Traffic information management method and system

Abstract

The present invention relates to the field of data processing technology, and in particular to a traffic information management method and system. The method includes: obtaining a vehicle speed time series sequence and a corresponding traffic flow time series sequence, presetting the number of seed points in the speed data points, and evenly dividing the vehicle speed time series sequence into a plurality of speed data segments centered on various sub-points; presetting a search range of seed points in the speed data, and calculating a first similarity between the seed points and the speed data points within the search range; obtaining a traffic flow mean corresponding to the speed data segment and a traffic flow point corresponding to the speed data point within the search range, and calculating a second similarity between the seed points and the speed data points within the search range; combining the speed data points within the search range whose second similarity is greater than a preset similarity threshold with the corresponding seed points, obtaining a target data segment and processing it, so as to realize the management of traffic information data, which can effectively improve the efficiency of traffic information data management.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a traffic information management method and system. Background Art

[0002] With the acceleration of urbanization, the number of vehicles has also increased, leading to increased traffic pressure. The monitoring and management of vehicle speed is of great significance for reducing traffic accidents and improving road safety. In the management of vehicle speed, optimizing the data storage method can improve the storage device's capacity to accommodate vehicle speed time series, thereby more efficiently collecting, processing and analyzing vehicle speed time series, providing strong support for traffic monitoring, command, planning, design and safety assessment.

[0003] A patent application document with publication number CN114155717A discloses a method for screening traffic flow data. The method obtains traffic data, divides the data into each segment, and then screens the hourly traffic flow rate, spatial average speed and density corresponding to the data. The final screened samples are closer to a stable state. Therefore, a more reliable basic graph model of traffic flow can be fitted using the screened samples in this scheme.

[0004] The above-mentioned existing technical solutions can construct a basic traffic flow graph model by acquiring traffic information data to facilitate subsequent analysis. Traffic models often need to collect and store a large amount of vehicle flow data to facilitate subsequent analysis of traffic patterns or planning. However, the above-mentioned technical solutions do not record how to store a large amount of traffic information data in order to subsequently construct a traffic model.

[0005] Based on this, how to store and manage a large amount of traffic information data so as to facilitate subsequent analysis and planning is a technical problem that needs to be urgently solved by technical personnel in this field. Summary of the invention

[0006] In order to solve the technical problem of how to store and manage a large amount of traffic information data so as to facilitate subsequent analysis and planning, the present invention provides a traffic information management method and system.

[0007] In a first aspect, the present invention provides a traffic information management method, which adopts the following technical solution:

[0008] A traffic information management method comprises the steps of:

[0009] A vehicle speed time series sequence and a corresponding traffic flow time series sequence are obtained, wherein the vehicle speed time series sequence includes a plurality of speed data points; a number of seed points are preset in the speed data points, and the vehicle speed time series sequence is evenly divided into a plurality of speed data segments centered on various sub-points; a speed mean of the speed data segment is determined, and a search range of the seed points is preset in the vehicle speed time series sequence, a difference between the speed mean of the speed data segment of the seed point and the speed value of the speed data point within the search range is obtained, and a first similarity between the seed point and the speed data point within the search range is calculated, wherein the first similarity is negatively correlated with the absolute value of the difference; a traffic flow mean corresponding to the speed data segment and a traffic flow point corresponding to the speed data point within the search range are obtained, and a second similarity between the seed point and the speed data point within the search range is calculated, wherein the second similarity is positively correlated with the first similarity and negatively correlated with the absolute value of the difference between the traffic flow point and the traffic flow mean; a speed data point within the search range whose second similarity is greater than a preset similarity threshold is combined with the corresponding seed point to obtain a target data segment, and the target data segment is processed by a compression algorithm to achieve management of traffic information data.

