Digital modeling method of urban area based on data analysis

Abstract

The present application relates to the field of urban traffic data processing technology, and specifically to a method for digital modeling of urban areas based on data analysis, the method comprising: collecting the traffic volume, average vehicle speed and average road occupancy rate of each section of the urban area in each time period; for each preset period, obtaining the congestion characteristic index according to the difference between the two-dimensional data points of the traffic volume and average vehicle speed in all time periods in the period; obtaining the road condition difference of each section according to the correlation between the congestion characteristic index of each section and its adjacent sections in all time periods of each day in the period; for each section, combining the change trend of the average road occupancy rate and the road condition difference in all time periods of each cycle, obtaining the traffic evaluation results of each cycle; establishing a visualized digital model of the urban area, and marking the traffic evaluation results in the visualized digital model of the urban area. The present application can improve the accuracy of the digital model of the urban area.

Description

Technical Field

[0001] The present application relates to the technical field of urban traffic data processing, and specifically to a method for digital modeling of urban areas based on data analysis. Background Art

[0002] Nowadays, cities are constantly developing and updating, and they need to optimize and adjust their internal functions to adapt to the new development environment, shifting from quantitative expansion to qualitative improvement. To this end, a digital model of the urban area is constructed based on the statistical data of a certain city. Through the digital model, planners and managers can understand the urban structure and layout more intuitively and carry out more effective urban planning and management.

[0003] Urban traffic service data plays a vital role in the development of modern cities. By analyzing traffic flow, congestion patterns and travel habits, traffic signal control and route planning can be optimized, which is conducive to reducing congestion. When analyzing traffic service data, due to the complexity and variability of road conditions and the interweaving of roads, conventional methods fail to fully consider the correlation characteristics between traffic flow and speed, as well as the mutual influence between adjacent road sections. It is often difficult to accurately capture the congestion characteristics of traffic roads, affecting the accuracy of urban digital models. Summary of the invention

[0004] In order to solve the above technical problems, the present application provides a digital modeling method for urban areas based on data analysis to solve the existing problems.

[0005] The urban digital modeling method based on data analysis in this application adopts the following technical solutions:

[0006] An embodiment of the present application provides a method for digital modeling of an urban area based on data analysis, the method comprising the following steps:

[0007] S1, collects the traffic volume, average vehicle speed and average road occupancy rate of each section of the urban area at each time period;

[0008] S2, for each preset period, clustering the two-dimensional data points consisting of the traffic flow and average speed of all time periods in the period to obtain each cluster, and obtaining the congestion characteristic index of each time period according to the difference between the two-dimensional data points of the same cluster and different clusters;

[0009] S3, according to the correlation between the congestion characteristic index of each road section and its adjacent road sections at all time periods every day in the cycle, the daily congestion correlation factor is obtained; according to the difference in traffic volume of each road section and its adjacent road sections at all time periods every day, the traffic flow transfer delay index is obtained; for each road section, the traffic flow transfer delay index and congestion correlation factor of each day in each cycle are combined to obtain the congestion impact coefficient of each cycle every day; according to the difference between the congestion impact coefficients of all days in different cycles of each road section, the road condition difference of each road section is obtained;

[0010] S4. For each road section, the congestion risk coefficient of each cycle is obtained by combining the changing trend of the average road occupancy rate in all time periods of each cycle and the difference in road conditions; the traffic assessment result of each cycle is obtained according to the value of the congestion risk coefficient of each cycle; a visualized digital model of the urban area is established, and the traffic assessment results are marked in the visualized digital model of the urban area.

[0011] Furthermore, the method for obtaining the congestion characteristic index of each time period includes:

[0012] The traffic volume and average speed of each time period are combined into two-dimensional data points of each time period; the two-dimensional data points of all time periods in the cycle are clustered to obtain clusters;

[0013] According to the differences between the two-dimensional data points of different clusters, the heterogeneous difference means of each time period are obtained;

[0014] Combining the differences between the two-dimensional data points of the same cluster and the heterogeneous difference means of each time period, the congestion characteristic index of each time period is obtained.

[0015] Furthermore, the method for obtaining the heterogeneous difference mean of each time period includes:

[0016] The two-dimensional data points that belong to different clusters from the two-dimensional data points in each time period are recorded as heterogeneous points; the mean distance between the two-dimensional data points in each time period and all its heterogeneous points is calculated and recorded as the heterogeneous difference mean of each time period.

