Data management method and system based on wisdom high-speed software

Abstract

This application relates to the field of data processing technology, proposing a data management method and system based on intelligent highway software. The method includes: initially segmenting the highway based on historical vehicle data at monitoring points, establishing a basic speed limit benchmark for each initial segment; obtaining predicted vehicle data for each monitoring point in the next time period based on real-time vehicle data at the monitoring points, quantifying the congestion level based on the predicted vehicle data, performing secondary segmentation based on the congestion level, and adjusting the speed limit according to the basic speed limit benchmark to obtain the latest speed limit benchmark; outputting the latest speed limit benchmark to the intelligent highway software platform, which then makes management decisions. The speed limit settings of this application can accurately reflect local characteristics.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a data management method and system based on intelligent high-speed software. Background Technology

[0002] Smart highway software collects and analyzes real-time data on highway conditions and vehicle status to predict and analyze traffic congestion or accidents on highways. This helps managers take timely and effective management measures, including adaptive adjustments to highway speed limits. Highway speed limits are dynamically variable, and relevant management departments adjust speed limits for different road sections based on traffic flow, weather changes, and other factors.

[0003] Existing highways are usually divided into speed limit zones based on administrative divisions or fixed mileage, which may lead to differences in speed performance within a certain section, and the speed limit settings cannot accurately reflect local characteristics. Summary of the Invention

[0004] To address the limitations of existing technologies in dynamically adjusting highway speed limits and their inability to accurately reflect local characteristics, this application provides a data management method and system based on intelligent highway software. This method adjusts speed limits by calculating the severity of congestion, enabling timely adjustments to local speed limits on highways.

[0005] Firstly, this application provides a data management method based on intelligent high-speed software, employing the following technical solution: The data management method based on intelligent highway software includes the following steps: The highway is initially segmented based on historical vehicle data at monitoring points, and a basic speed limit benchmark is established for each initial segment. Based on real-time vehicle data at monitoring points, predictive vehicle data for each monitoring point in the next time period is obtained. The degree of congestion is quantified based on the predicted vehicle data. Based on the degree of congestion, secondary segmentation is performed on the basis of the initial segmentation, and the speed limit is adjusted according to the basic speed limit benchmark to obtain the latest speed limit benchmark. The latest speed limit benchmark is output and input into the intelligent highway software platform, which then makes management decisions. The vehicle data includes vehicle density and average vehicle speed; the quantification of congestion level based on predicted vehicle data includes: calculating the ratio of the predicted average vehicle speed at each monitoring point to the basic speed limit benchmark of the segment to be used as the speed deviation level; calculating the difference between 1 and the speed deviation level as the speed deviation; and calculating the product of the normalized predicted traffic density and the speed deviation at each monitoring point to represent the congestion level at the corresponding monitoring point.

[0006] Furthermore, the initial segment is obtained by using a clustering method to merge all monitoring points based on historical vehicle data at the monitoring points to form the initial segment.

[0007] Furthermore, the method of merging all monitoring points using clustering includes: dividing and merging based on the average vehicle speed, the standard deviation of vehicle speed at each monitoring point, and the optimized distance between two adjacent monitoring points; The optimized distance between two adjacent monitoring points is the product of the normalized actual distance between the two adjacent monitoring points, the speed difference between the two adjacent monitoring points, and the maximum value of the standard deviation of the speed between the two adjacent monitoring points. The difference in vehicle speed between two adjacent monitoring points is the absolute value of the difference between 1 and the ratio of the average vehicle speed between the two adjacent monitoring points.

[0008] Furthermore, establishing a basic speed limit benchmark for each initial segment includes: calculating the average vehicle speed of each initial segment; calculating the information entropy value of the average vehicle speed at the monitoring point in each initial segment and performing negative correlation normalization; calculating the ratio of the product of the average vehicle speed and the negative correlation normalized information entropy value to the preset speed limit benchmark index and rounding it up to obtain the initial speed limit target value; and comparing the initial speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark corresponding to each initial segment.

[0009] Furthermore, the step of comparing the initial speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark for each initial segment includes: if the initial speed limit target value is within the range of the minimum and maximum preset speed limits, then the initial speed limit target value is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is less than the minimum preset speed limit, then the minimum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is greater than the maximum preset speed limit, then the maximum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment.