[0010] The present invention takes into account that a large amount of repeated traffic information data will be obtained when managing traffic information. In order to improve the efficiency of traffic information management, the present invention obtains the deviation between various sub-points in the vehicle speed time series sequence and the speed data points in the search range, obtains the similarity between the seed point and the speed data points in the search range, divides the vehicle speed time series sequence into multiple target data segments, and compresses the target data segments, thereby improving the efficiency of traffic information data management; in addition, considering the influence of noise data in the vehicle speed time series sequence, the present invention also introduces a traffic flow time series sequence that is correlated with the vehicle speed time series sequence to screen the noise data, obtains the accurate similarity between the seed point and the speed data points in the search range, and can accurately divide the vehicle speed time series sequence, thereby effectively improving the efficiency of traffic information data management.

[0011] According to a traffic information management method provided by the present invention, the step of obtaining a vehicle speed time series sequence and a corresponding traffic flow time series sequence also includes: collecting the initial operating speed of the vehicle and the initial traffic flow by means of a collection device, respectively, and preprocessing the initial operating speed and the initial traffic flow to obtain the vehicle speed time series sequence and the traffic flow time series sequence.

[0012] The present invention can significantly improve the overall quality of vehicle speed time series and traffic flow time series through preprocessing, and effectively improve the accuracy of the similarity between the seed point and the speed data points within the search range.

[0013] According to a traffic information management method provided by the present invention, the first similarity between the seed point and the speed data point within the search range satisfies the relationship:

[0014] ;

[0015] In the formula, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The speed value of the i-th speed data point within the search range of the seed point, Indicates The velocity mean of the velocity data segment of the seed point, Indicates The variance of the velocity data segment of the seed point, Indicates that the The variance of the i-th velocity data point in the search range of the seed point after adding it to the velocity data segment, Indicates The sampling time of the seed point, Indicates The sampling time of the i-th velocity data point within the search range of the seed point, represents the exponential function with base e, represents the normalization function, Represents the absolute value symbol.

[0016] According to a traffic information management method provided by the present invention, the calculating the second similarity between the seed point and the speed data point within the search range also includes: obtaining a road visibility time series sequence corresponding to the vehicle speed time series sequence, determining a road visibility mean corresponding to the speed data segment, and a road visibility point corresponding to the speed data point within the search range; determining the second similarity between the seed point and the speed data point within the search range, the second similarity being negatively correlated with the absolute value of the difference between the road visibility point and the road visibility mean.

[0017] The present invention takes into account that during the data correction process, if there are problems with the accuracy of the traffic flow time series sequence itself, the error may be transferred to the vehicle speed time series sequence. Based on this, in order to obtain the second similarity more accurately, the embodiment of the present invention can also introduce another road visibility time series sequence in the traffic information data that is correlated with the vehicle speed time series sequence, and combine the traffic flow time series sequence and the road visibility time series sequence to jointly correct the first similarity, so that the second similarity can be accurately obtained.

[0018] According to a traffic information management method provided by the present invention, the second similarity between the seed point and the speed data point within the search range satisfies the relationship:

[0019] ;

[0020] In the formula, Indicates The second similarity between the seed point and the i-th velocity data point in the search range, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The traffic flow point corresponding to the i-th speed data point within the search range of the seed point, Indicates The mean traffic flow corresponding to the speed data segment of the seed point, Indicates The road visibility point corresponding to the i-th speed data point within the search range of seed points, Indicates The average road visibility corresponding to the speed data segment of the seed point, represents the exponential function with base e, Represents the absolute value symbol.

[0021] The present invention provides an accurate second similarity calculation method, which can effectively improve the accuracy of the second similarity by combining the traffic flow time series sequence and the road visibility time series sequence to jointly determine the second similarity between the seed point and the speed data point within the search range.

[0022] According to a traffic information management method provided by the present invention, the speed data points whose second similarity is greater than a preset similarity threshold within a search range are combined with corresponding seed points, including: within the search range, obtaining the sampling time corresponding to the speed data points whose second similarity is greater than a preset similarity threshold, marking the speed data points with the corresponding sampling time, and then combining them with the seed points.

[0023] The present invention takes into account that the difference in data values ​​between speed data points with higher similarity and seed points is smaller. Therefore, by obtaining speed data points with a second similarity greater than a preset similarity threshold and combining them with the seed points, the overall difference in data values ​​of speed data points in the target data segment is smaller.