[0017] Furthermore, the congestion characteristic index of each time period is obtained by combining the difference between the two-dimensional data points of the same cluster and the heterogeneous difference mean of each time period, including: recording the congestion characteristic index of the jth time period of the i-th cycle as , ;in, Represents the mean distance between the two-dimensional data points of the jth period of the i-th cycle and all other periods in the cluster to which it belongs; represents the heterogeneous difference mean of the jth period in the i-th period; It represents the difference between the traffic volume and the average speed in the jth period of the i-th cycle.

[0018] Furthermore, the method for obtaining the daily congestion correlation factor includes:

[0019] Arrange the congestion characteristic indexes of all time periods included in each day of the cycle in chronological order to obtain the congestion status sequence of each day;

[0020] Obtain the distance between each road section and the center point of other road sections, recorded as the first distance; and use a preset number of road sections with the smallest first distances to each road section as adjacent road sections to each road section;

[0021] The mean absolute value of the correlation between the daily congestion status series of each road section and all its adjacent road sections is calculated and recorded as the daily congestion correlation factor of each road section.

[0022] Furthermore, the method for obtaining the traffic flow transfer delay index includes:

[0023] For each time period of each day, the mean difference in traffic volume between each road section and all its adjacent road sections is calculated; the average value of the mean difference in traffic volume for each road section in all time periods of each day is taken as the traffic volume transfer delay index for each road section every day.

[0024] Furthermore, the congestion impact coefficient of each cycle is obtained by combining the traffic flow transfer delay index and the congestion correlation factor of each cycle every day, including: recording the congestion impact coefficient of the kth day in the ith cycle as , ; In the formula, represents the congestion correlation factor on the kth day in the ith period, represents the traffic flow transfer delay index of the kth day in the ith period.

[0025] Furthermore, the method for obtaining the difference in road conditions of each road section includes:

[0026] For each road section, the congestion impact coefficients of all days in each cycle are arranged in chronological order to obtain the congestion impact sequence of each cycle;

[0027] The distance between the congestion impact sequences corresponding to any two cycles is calculated and recorded as the second distance; the average of the second distances of all the cycles combined in pairs is taken as the road condition difference of each road section.

[0028] Furthermore, the method for obtaining the congestion risk coefficient of each period includes:

[0029] For each road section, obtain the trend test statistic of the average road occupancy sequence composed of the average road occupancy in all time periods of each cycle in chronological order; obtain an exponential function with a natural constant as the base and the trend test statistic as the exponent; and use the ratio of the calculation result of the exponential function and the road condition difference of each road section as the congestion risk coefficient of each cycle.

[0030] Furthermore, the traffic assessment results of each period are obtained according to the values ​​of the congestion risk coefficients of each period, including:

[0031] Obtain the normalized value of the congestion risk coefficient of each road section in each period; for each road section, record the period in which the normalized value of the congestion risk coefficient is less than or equal to the first congestion threshold as a time period not prone to congestion; record the period in which the normalized value of the congestion risk coefficient is greater than the first congestion threshold and less than the second congestion threshold as a normal traffic time period; record the period in which the normalized value of the congestion risk coefficient is greater than the second congestion threshold as a congestion time period; wherein the first congestion threshold is less than the second congestion threshold.

[0032] This application has at least the following beneficial effects:

[0033] This application analyzes that the existing methods fail to fully consider the correlation characteristics between traffic flow and speed, as well as the mutual influence between adjacent road sections, making it difficult to accurately obtain the congestion characteristics of road conditions, thereby affecting the accuracy of digital modeling of urban areas. In response to this problem, this application calculates the significance of the difference between traffic flow and average speed based on the correlation characteristics between traffic flow and average speed data under different road conditions to obtain a congestion characteristic index, which has the beneficial effect of accurately obtaining the congestion status of the road section at different times. By analyzing the similarity of congestion status between adjacent road sections within a day and the degree of mutual influence of traffic flow, the congestion influence coefficient of each road section on the congestion degree of the adjacent road section is calculated. Combined with the similarity of the congestion impact of road sections under each cycle and the trend change of the average road occupancy rate, the congestion risk coefficient of the road section is calculated. Its beneficial effect is that it takes into account the mutual influence between roads, which helps to accurately evaluate road conditions. The evaluation results are digitally modeled to improve the reliability of the digital model of the urban area. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0035] Figure 1 A flowchart of the steps of the urban area digital modeling method based on data analysis provided for this application;

[0036] Figure 2 A block diagram for obtaining the congestion characteristic index for each time period provided for one embodiment of the present application. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0038] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0039] The specific scheme of the urban area digital modeling method based on data analysis provided by this application is described in detail below with reference to the accompanying drawings.