[0010] Furthermore, the secondary segmentation based on the congestion level on the basis of the initial segmentation includes: calculating the congestion level of each monitoring point in the initial segmentation, fitting the curve using the least squares method, marking the inflection point of the curve as the segmentation point, performing secondary segmentation, and obtaining the secondary segmentation result.

[0011] Furthermore, the step of adjusting the speed limit based on the basic speed limit benchmark to obtain the latest speed limit benchmark includes: obtaining the sequence number of the most congested monitoring point in the secondary segmentation results of the initial segment, and calculating the normalized distance between the monitoring point sequence number and the endpoint of the secondary segment; calculating the ratio of the mean of the congestion level of all monitoring points in the secondary segment to the maximum value of the congestion level of all monitoring points in the initial segment to which the secondary segment belongs, representing the average level difference of the congestion level of the monitoring points; calculating the product of the basic speed limit benchmark of the initial segment to which the current secondary segment belongs and the above-mentioned normalized distance and the average level difference of the congestion level of the monitoring points, and rounding up to obtain the latest speed limit target value; The latest speed limit benchmark for each secondary segment is obtained by comparing the latest target speed limit with the minimum and maximum preset speed limits in the highway section.

[0012] Furthermore, an LSTM model is used to predict vehicle data at each monitoring point.

[0013] Secondly, this application provides a data management system based on intelligent high-speed software, which adopts the following technical solution: A data management system based on intelligent high-speed software includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a data management method based on intelligent high-speed software as described above is implemented.

[0014] This application has the following technical effects: This application utilizes an improved distance calculation formula that considers average vehicle speed, speed standard deviation (reflecting stability), and the actual distance between two adjacent monitoring points. This formula effectively merges adjacent road segments with similar characteristics, forming homogeneous road segment groups. This avoids the internal speed difference problem caused by traditional fixed divisions, improves the accuracy and adaptability of segmentation, and ensures that complex road segments (such as curves) are independently identified. This application calculates based on historical average vehicle speed, information entropy (reflecting road condition complexity), and preset speed limit benchmark indicators, and can generate safe and reasonable speed limit benchmarks (limited to the minimum / maximum of the regulations and rounded up); avoids non-compliance or risks caused by excessively low or high speed limits, and at the same time considers the degree of road condition chaos to reduce speed limits to prevent accidents, improve driver compliance and overall traffic efficiency; This application is based on the expression of congestion severity based on predicted density, speed deviation and basic speed limit, as well as the secondary segmentation of curve fitting. It can finely adjust the road segment boundaries on the basis of the initial segmentation, which facilitates targeted speed limit management. This application uses the latest speed limit benchmark calculation expression (taking into account the distance to the most severe congestion point ahead and the difference in congestion level) to reduce speed limits on congested road sections and upstream, control traffic flow, reduce accidents and accelerate congestion dispersal; and ensures that the speed limit adjustment range is moderate to avoid excessive reduction affecting overall traffic flow. Attached Figure Description

[0015] The above and other objects, features, and advantages of the present invention will become readily apparent from the following detailed description of exemplary embodiments, accompanied by the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein: Figure 1 This is a flowchart of a data management method based on intelligent high-speed software provided in an embodiment of this application. Detailed Implementation

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

[0017] This application discloses a data management method based on intelligent highway software, referring to... Figure 1 The steps include: S101: Based on historical vehicle data at monitoring points, the highway is initially segmented, and a basic speed limit benchmark is established for each initial segment.

[0018] Specifically, monitoring points are set up on the highway at fixed intervals. In this embodiment, the fixed interval is set to 1km. Historical data is collected, and vehicle data of all vehicles passing through each monitoring point is obtained from the historical data. Since road conditions such as curves, road slopes and accident-prone areas will affect the average vehicle speed, the regional average vehicle speed can be used to reflect the road conditions and thus serve as a basis for segmentation. The vehicle data includes vehicle density and average vehicle speed.

[0019] Specifically, analyze vehicle speed data from historical data to identify changes in road conditions (such as areas where speeds rise or fall significantly due to factors like curves, gradients, and accident-prone areas), and divide the highway into segments with consistent characteristics to ensure that speed limits match actual road conditions (such as lower speed limits for complex road sections).

[0020] Specifically, based on historical vehicle data at the monitoring points, clustering methods are used to merge all monitoring points to form initial segments.