[0024] According to a traffic information management method provided by the present invention, the target data segment is processed by a compression algorithm to achieve management of traffic information data, including: after processing the target data segment, a traffic prediction model is constructed through the vehicle speed time series to obtain traffic distribution prediction and manage it.

[0025] In a second aspect, the present invention provides a traffic information management system, which adopts the following technical solution:

[0026] A traffic information management system includes: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned traffic information management method is implemented.

[0027] By adopting the above technical solution, the above traffic information management method is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0028] The present invention has the following technical effects:

[0029] Based on the above scheme, when managing traffic information, the present invention can divide the vehicle speed time series sequence into multiple target data segments by obtaining the deviation between various sub-points in the vehicle speed time series sequence and the speed data points in the search range, and compress the target data segments, which can effectively improve the efficiency of traffic information data management; in addition, considering the influence of noise data in the vehicle speed time series sequence, the present invention also introduces a traffic flow time series sequence and a road visibility time series sequence that are correlated with the vehicle speed time series sequence, screens the noise data, and obtains the second similarity between the accurate seed point and the speed data points in the search range, which can accurately divide the vehicle speed time series sequence, thereby effectively improving the efficiency of traffic information data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0031] Figure 1 A flow chart of a traffic information management method provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0033] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0034] It should be noted that when using traffic information data, it is necessary to first store the traffic information data on a large scale so that traffic conditions can be predicted, analyzed and managed based on it later. Therefore, optimizing the storage method of traffic information data plays an important role in the management of traffic information data. There are many types of traffic information data, such as traffic flow, road vehicle data, vehicle speed, road visibility and vehicle model data. The embodiment of the present invention takes the storage of vehicle speed as an example to illustrate, but it does not mean that the embodiment of the present invention is limited to this.

[0035] When collecting vehicle speed time series, there will be a large amount of duplicate data in the data. In order to improve the utilization of storage space, the present invention combines speed data points with high similarity into the same data segment, and then uses a compression algorithm to find duplicate data in the target data segment to achieve data compression, which can effectively improve the efficiency of traffic information management.

[0036] Based on this, the embodiment of the present invention discloses a traffic information management method, see Figure 1 As shown, Figure 1 A flow chart of a traffic information management method provided by an embodiment of the present invention, the method comprises the following steps S1 to S5:

[0037] S1: Obtain vehicle speed time series and corresponding traffic flow time series.

[0038] The vehicle speed time series contains multiple speed data points.

[0039] It should be noted that when managing traffic information, it is necessary to collect and store traffic information data in advance to facilitate subsequent analysis of traffic patterns or planning. However, the amount of traffic information data collected is large and there is a large amount of duplicate data, and there will be the influence of noise data in the process of collecting traffic information. For example, when collecting vehicle data, it may be impossible to accurately obtain the similarity between speed data points due to the influence of surrounding electromagnetic equipment. Based on this, the embodiment of the present invention obtains a traffic flow time series sequence that is correlated with the vehicle speed time series sequence in the traffic information data, and distinguishes between noise data and normal data in the vehicle speed time series sequence to reduce the impact of noise data on the storage effect. Among them, the higher the traffic flow, the lower the vehicle speed, and the two are negatively correlated.

[0040] It is understandable that the initial data collected by the collection device can be pre-processed before subsequent processing.

[0041] For example, in an embodiment of the present invention, before obtaining the vehicle speed time series sequence and the corresponding traffic flow time series sequence, it is also possible to: respectively collect the initial running speed of the vehicle and the initial traffic flow through a collection device, pre-process the initial running speed and the initial traffic flow, and obtain the vehicle speed time series sequence and the traffic flow time series sequence. At the same sampling moment, the speed data points in the vehicle speed time series sequence and the traffic flow points in the traffic flow time series sequence correspond one by one.

[0042] For example, the collection device for collecting the initial running speed of the vehicle may be a magnetoelectric speed sensor, and the collection device for collecting the initial traffic flow may be an infrared sensor. The collection device may be specifically configured according to actual needs.