[0040] An embodiment of the present application provides a method for digital modeling of urban areas based on data analysis. Specifically, the following method for digital modeling of urban areas based on data analysis is provided. Figure 1 , the method comprises the following steps:

[0041] S1, collects the traffic volume, average vehicle speed and average road occupancy rate of each section of the urban area at each time period.

[0042] The urban area digital modeling method includes a data hub module and a service hub module. The data hub module is mainly used for data collection and preprocessing. The service hub module performs data analysis and feature extraction, and performs digital modeling in combination with the extracted features.

[0043] This application collects traffic data of various sections of urban roads in the past quarter through the urban data open platform, taking one hour as a period to obtain the traffic volume, average speed and average road occupancy rate of each period. The collected traffic data may have missing values ​​due to sensor failure or data entry problems. This application uses linear interpolation technology to fill in the missing values. Linear interpolation is a well-known technology. The filled data is then normalized to eliminate data inconsistencies and analyze the data at the same scale.

[0044] S2, for each preset cycle, cluster the two-dimensional data points consisting of the traffic flow and average speed of all time periods in the cycle to obtain each cluster cluster, and obtain the congestion characteristic index of each time period according to the differences between the two-dimensional data points of the same cluster cluster and different cluster clusters.

[0045] The pre-processed traffic flow data, average vehicle speed data, and average lane occupancy rate data are arranged in ascending time order to obtain the corresponding traffic flow sequence, average vehicle speed sequence, and average lane occupancy rate sequence.

[0046] The traffic volume of a road section is easily affected by time factors. For example, during the morning and evening rush hours on weekdays, the traffic volume will increase significantly, leading to increased traffic congestion. Compared with weekdays, the traffic volume during the morning and evening rush hours on weekends or holidays may not be as obvious as on weekdays. Therefore, the traffic flow sequence shows a cyclical trend: the traffic volume on weekdays is relatively high, while that on non-weekdays may be relatively low. Due to weather or large-scale events, the traffic volume fluctuates between different cycles. In order to better analyze the changes in traffic volume in each cycle, the time between Monday and Sunday is taken as a cycle to divide the traffic flow sequence.

[0047] The volume of traffic flow can reflect the congestion of the road to a certain extent. An increase in traffic flow may indicate that the road is in good condition and there are more vehicles passing through a certain section of the road. When the traffic flow is too large, the interval between vehicles will decrease, thereby reducing the speed. The decrease in the average speed is a direct manifestation of congestion. The reduction in speed means that it takes longer for vehicles to pass through the section. Therefore, when the traffic flow and the average speed are both large, it means that the road traffic is smooth and running well; when the traffic flow is large and the average speed is high, it means that the road is congested. Based on the above correlation characteristics between traffic flow and speed, the degree of road traffic congestion is analyzed for each day.

[0048] Since there are large differences between the two-dimensional data points corresponding to road congestion and smooth traffic, this embodiment firstly forms the two-dimensional data points of each time period with the traffic volume and average speed of each time period; for each period, the two-dimensional data points of all time periods in the period are clustered to obtain each cluster;

[0049] Specifically, in the ith cycle, the traffic volume and average speed at the same time are combined to form a two-dimensional data point. This application uses the DPC density peak clustering algorithm to distinguish different traffic states. The input of the DPC algorithm is all two-dimensional data points in a cycle, the cutoff distance is set to 2% of the total data, and the output is multiple clusters. The DPC algorithm is a technology well known to those skilled in the art, and the specific calculation process will not be repeated.

[0050] Furthermore, according to the degree of data difference between different clusters, the congestion of the road section in each time period is analyzed. Specifically, the two-dimensional data points that belong to different clusters from the two-dimensional data points in each time period are recorded as heterogeneous points; the mean distance between the two-dimensional data points in each time period and all its heterogeneous points is calculated, and recorded as the heterogeneous difference mean of each time period.