[0021] Specifically, in the process of segmenting the highway, the monitoring points are merged using a clustering method based on historical vehicle data at the monitoring points. Each monitoring point corresponds to a 1km segment along the highway's direction of travel, and the segments corresponding to all monitoring points contained in a single cluster are merged.

[0022] Specifically, in the process of merging and segmenting, in addition to considering the average speed of vehicles passing through each monitoring point, the difference in average speed when vehicles pass through each monitoring point is also considered. This is mainly used to measure the stability of vehicle speed. If the difference in vehicle speed passing through a single monitoring point is small, it indicates that the road conditions there are relatively stable and consistent. If the difference in vehicle speed distribution is large, it may reflect the instability of the road conditions, which may be caused by curves, slopes or external interference, thus helping the clustering algorithm to identify more homogeneous road segment groups.

[0023] Specifically, the clustering method for merging all monitoring points includes: dividing and merging based on the average vehicle speed, the standard deviation of vehicle speed at each monitoring point, and the optimized distance between two adjacent monitoring points; The optimized distance between two adjacent monitoring points is the product of the normalized actual distance between the two adjacent monitoring points, the speed difference between the two adjacent monitoring points, and the maximum value of the standard deviation of the speed between the two adjacent monitoring points. The absolute value of the difference between the speed difference between two adjacent monitoring points is 1 and the ratio of the average speed of the two adjacent monitoring points.

[0024] Specifically, in this embodiment, during the merging and segmenting of monitoring points using a clustering method, the clustering algorithm selected is DBSCAN (Density-Based Spatial Clustering of Applications with Noise). Based on the above analysis, the method for calculating the distance between every two monitoring points is improved, and the calculation expression is as follows: in, For the first The and the first The normalized actual distance between each monitoring point is considered when clustering segments to merge adjacent road segments with small differences in average vehicle speed stability. and These are the historical data of all vehicles passing through the [number]th [stage]. The and the first The average vehicle speed at each monitoring point It reflects the difference in vehicle speed between two monitoring points; the greater the difference, the greater the distance and they cannot be combined into one segment. and These are the historical data of all vehicles passing through the [number]th [stage]. The and the first When calculating the standard deviation of vehicle speed at two monitoring points, if one of the monitoring points has poor stability, the distance between the two points needs to be increased to avoid merging.

[0025] Specifically, the distance between every two monitoring points is calculated using the improved distance calculation expression. Based on this, the DBSCAN algorithm is used to cluster all monitoring points, with a cluster radius of 1. The road segments corresponding to all monitoring points contained in a single merged cluster are then merged as the preliminary segmentation result.

[0026] Specifically, by using an improved distance calculation formula that considers average vehicle speed, speed standard deviation (reflecting stability), and actual distance between monitoring points, adjacent road segments with similar characteristics can be effectively merged to form homogeneous road segment groups. This avoids the internal speed difference problem caused by traditional fixed divisions, improves the accuracy and adaptability of segmentation, and ensures that complex road segments (such as curve areas) are independently identified.

[0027] Specifically, establishing a basic speed limit benchmark for each initial segment includes: calculating the average vehicle speed of each initial segment; calculating the information entropy value of the average vehicle speed at the monitoring points in each initial segment and performing negative correlation normalization; calculating the ratio of the product of the average vehicle speed and the negative correlation normalized information entropy value to the preset speed limit benchmark index and rounding it up to obtain the initial speed limit target value; and comparing the initial speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark corresponding to each initial segment.

[0028] Specifically, the comparison between the initial speed limit target value and the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark for each initial segment includes: if the initial speed limit target value is within the range of the minimum and maximum preset speed limits, then the initial speed limit target value is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is less than the minimum preset speed limit, then the minimum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is greater than the maximum preset speed limit, then the maximum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment.

[0029] Specifically, after the initial segmentation of the highway, it is necessary to establish basic speed limit benchmarks for each segment. The calculation of these benchmarks is based on the average vehicle speed at monitoring points within each segment, and the stability of the average vehicle speed at those monitoring points. The segmentation results of the merged highway system... The basic speed limit benchmark calculation expression for each initial segment is: in, and These are the minimum and maximum speed limits for the preset highway sections, which can be limited based on regulations; Function refers to Time to take ;when Time to take ;when Time to take ; To round up; This represents the initial speed limit target value; For the first Each initial segment contains the historical average vehicle speed of the monitoring points. For the first Each initial segment contains the information entropy value of the average vehicle speed at the monitoring points. This entropy value reflects the degree of disorder in the historical average vehicle speed of the monitoring points within that initial segment. The higher the entropy value, the greater the disorder, indicating a higher level of road condition complexity, and a need to reduce vehicle speed to avoid accidents. In this embodiment, a preset speed limit benchmark index is used. This is the most commonly used benchmark for setting speed limits, defined as the speed at which 85% of vehicles in the speed distribution are below this value (i.e., the 85th percentile speed). In this scheme, it is used as the influence coefficient for adjusting the speed limit benchmark using the average vehicle speed.