[0043] Among them, the preprocessing can be to convert the initial operating speed and initial traffic flow into an easily processible digital form through an analog-to-digital conversion device; the preprocessing method can be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0044] S2: Preset the number of seed points in the speed data points, and divide the vehicle speed time series into a plurality of speed data segments centered on various sub-points.

[0045] It should be noted that the vehicle speed time series will show a relatively stable data change trend over a period of time. In order to accurately obtain the similarity between speed data points, the embodiment of the present invention pre-sets the number of seed points in the speed data points and roughly divides the speed data, so as to better obtain the changes in the vehicle speed time series.

[0046] For example, the number of seed points can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0047] For example, after the vehicle speed time series is divided into a plurality of speed data segments centered at various sub-points, the speed data segments of various sub-points obtained have the same length.

[0048] For example: the number of seed points of the vehicle speed time series can be determined by the number of speed data points at intervals of 1 hour, that is, the speed data segment of the seed point contains speed data points within one hour. For example, if the speed data point collection interval is 1 minute, and the collection time is from 8:30 to 11:35, the seed points can be the speed data points corresponding to 9 o'clock, 10 o'clock and 11 o'clock respectively; the vehicle speed time series is divided based on the seed points, and the speed data segment of the seed point 9 is [8:30, 9:30], the speed data segment of the seed point 10 is [9:30, 10:30], and the speed data segment of the seed point 11 is [10:30, 11:30].

[0049] It should be noted that when the vehicle speed time series is divided based on the above method, there may be a situation where some speed data points at the end have no corresponding seed points.

[0050] In this case, the remaining speed data points at the end are automatically combined into a speed data segment, and the number of speed data points at the center of the speed data segment is obtained. The number of speed data points at the center of the speed data segment includes the following two possible situations:

[0051] In one possible case, the number of speed data points at the center of the speed data segment is 1. In this case, the speed data point at the center of the speed data segment is the seed point of the speed data segment.

[0052] In another possible case, the number of speed data points at the center of the speed data segment is 2. In this case, the speed data point close to the end of the speed data segment is used as the seed point of the speed data segment.

[0053] That is, in the above example, the vehicle speed time series sequence collected from 8:30 to 11:35 has a final number of seed points of 4, namely, the speed data points corresponding to 9 o'clock, 10 o'clock, 11 o'clock and 11:33 respectively.

[0054] After dividing the vehicle speed time series based on the above steps, the similarity between the speed data segment of the seed point and the speed data points within the search range can be analyzed, and the speed data points with higher similarity and the corresponding seed points can be recombined and divided, that is, continue to perform the following steps:

[0055] S3: Determine the speed mean of the speed data segment, and preset the search range of the seed point in the vehicle speed time series sequence, obtain the difference between the speed mean of the speed data segment of the seed point and the speed value of the speed data point in the search range, and calculate the first similarity between the seed point and the speed data point in the search range.

[0056] The first similarity is negatively correlated with the absolute value of the difference between the speed mean of the speed data segment of the seed point and the speed value of the speed data point within the search range.

[0057] It should be noted that in order to accurately obtain the speed data point that is relevant to the seed point in the search range, the speed change between the speed data point and the speed data segment of the seed point, as well as the change of the speed data segment before and after the speed data point is added can be analyzed, so as to obtain the influence of the speed data point on the speed data segment of the seed point.

[0058] For example, in the embodiment of the present invention, when the search ranges of various sub-points are preset, the lengths of the search ranges can be preset on both sides of the seed point with the various sub-points as the center. It should be noted that, considering that there is a high possibility that there are speed data points with high similarity in adjacent speed data segments, in order to better obtain speed data points with high similarity from adjacent data segments, the length of the search range of the seed point can be greater than the length of its speed data segment, and the length of the search range can be specifically set according to actual needs.

[0059] For example, if the acquisition interval of the speed data points is 1 minute, and the speed data segment of the obtained seed point is [9:30, 10:30], then the search range of the seed point is at least [9:29, 10:31].