[0051] The congestion characteristic index of the jth period of the i-th cycle is recorded as , ;in, Represents the mean distance between the two-dimensional data points of the jth period of the i-th cycle and all other periods in the cluster to which it belongs; represents the heterogeneous difference mean of the jth period in the i-th period; It represents the difference between the traffic volume and the average speed in the jth period of the i-th cycle.

[0052] It should be noted that the distance between two-dimensional data points represents the difference between two data contained in the two-dimensional data point and the corresponding data of other two-dimensional data points; Manhattan distance calculation is adopted in this embodiment, and Euclidean distance can be selected as other embodiments of this application, and this application does not impose any limitation.

[0053] The smaller it is, the closer the traffic flow and average speed characteristics at that time are to other data of the same category. The larger the value, the greater the difference between the traffic flow and average speed at that time and other categories. The larger the value, the more serious the concentration of vehicles at that time, that is, the average speed is low under excessive traffic flow; the final value is The larger it is, the more significant the difference between the traffic flow and the average speed at that time is, and there may be congestion on this road section.

[0054] The block diagram for obtaining the congestion characteristic index of each time period is as follows: Figure 2 shown.

[0055] S3, according to the correlation between the congestion characteristic index of each road section and its adjacent road sections at all time periods every day within the cycle, the daily congestion correlation factor is obtained; according to the difference in traffic volume between each road section and its adjacent road sections at all time periods every day, the traffic flow transfer delay index is obtained; for each road section, the congestion impact coefficient of each cycle is obtained by combining the traffic flow transfer delay index and the congestion correlation factor of each day; according to the difference between the congestion impact coefficients of all days in different cycles of each road section, the road condition difference of each road section is obtained.

[0056] The traffic conditions between different sections may affect each other, and congestion association and traffic flow transfer may occur. Congestion association means that congestion in one section may cause the vehicle queue to extend to the adjacent sections, affecting the traffic flow of these sections. Traffic flow transfer means that when congestion occurs in one section, vehicles may choose to take a detour, resulting in an increase in the traffic flow of the section with less traffic. Therefore, this embodiment analyzes the traffic conditions of each section according to the congestion conditions between adjacent sections.

[0057] Specifically, for each cycle, the congestion characteristic indexes of all time periods included in each day of the cycle are arranged in chronological order to obtain the congestion state sequence of each day;

[0058] The distance between each road section and the center point of other road sections is obtained and recorded as the first distance; and a preset number x=4 road sections with the smallest first distance between each road section and each road section are taken as adjacent road sections of each road section.

[0059] When congestion occurs on a certain road section, congestion will also occur on the adjacent road sections. Moreover, the faster the congestion correlation speed is, the worse the traffic conditions of the road section are.

[0060] First, the mean absolute value of the correlation between the daily congestion status series of each road section and all its adjacent road sections is calculated, which is recorded as the congestion correlation factor of each road section every day;

[0061] For each time period of each day, the mean difference in traffic volume between each road section and all its adjacent road sections is calculated; the average value of the mean difference in traffic volume for each road section at all time periods of each day is taken as the traffic volume transfer delay index for each road section every day;

[0062] The smaller the traffic flow transfer delay index is, the more likely the traffic flow on this road section is to be quickly transferred to other road sections when there is congestion.

[0063] The larger the congestion correlation factor, the more easily the traffic status of the adjacent road section is affected by the congestion of the road section. Then, the speed of mutual influence of traffic flow between adjacent roads is further analyzed.

[0064] Thus, the influence of a certain road section on the congestion degree of adjacent road sections is analyzed. For each road section, the congestion influence coefficient of the kth day in the i-th cycle is recorded as , the calculation formula is:

[0065]

[0066] In the formula, represents the congestion impact coefficient of the kth day in the ith period, represents the congestion correlation factor on the kth day in the ith period, represents the traffic flow transfer delay index of the kth day in the ith period.

[0067] The smaller the traffic flow transfer delay index is, the more likely the traffic flow on this road section is to be quickly transferred to other road sections when there is congestion; the larger the congestion correlation factor is, the more likely the traffic state of the adjacent road section is to be affected by the congestion on this road section. The larger it is, the greater the impact of the road section on the congestion of other road sections.