[0030] Specifically, based on historical average vehicle speed, information entropy (reflecting road condition complexity), and preset speed limit benchmarks, a safe and reasonable speed limit benchmark can be generated (limited to the minimum / maximum of the regulations and rounded up). This avoids non-compliance or risks caused by excessively low or high speed limits, while also considering the degree of road condition chaos to reduce speed limits to prevent accidents, thereby improving driver compliance and overall traffic efficiency.

[0031] S102: Based on the real-time vehicle data at the monitoring points, obtain the predicted vehicle data at each monitoring point for the next time period, quantify the congestion level based on the predicted vehicle data, perform secondary segmentation based on the initial segmentation based on the congestion level, and adjust the speed limit based on the basic speed limit benchmark to obtain the latest speed limit benchmark.

[0032] Specifically, the secondary segmentation based on the initial segmentation, according to the degree of congestion, includes: calculating the congestion level at each monitoring point in the initial segment, fitting a curve using the least squares method, marking the inflection points of the curve as segmentation points, performing secondary segmentation, and obtaining the secondary segmentation results. Specifically, after initially segmenting the highway based on historical data and establishing basic speed limit benchmarks for each segment, the speed limits need to be adjusted based on real-time vehicle traffic conditions. Existing technologies consider factors such as weather to predict congestion. To avoid large-scale congestion or to prevent the spread of congestion in the event of congestion, the speed limits for each segment need to be adjusted to alleviate congestion as quickly as possible.

[0033] Specifically, the density and average speed of vehicles passing through each monitoring point on the highway are collected in real time at fixed intervals. In order to avoid drivers being unable to react due to frequent changes in speed limit information, the time for collecting information and updating speed limits is adjusted to 30 minutes. The LSTM (Long Short-Term Memory) model is used to predict the traffic flow density and average speed at each monitoring point on the highway.

[0034] Specifically, after predicting the traffic flow density and average vehicle speed at each monitoring point, the congestion severity at each monitoring point is calculated. Based on the preliminary segmentation results, a second segmentation is performed using the congestion severity, which facilitates speed limit adjustments based on the predicted congestion level.

[0035] Specifically, quantifying congestion levels based on predicted vehicle data includes: calculating the ratio of the predicted average vehicle speed at each monitoring point to the baseline speed limit for the corresponding segment as the speed deviation level; calculating the difference between 1 and the speed deviation level as the speed deviation; and calculating the product of the normalized predicted traffic density and the speed deviation at each monitoring point to represent the congestion level at the corresponding monitoring point.

[0036] Specifically, LSTM is used to predict the traffic flow density and average vehicle speed at each monitoring point, and based on this, the congestion severity at each monitoring point is calculated. The calculation expression is as follows: in, To predict the traffic density at each monitoring point, the higher the traffic density, the higher the likelihood of congestion. Indicates normalization; For the first The average vehicle speed was collected from each monitoring point; the more severe the congestion, the lower the average vehicle speed. For the first The monitoring point is located at the [number]th The basic speed limit benchmark value for each segment, and the difference. The larger the value, the higher the value. The lower the vehicle speed at each monitoring point, the more severe the congestion.

[0037] Specifically, after calculating the congestion severity at each monitoring point, it is necessary to further segment the data based on the initial segmentation results to obtain the [number of segments]. Each segment contains the congestion severity of all monitoring points. The least squares method is used to fit the curve, and the inflection points are marked as segmentation points. The curve is then further segmented to obtain the secondary segmentation results. Speed ​​limit adjustments are made based on these results.

[0038] Specifically, based on the formula for congestion severity derived from predicted density, speed deviation, and basic speed limit, as well as the secondary segmentation through curve fitting, road segment boundaries can be finely adjusted on the basis of preliminary segmentation, facilitating targeted speed limit management.