[0060] It is understandable that the search range of various sub-points obtained in the above manner includes the speed data segment of the seed point, and the similarity between each speed data point in the search range and the speed data segment of the corresponding seed point is determined, and the similarity is used as the first similarity.

[0061] For example, in the embodiment of the present invention, the first similarity between the seed point and the speed data point within the search range is determined, and the specific similarity can be seen in the following formula:

[0062] ;

[0063] In the formula, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The velocity value of the i-th velocity data point within the search range of the seed point, Indicates The velocity mean of the velocity data segment of the seed point, Indicates The variance of the velocity data segment of the seed point, Indicates that the The variance of the i-th velocity data point in the search range of seed points after adding it to the velocity data segment, Indicates The sampling time of the seed point, Indicates The sampling time of the i-th velocity data point within the search range of the seed point, represents the exponential function with base e, represents the normalization function, Represents the absolute value symbol.

[0064] In the above formula, Indicates The velocity value of the i-th velocity data point within the search range of the seed point is The difference between the speed mean of the speed data segment of the seed points. The smaller the difference, the closer the speed data point is to the i-th speed data point. The closer the speed mean of the speed data segments of the seed points are, the i-th speed data point is divided into the The greater the possibility of the seed point being in the velocity data segment, the greater the corresponding first similarity.

[0065] Indicates The difference in variance of the speed data segment before and after the i-th speed data point is added within the search range of the seed point. The smaller the difference, the better the stability of the speed data segment after the i-th speed data point is added, and there is no significant fluctuation due to the addition of new data. That is, the i-th speed data point is divided into the The greater the possibility of the seed point being in the velocity data segment, the greater the corresponding first similarity.

[0066] Indicates The sampling time interval between the seed point and the i-th velocity data point in the search range, the smaller the time interval, the more accurate the sampling time. The closer the objective influencing factors are when the ith seed point and the ith speed data point are, the higher the reliability of the calculated first similarity is.

[0067] Based on the above method, the speed change between the speed data point and the speed data segment of the seed point is analyzed, and the first similarity between the speed data point and the speed data segment can be obtained. However, in the process of collecting the vehicle speed time series, due to the surrounding high-voltage wires, etc., there will be noise data in the collected vehicle speed time series, thereby affecting the accuracy of the first similarity obtained; in addition, due to the influence of objective factors, the vehicle speed time series will change. For example, when the traffic flow decreases, the vehicle speed will increase significantly. Such data belongs to normal data changes, but due to the large changes, it may be classified as noise data. Based on this, the first similarity can be corrected by obtaining data that is correlated with the vehicle speed time series, and the real noise data can be screened out to reduce the impact of noise data on the similarity.

[0068] S4: Obtain the traffic flow mean corresponding to the speed data segment and the traffic flow point corresponding to the speed data point within the search range, and calculate the second similarity between the seed point and the speed data point within the search range.

[0069] The second similarity is positively correlated with the first similarity, and negatively correlated with the absolute value of the difference between the traffic flow point and the traffic flow mean.

[0070] It should be noted that there is a correlation between the traffic flow time series sequence and the vehicle speed time series sequence in the traffic information data. The higher the traffic flow, the lower the vehicle speed. Therefore, the first similarity can be corrected by the correlation between the two to obtain the second similarity; however, in the data correction process, if there is a problem with the accuracy of the traffic flow time series sequence itself, the error may be transferred to the vehicle speed time series sequence, and ultimately lead to inaccurate correction results. Based on this, in order to more accurately obtain the second similarity, the embodiment of the present invention can also introduce another road visibility time series sequence in the traffic information data that is correlated with the vehicle speed time series sequence, and combine the traffic flow time series sequence and the road visibility time series sequence to jointly correct the first similarity, so that the second similarity can be accurately obtained; wherein, the higher the road visibility, the higher the vehicle speed.

[0071] For example, in an embodiment of the present invention, when determining the second similarity, a road visibility time series sequence corresponding to the vehicle speed time series sequence can also be obtained to determine the road visibility mean of the road visibility time series segment corresponding to the speed data segment, and the road visibility point corresponding to the speed data point within the search range; determine the second similarity between the seed point and the speed data point within the search range, and the second similarity is negatively correlated with the absolute difference between the road visibility point and the road visibility mean.