[0068] Arrange the congestion impact coefficients of adjacent road sections corresponding to each day in the i-th cycle in ascending order of time, and record them as the congestion impact sequence. Since a road section may be congested for a short period of time due to factors such as road construction or traffic accidents, the congestion is in a state that can be quickly recovered. However, if the same congestion impact occurs in different cycles, it indicates that the road section is a congested section. Therefore, for each road section, arrange the congestion impact coefficients of all days in each cycle in chronological order to obtain the congestion impact sequence of each cycle;

[0069] Calculate the SBD (Stop Bar Distance) distance of the congestion impact sequence corresponding to any two cycles, and record it as the second distance; take the average of the second distances of all cycles in pairs as the road condition difference of each section. The smaller the road condition difference is, the closer the traffic congestion state of the section is in different cycles.

[0070] S4. For each road section, the congestion risk coefficient of each cycle is obtained by combining the changing trend of the average road occupancy rate in all time periods of each cycle and the difference in road conditions; the traffic assessment result of each cycle is obtained according to the value of the congestion risk coefficient of each cycle; a visualized digital model of the urban area is established, and the traffic assessment results are marked in the visualized digital model of the urban area.

[0071] The average road occupancy rate of a road section indicates the coverage of the road section by vehicles. Different sections may have different traffic volumes due to different road widths. The road condition characteristics can be more accurately obtained by combining the average road occupancy rate. If the average road occupancy rate sequence shows an increasing trend, it means that the vehicle occupancy rate of the road section is higher. For each road section, obtain the trend test statistic of the average road occupancy rate sequence composed of the average road occupancy rate of all time periods in each cycle in chronological order; obtain an exponential function with the natural constant e as the base and the trend test statistic as the exponent; and use the ratio of the calculation result of the exponential function to the road condition difference of each section as the congestion risk coefficient of each cycle.

[0072] Since the trend test statistic of the average road occupancy rate series may be negative, an exponential function is used to process it to ensure that it is always greater than 0. The greater the difference in road conditions and the greater the difference in congestion conditions, the greater the congestion risk coefficient, which means that congestion is more likely to occur on this road section.

[0073] This application analyzes the traffic service data of the urban area and obtains the congestion risk coefficient of each road section in each cycle in the urban area. The larger the congestion risk coefficient, the higher the congestion level of the corresponding road section, which in turn affects the overall traffic smoothness of the urban area. In order to accurately quantify the degree of congestion, the linear normalized value of the congestion risk coefficient of each road section in each cycle is obtained. The road condition is evaluated according to the linear normalized value of the congestion risk coefficient. Set the first congestion threshold and the second congestion threshold ; For each road section, the period when the linear normalized value of the congestion risk coefficient is less than or equal to the first congestion threshold is recorded as the period of time without congestion; the period when the linear normalized value of the congestion risk coefficient is greater than the first congestion threshold and less than the second congestion threshold is recorded as the normal traffic period; the period when the linear normalized value of the congestion risk coefficient is greater than the second congestion threshold is recorded as the congestion period; wherein the first congestion threshold Less than the second congestion threshold .

[0074] After obtaining the evaluation results, the service center module uses 3D modeling technology to build a visualized digital model of the urban area. This application uses 3ds Max software to implement it. Then the traffic evaluation results are marked in the visualized digital model of the urban area to provide a reference for urban planning and management.

[0075] Through the above description of the implementation method in combination with the accompanying drawings, technical personnel in the relevant field can understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0076] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be covered by the protection scope of the present application.

