

[0066] It also includes step 5, which uses cluster analysis to analyze the relationship between building information and the predicted average driving speed at intersections; the use of buildings has a direct or indirect impact on the average driving speed at intersections; for example, on weekends or holidays, there are more vehicles and the average driving speed is slower at intersections near shopping malls, scenic spots, and entertainment venues; on weekdays, there are more vehicles and the average driving speed is slower around schools, office buildings, and industrial parks.

[0067] Step 6: Recommend auxiliary traffic flow solutions based on the relationship between building information and the predicted average driving speed at intersections. This involves combining road information, including road structure maps, number of lanes, driving direction, traffic lights, lane types, lane gradients, and road surface smoothness, to recommend auxiliary traffic flow solutions. For example, if the average driving speed is below a threshold, temporary closures may be implemented on roads with many lanes and few vehicles; the red light duration for lanes with slower driving speeds may be temporarily shortened.

[0068] The intersection average driving speed analysis system uses the aforementioned intersection average driving speed analysis method.

[0069] A storage medium storing a computer program that, when run on a computer, causes the computer to execute the intersection average driving speed analysis method.

[0070] The above descriptions are merely embodiments of the present invention, and common knowledge such as specific technical solutions and / or characteristics are not described in detail here. It should be noted that those skilled in the art can make various modifications and improvements without departing from the technical solutions of the present invention, and these should also be considered within the scope of protection of the present invention. These modifications and improvements will not affect the effectiveness of the implementation of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A method for analyzing average driving speed at intersections, characterized in that, include: Step 1: Obtain map data for the analysis area and parse road and building information from the map data. The building information includes building location, building name, or building purpose; the road information includes road structure diagram, number of lanes, driving direction, traffic lights, lane type, lane slope, or road surface smoothness. Step 2: Identify intersections in the road information and obtain driving speed information within a preset range for each intersection; Step 2 includes: Step 21: Identify intersections in the road information; Step 22, determine the range for calculating the average driving speed at each intersection; Step 22 also includes: Step 221: Assess the complexity of the intersections based on the conflict points and merging points at each intersection. The specific scores are as follows: in, Let i be the number of conflict points at intersection i. The weight corresponding to the number of conflict points x; The number of merging points at intersection i. The weight corresponding to the number of merging points y; Let z be the number of lanes at the z-th exit of intersection i. This represents the weight value corresponding to the number of lanes j; A constant is used to adjust the complexity; different preset time periods correspond to different... , , and value, , , and The values ​​are obtained by training on historical data; Step 222: Divide the road length between the two intersections according to the complexity ratio. The area within the ratio range is the range for calculating the average driving speed. Step 23: Obtain the average driving speed of vehicles within the area of ​​the intersection for a preset time period. The average driving speed includes the average driving speed in one direction and the comprehensive average driving speed. Step 3: Learn from the driving speed information to obtain the intersection average driving speed prediction model; Step 4: Predict the average speed at each intersection using the intersection average speed prediction model, and recommend the optimal route based on the average speed at each intersection.

2. The intersection average driving speed analysis method according to claim 1, characterized in that: The preset time period includes morning peak, evening peak, daytime and nighttime off-peak. The morning peak is from 7:30 to 9:30, the evening peak is from 17:00 to 19:00, the daytime is from 8:00 to 20:00, and the nighttime is from 20:00 to 8:00 the next day. Specifically, the average driving speed of vehicles for any fixed duration is obtained within the preset time period.

3. The intersection average driving speed analysis method according to claim 1, characterized in that: In step 23, the methods for obtaining the average driving speed include: stopwatch speed measurement, speed measuring instrument measurement, or vehicle sensor speed measurement.

4. The intersection average driving speed analysis method according to claim 1, characterized in that: Step 3 includes: Step 31: Clean the average driving speed information to obtain data in a unified format; Step 32: Add time and intersection labels to the uniform format data to obtain the dataset, and divide the dataset into training set and test set; Step 33: Substitute the training set into the neural network model for training, and use the test set to test the neural network model to obtain the intersection driving speed prediction model.

5. The intersection average driving speed analysis method according to claim 1, characterized in that: It also includes step 5, which uses cluster analysis to analyze the relationship between building information and the predicted average driving speed at intersections; Step 6: Recommend auxiliary traffic diversion routes based on the relationship between building information and the predicted average driving speed at intersections.

6. An intersection average driving speed analysis system, characterized in that: The intersection average driving speed analysis method as described in any one of claims 1-5 was used.

7. A storage medium having a computer program stored thereon, characterized in that: When the computer program is run on a computer, the computer performs the intersection average driving speed analysis method as described in any one of claims 1 to 5.

Images