[0072] It can be understood that at the same sampling time, the speed data points, road visibility points and traffic flow correspond to each other. The average traffic flow and average road visibility corresponding to the above speed data segment both represent the average traffic flow and average road visibility in the same sampling time period as the speed data segment.

[0073] For example, in the embodiment of the present invention, the second similarity between the seed point and the speed data point within the search range is determined, and the specific similarity can be seen from the following relationship:

[0074] ;

[0075] In the formula, Indicates The second similarity between the seed point and the i-th velocity data point in the search range, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The traffic flow point corresponding to the i-th speed data point within the search range of the seed point, Indicates The mean traffic flow corresponding to the speed data segment of the seed point, Indicates The road visibility point corresponding to the i-th speed data point within the search range of seed points, Indicates The average road visibility corresponding to the speed data segment of the seed point, represents the exponential function with base e, Represents the absolute value symbol.

[0076] In the above formula, Indicates The difference between the traffic flow point corresponding to the ith speed data point and the traffic flow mean corresponding to the speed data segment within the search range of the seed point is smaller, indicating that the difference between the influence of the traffic flow point corresponding to the ith speed data point on the speed data and the influence of the traffic flow mean corresponding to the speed data segment on the speed data is smaller, and the credibility of the obtained second similarity is higher.

[0077] Indicates The difference between the road visibility point corresponding to the ith speed data point and the road visibility mean corresponding to the speed data segment within the search range of the seed points is calculated. The smaller the difference is, the smaller the difference is, indicating that the difference between the influence of the road visibility point corresponding to the ith speed data point on the speed data and the influence of the road visibility mean corresponding to the speed data segment on the speed data is, and the higher the credibility of the obtained second similarity is.

[0078] It can be understood that, the higher the second similarity of the speed data point, the smaller the possibility that the speed data point is noise data; and the lower the second similarity of the speed data point, the greater the possibility that the speed data point is noise data.

[0079] After obtaining the second similarity between the seed point and each speed data point in the search range based on the above steps, the speed data points with higher second similarity can be regrouped and divided with the corresponding seed points to obtain the target data segment.

[0080] S5: combining the speed data points within the search range whose second similarity is greater than the preset similarity threshold with the corresponding seed points to obtain a target data segment, and processing the target data segment through a compression algorithm to achieve management of traffic information data.

[0081] It should be noted that the higher the second similarity between the seed point and each speed data point in the search range, the smaller the data gap between the speed data point and the seed point. By combining speed data points with smaller data gaps, the vehicle speed time series can be re-divided into multiple target data segments. The data in the obtained target data segments have higher data repeatability. Compressing the target data segments with higher repeatability can effectively improve the efficiency of data compression, thereby effectively improving the management efficiency of traffic information data.

[0082] For example, in the embodiment of the present invention, when the speed data points are re-combined based on the comparison result between the second similarity and the preset similarity threshold, the following two possible situations are included:

[0083] In one possible case, the second similarity is greater than a preset similarity threshold. In this case, the sampling time corresponding to the speed data point whose second similarity is greater than the preset similarity threshold can be obtained within the search range, and the speed data point is marked with the corresponding sampling time and then combined with the speed data segment.

[0084] In another possible case, the second similarity is less than or equal to the preset similarity threshold. In this case, the speed data points corresponding to the second similarity less than or equal to the preset similarity threshold are used to form a new vehicle speed time series sequence, and the second similarity is recalculated based on the above steps S2-S5 for comparison, and this cycle is repeated until the second similarity between all speed data points in the new vehicle speed time series sequence and the seed point is less than or equal to the preset similarity threshold, the cycle is stopped, and each speed data point in the new vehicle speed time series sequence whose second similarity is less than or equal to the preset similarity threshold is used as a target data segment.

[0085] The similarity threshold may be preset to 0.8; the similarity threshold may be specifically set according to actual needs.