Claims

1. A digital modeling method for urban areas based on data analysis, characterized in that: The method comprises the following steps: S1, collects the traffic volume, average vehicle speed and average road occupancy rate of each section of the urban area at each time period; S2, for each preset period, clustering the two-dimensional data points consisting of the traffic flow and average speed of all time periods in the period to obtain each cluster, and obtaining the congestion characteristic index of each time period according to the difference between the two-dimensional data points of the same cluster and different clusters; S3, according to the correlation between the congestion characteristic index of each road section and its adjacent road sections at all time periods every day in the cycle, the daily congestion correlation factor is obtained; according to the difference in traffic volume of each road section and its adjacent road sections at all time periods every day, the traffic flow transfer delay index is obtained; for each road section, the traffic flow transfer delay index and congestion correlation factor of each day in each cycle are combined to obtain the congestion impact coefficient of each cycle every day; according to the difference between the congestion impact coefficients of all days in different cycles of each road section, the road condition difference of each road section is obtained; S4, for each road section, combining the changing trend of the average road occupancy rate in all time periods of each cycle and the difference in road conditions, obtain the congestion risk coefficient of each cycle; obtain the traffic assessment result of each cycle according to the value of the congestion risk coefficient of each cycle; establish a visualized digital model of the urban area, and mark the traffic assessment result in the visualized digital model of the urban area; The method for obtaining the congestion characteristic index of each time period includes: The traffic volume and average speed of each time period are combined into two-dimensional data points of each time period; the two-dimensional data points of all time periods in the cycle are clustered to obtain clusters; According to the differences between the two-dimensional data points of different clusters, the heterogeneous difference means of each time period are obtained; Combining the differences between the two-dimensional data points of the same cluster and the heterogeneous difference means of each time period, the congestion characteristic index of each time period is obtained; The method for obtaining the heterogeneous difference mean of each time period includes: The two-dimensional data points that belong to different clusters from the two-dimensional data points of each time period are recorded as heterogeneous points; the mean distance between the two-dimensional data points of each time period and all its heterogeneous points is calculated, and recorded as the heterogeneous difference mean of each time period; The method combines the differences between the two-dimensional data points of the same cluster and the heterogeneous difference means of each time period to obtain the congestion characteristic index of each time period, including: recording the congestion characteristic index of the jth time period of the i-th cycle as , ;in, Represents the mean distance between the two-dimensional data points of the jth period of the i-th cycle and all other periods in the cluster to which it belongs; represents the heterogeneous difference mean of the jth period in the i-th period; It represents the difference between the traffic volume and the average speed in the jth period of the i-th cycle.

2. The urban area digital modeling method based on data analysis according to claim 1, characterized in that: The method for obtaining the daily congestion correlation factor includes: Arrange the congestion characteristic indexes of all time periods included in each day of the cycle in chronological order to obtain the congestion status sequence of each day; Obtain the distance between each road section and the center point of other road sections, recorded as the first distance; and use a preset number of road sections with the smallest first distances to each road section as adjacent road sections to each road section; The mean absolute value of the correlation between the daily congestion status series of each road section and all its adjacent road sections is calculated and recorded as the daily congestion correlation factor of each road section.

3. The urban area digital modeling method based on data analysis according to claim 2, characterized in that: The method for obtaining the traffic flow transfer delay index includes: For each time period of each day, the mean difference in traffic volume between each road section and all its adjacent road sections is calculated; the average value of the mean difference in traffic volume for each road section in all time periods of each day is taken as the traffic volume transfer delay index for each road section every day.

4. The urban area digital modeling method based on data analysis according to claim 1, characterized in that: The congestion impact coefficient of each cycle is obtained by combining the traffic flow transfer delay index and the congestion correlation factor of each cycle, including: recording the congestion impact coefficient of the kth day in the ith cycle as , ; In the formula, represents the congestion correlation factor on the kth day in the ith period, represents the traffic flow transfer delay index of the kth day in the ith period.

5. The urban area digital modeling method based on data analysis according to claim 1, characterized in that: The method for obtaining the road condition differences of each road section includes: For each road section, the congestion impact coefficients of all days in each cycle are arranged in chronological order to obtain the congestion impact sequence of each cycle; The distance between the congestion impact sequences corresponding to any two cycles is calculated and recorded as the second distance; the average of the second distances of all the cycles combined in pairs is taken as the road condition difference of each road section.

6. The urban area digital modeling method based on data analysis according to claim 1, characterized in that: The method for obtaining the congestion risk coefficient of each cycle includes: For each road section, obtain the trend test statistic of the average road occupancy sequence composed of the average road occupancy in all time periods of each cycle in chronological order; obtain an exponential function with a natural constant as the base and the trend test statistic as the exponent; and use the ratio of the calculation result of the exponential function and the road condition difference of each road section as the congestion risk coefficient of each cycle.

7. The urban area digital modeling method based on data analysis according to claim 1, characterized in that: The traffic assessment results of each period are obtained according to the value of the congestion risk coefficient of each period, including: Obtain the normalized value of the congestion risk coefficient of each road section in each period; for each road section, record the period in which the normalized value of the congestion risk coefficient is less than or equal to the first congestion threshold as a time period not prone to congestion; record the period in which the normalized value of the congestion risk coefficient is greater than the first congestion threshold and less than the second congestion threshold as a normal traffic time period; record the period in which the normalized value of the congestion risk coefficient is greater than the second congestion threshold as a congestion time period; wherein the first congestion threshold is less than the second congestion threshold.

Images