[0039] Specifically, adjusting the speed limit based on the basic speed limit benchmark to obtain the latest speed limit benchmark includes: obtaining the sequence number of the most congested monitoring point in the secondary segmentation results of the initial segment, and calculating the normalized distance between the monitoring point sequence number and the endpoint of the secondary segment; calculating the ratio of the mean congestion level of all monitoring points in the secondary segment to the maximum congestion level of all monitoring points in the initial segment to which the secondary segment belongs, representing the average level difference of the congestion level of the monitoring points; calculating the product of the basic speed limit benchmark of the initial segment to which the current secondary segment belongs and the above-mentioned normalized distance and the average level difference of the congestion level of the monitoring points, and rounding up to obtain the latest speed limit target value; and comparing the latest speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the latest speed limit benchmark corresponding to each secondary segment.

[0040] Specifically, based on the initial segmentation of S101, a second segmentation is obtained by using the predicted congestion severity. Using the segments in the second segmentation as the smallest unit, the speed limit is adjusted based on the baseline speed limit and the congestion severity. In the second segmentation result, the segment... The calculation formula for the speed limit adjustment of each segment is as follows: in, This indicates the latest speed limit target value; This indicates the latest speed limit standard; and These are the minimum and maximum speed limits for the preset highway sections, which can be limited based on regulations; To round up; The speed limit is calculated based on the baseline speed limit in S101. In order to avoid accidents when congestion occurs, the speed limit needs to be lowered based on the baseline speed limit. For the first on the highway The first section of road continues forward in the direction of travel (i.e., the first...) The sequence number of the monitoring point with the most severe congestion (including the current road segment and all subsequent road segments). For the first If a section of road is congested along the direction of travel on the highway and is close to or is currently in a congested section, the reduction in speed limit should be increased. For the first on the highway The first section of road continues forward in the direction of travel (i.e., the first...) The maximum congestion severity among all monitoring points (including the first road segment and all subsequent road segments), For the first Each road segment includes the mean of congestion severity at all monitoring points; the ratio A ratio of 1 is a positive number that does not exceed 1 and can reflect the difference between the two. The closer the ratio is to 1, the less the difference in the severity of congestion is, and the less the speed limit needs to be reduced. The smaller the ratio is, the more the difference in the severity of congestion is, and the more the speed limit should be reduced in order to prevent the congestion from spreading.

[0041] Specifically, by using the latest speed limit benchmark calculation expression (which takes into account the distance to the most severe congestion point ahead and the difference in congestion level), the speed limit can be reduced in and upstream of congested road sections to control traffic flow, reduce accidents, and accelerate congestion evacuation; ensuring that the speed limit adjustment range is moderate and avoiding excessive reduction that would affect overall traffic flow.

[0042] S103: Outputs the latest speed limit benchmark to the intelligent highway software platform, which then makes management decisions.

[0043] After S102 completes secondary segmentation and speed limit adjustment, the results are pushed to the intelligent highway software system (such as variable speed limit signs, vehicle APP or management platform). At the same time, all collected and calculated data are stored in a structured manner to facilitate analysis and decision-making by management personnel.

[0044] This application also discloses a data management system based on intelligent high-speed software, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a data management method based on intelligent high-speed software according to this application is implemented.

[0045] The system also includes other components well known to those skilled in the art, such as communication buses and communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0046] In this application, the aforementioned memory can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as resistive random access memory (DRAM), dynamic random access memory (DRAM), static random access memory (SRAM), etc., or any other medium that can be used to store required information and can be accessed by an application program, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device.