[0086] It should be noted that the search ranges of different seed points may overlap, so there may be a situation where the same speed data point belongs to the search ranges of multiple seed points; in this case, the second similarities between the speed data point and various sub-points are compared, and the speed data point is combined into the target data segment of the seed point with the largest second similarity to the speed data point; if the second similarities between the speed data point and various sub-points are equal, then any seed point can be selected for combination.

[0087] It can be understood that if the second similarity between a speed data point in the search range of the seed point and the seed point is less than or equal to the preset similarity threshold, the speed data point will not be divided into the target data segment where the seed point is located. The speed data points in the target data segment finally obtained only have a time sequence, but their time intervals are not exactly the same, so each speed data point needs to be marked.

[0088] After obtaining the target data segment in the vehicle speed time series sequence based on the above method, the target data segment can be compressed, and the management of traffic information data can be achieved based on the compressed data.

[0089] Among them, the compression processing of the target data segment can be achieved through a compression algorithm, such as LZ77 compression algorithm, LZ78 compression algorithm, etc., which can be specifically set according to actual needs. The embodiment of the present invention takes the processing of vehicle speed timing sequence by LZ77 compression algorithm as an example, but it does not mean that the embodiment of the present invention is limited to this.

[0090] For example, when the vehicle speed time series is processed by the LZ77 compression algorithm, each target data segment can be compressed by the LZ77 algorithm one by one. In each target data segment, the LZ77 algorithm will find the longest repeated data substring, and then use a pointer pair to represent the repeated data substring to replace the original data in the target data segment, and combine the results of each target data segment after algorithm compression into a final compressed data stream or file, thereby achieving compression. The vehicle speed time series sequence generated by the final compression includes two parts: a pointer pair and a literal value.

[0091] The pointer pair is used to indicate the location where the repeated data substring appears and gives the length of the repeated data substring. The literal is used to indicate the unmatched data in the target data segment, that is, the data part that cannot be represented by the pointer pair.

[0092] For example, after the target data segment is compressed, a traffic prediction model can be constructed through the vehicle speed time series to obtain traffic distribution prediction and manage it. When obtaining the compressed vehicle speed time series for analysis, the literal data obtained by compression can be focused on.

[0093] It can be seen that in the embodiment of the present invention, when managing traffic information data, the present invention obtains a vehicle speed time series sequence and a corresponding traffic flow time series sequence, wherein the vehicle speed time series sequence includes a plurality of speed data points; presets the number of seed points in the speed data points, and divides the vehicle speed time series sequence into a plurality of speed data segments with various sub-points as the center; determines the speed mean of the speed data segment, obtains the preset search range of the seed point in the speed data, obtains the difference between the speed mean of the speed data segment of the seed point and the speed value of the speed data point within the search range, and calculates the first similarity between the seed point and the speed data point within the search range, wherein the first similarity is negatively correlated with the absolute value of the difference; obtains the traffic flow mean corresponding to the speed data segment and the traffic flow point corresponding to the speed data point within the search range, calculates the second similarity between the seed point and the speed data point within the search range, wherein the second similarity is positively correlated with the first similarity and negatively correlated with the absolute value of the difference between the traffic flow point and the traffic flow mean; combines the speed data point within the search range whose second similarity is greater than the preset similarity threshold with the corresponding seed point to obtain the target data segment, and processes the target data segment through a compression algorithm to achieve management of traffic information data.

[0094] In this way, the present invention obtains the deviation between various sub-points in the vehicle speed time series sequence and the speed data points in the search range to obtain the first similarity between the seed point and the speed data points in the search range, and can divide the vehicle speed time series sequence into multiple target data segments, and compress the target data segments, which can effectively improve the efficiency of traffic information data management; in addition, considering the influence of noise data in the vehicle speed time series sequence, the present invention also introduces a traffic flow time series sequence and a road visibility time series sequence that are correlated with the vehicle speed time series sequence, screens the noise data, and obtains the accurate second similarity between the seed point and the speed data points in the search range, which can accurately divide the vehicle speed time series sequence, thereby effectively improving the efficiency of traffic information data management.

[0095] The embodiment of the present invention further discloses a traffic information management system, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a traffic information management method according to the present invention is implemented.

[0096] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0097] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0098] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0099] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A traffic information management method, characterized in that: include: Acquire a vehicle speed time series sequence and a corresponding traffic flow time series sequence, wherein the vehicle speed time series sequence includes a plurality of speed data points; Presetting the number of seed points in the speed data points, and dividing the vehicle speed time series into a plurality of speed data segments centered on various sub-points; Determine a speed mean of the speed data segment, preset a search range of a seed point in the vehicle speed time series, obtain a difference between the speed mean of the speed data segment of the seed point and the speed data points within the search range, and calculate a first similarity between the seed point and the speed data points within the search range, wherein the first similarity is negatively correlated with an absolute value of the difference; Obtaining a traffic flow mean corresponding to the speed data segment and a traffic flow point corresponding to a speed data point within a search range, calculating a second similarity between the seed point and the speed data point within the search range, wherein the second similarity is positively correlated with the first similarity and negatively correlated with an absolute value of a difference between the traffic flow point and the traffic flow mean, and calculating the second similarity between the seed point and the speed data point within the search range further comprises: Acquire a road visibility time series sequence corresponding to the vehicle speed time series sequence, determine a road visibility mean corresponding to the speed data segment, and a road visibility point corresponding to a speed data point within a search range; Determining a second similarity between the seed point and the speed data point within the search range, wherein the second similarity is negatively correlated with an absolute value of a difference between the road visibility point and a road visibility mean; The second similarity between the seed point and the velocity data point within the search range satisfies the relationship: ； In the formula, Indicates The second similarity between the seed point and the i-th velocity data point in the search range, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The traffic flow point corresponding to the i-th speed data point within the search range of the seed point, Indicates The mean traffic flow corresponding to the speed data segment of the seed point, Indicates The road visibility point corresponding to the i-th speed data point within the search range of seed points, Indicates The average road visibility corresponding to the speed data segment of the seed point, represents the exponential function with base e, Indicates the absolute value symbol; The speed data points whose second similarity is greater than a preset similarity threshold within the search range are combined with corresponding seed points to obtain a target data segment, and the target data segment is processed by a compression algorithm to achieve management of traffic information data.

2. A traffic information management method according to claim 1, characterized in that: The step of obtaining the vehicle speed time series and the corresponding traffic flow time series also includes: The initial running speed of the vehicle and the initial traffic flow are respectively collected by the collecting device, and the initial running speed and the initial traffic flow are preprocessed to obtain the vehicle speed time series sequence and the traffic flow time series sequence.

3. A traffic information management method according to claim 1, characterized in that: The first similarity between the seed point and the speed data point within the search range satisfies the relationship: ； In the formula, Indicates The first similarity between the seed point and the i-th velocity data point in the search range, Indicates The velocity value of the i-th velocity data point within the search range of the seed point, Indicates The velocity mean of the velocity data segment of the seed point, Indicates The variance of the velocity data segment of the seed point, Indicates that the The variance of the i-th velocity data point in the search range of seed points after adding it to the velocity data segment, Indicates The sampling time of the seed point, Indicates The sampling time of the i-th velocity data point within the search range of the seed point, represents the exponential function with base e, represents the normalization function, Represents the absolute value symbol.

4. A traffic information management method according to claim 1, characterized in that: The combining of the speed data points within the search range whose second similarity is greater than a preset similarity threshold with corresponding seed points includes: In the search range, the sampling time corresponding to the speed data point whose second similarity is greater than the preset similarity threshold is obtained, and the speed data point is marked with the corresponding sampling time and then combined with the seed point.

5. A traffic information management method according to claim 1, characterized in that: The target data segment is processed by a compression algorithm to achieve management of traffic information data, including: After processing the target data segment, a traffic prediction model is constructed through the vehicle speed time series to obtain traffic distribution prediction and manage it.

6. A traffic information management system, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a traffic information management method according to any one of claims 1 to 5 is implemented.

Images