[0047] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A data management method based on intelligent high-speed software, characterized by the following steps: include: The highway is initially segmented based on historical vehicle data at monitoring points, and a basic speed limit benchmark is established for each initial segment. Based on real-time vehicle data at monitoring points, predictive vehicle data for each monitoring point in the next time period is obtained. The degree of congestion is quantified based on the predicted vehicle data. Based on the degree of congestion, secondary segmentation is performed on the basis of the initial segmentation, and the speed limit is adjusted according to the basic speed limit benchmark to obtain the latest speed limit benchmark. The latest speed limit benchmark is output and input into the intelligent highway software platform, which then makes management decisions. The vehicle data includes vehicle density and average vehicle speed; the quantification of congestion level based on predicted vehicle data includes: calculating the ratio of the predicted average vehicle speed at each monitoring point to the basic speed limit benchmark of the segment to be used as the speed deviation level; calculating the difference between 1 and the speed deviation level as the speed deviation; and calculating the product of the normalized predicted traffic density and the speed deviation at each monitoring point to represent the congestion level at the corresponding monitoring point. The expression for calculating the congestion level at the corresponding monitoring point is: in, Indicates the first The degree of vehicle congestion at each monitoring point To predict the traffic density at each monitoring point, the higher the traffic density, the higher the likelihood of congestion. Indicates normalization; For the first The average vehicle speed was collected from each monitoring point; the more severe the congestion, the lower the average vehicle speed. For the first The monitoring point is located at the [number]th The basic speed limit benchmark value for each segment, and the difference. The larger the value, the higher the value. The lower the vehicle speed at each monitoring point, the more severe the congestion.

2. The data management method based on intelligent high-speed software according to claim 1, characterized in that, The initial segments are obtained by using a clustering method to merge all monitoring points based on historical vehicle data at the monitoring points to form the initial segments.

3. The data management method based on intelligent high-speed software according to claim 2, characterized in that, The method of merging all monitoring points using clustering includes: dividing and merging based on the average vehicle speed, the standard deviation of vehicle speed at each monitoring point, and the optimized distance between two adjacent monitoring points; The optimized distance between two adjacent monitoring points is the product of the normalized actual distance between the two adjacent monitoring points, the speed difference between the two adjacent monitoring points, and the maximum value of the standard deviation of the speed between the two adjacent monitoring points. The difference in vehicle speed between two adjacent monitoring points is the absolute value of the difference between 1 and the ratio of the average vehicle speed between the two adjacent monitoring points.

4. The data management method based on intelligent high-speed software according to claim 1, characterized in that, The process of establishing a basic speed limit benchmark for each initial segment includes: calculating the average vehicle speed of each initial segment; calculating the information entropy value of the average vehicle speed at the monitoring point in each initial segment and performing negative correlation normalization; calculating the ratio of the product of the average vehicle speed and the negative correlation normalized information entropy value to the preset speed limit benchmark index and rounding it up to obtain the initial speed limit target value; and comparing the initial speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark corresponding to each initial segment.

5. The data management method based on intelligent high-speed software according to claim 4, characterized in that, The step of comparing the initial speed limit target value with the minimum and maximum preset speed limits in the highway segment to obtain the basic speed limit benchmark for each initial segment includes: if the initial speed limit target value is within the range of the minimum and maximum preset speed limits, then the initial speed limit target value is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is less than the minimum preset speed limit, then the minimum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment; if the initial speed limit target value is greater than the maximum preset speed limit, then the maximum preset speed limit is taken as the basic speed limit benchmark for the corresponding segment.

6. The data management method based on intelligent high-speed software according to claim 1, characterized in that, The process of performing secondary segmentation based on the initial segmentation according to the degree of congestion includes: calculating the degree of congestion at each monitoring point in the initial segmentation, fitting a curve using the least squares method, marking the inflection point of the curve as the segmentation point, performing secondary segmentation, and obtaining the secondary segmentation result.

7. The data management method based on intelligent high-speed software according to claim 1, characterized in that, The process of adjusting the speed limit based on the basic speed limit benchmark to obtain the latest speed limit benchmark includes: obtaining the sequence number of the most congested monitoring point in the secondary segmentation results of the initial segment; calculating the normalized distance between the monitoring point sequence number and the endpoint of the secondary segment; calculating the ratio of the mean congestion level of all monitoring points in the secondary segment to the maximum congestion level of all monitoring points in the initial segment to which the secondary segment belongs, representing the average level difference of the congestion level of the monitoring points; calculating the product of the basic speed limit benchmark of the initial segment to which the current secondary segment belongs and the above-mentioned normalized distance and the average level difference of the congestion level of the monitoring points, and rounding up to obtain the latest speed limit target value; The latest speed limit benchmark for each secondary segment is obtained by comparing the latest target speed limit with the minimum and maximum preset speed limits in the highway section.

8. The data management method based on intelligent high-speed software according to claim 1, characterized in that, Use an LSTM model to predict vehicle data at each monitoring point.

9. A data management system based on intelligent high-speed software, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions that, when executed by the processor, implement the data management method based on intelligent high-speed software according to any one of claims 1-8.

Images