Traffic data processing method, device and equipment based on heterogeneous truck flow

Abstract

The embodiment of the invention discloses a traffic data processing method, device and equipment based on heterogeneous truck flow, and relates to the technical field of data processing. The method comprises the following steps: determining a plurality of traffic flow characteristics according to different truck types, and taking the traffic flow characteristics as traffic state evaluation indexes; setting a classic domain and a node domain according to a preset traffic state grade and a traffic state evaluation index; determining a traffic state level matter element and a correlation function of the to-be-evaluated state road section according to the classic domain and the node domain; constructing a judgment matrix; determining an entropy weight coefficient according to the judgment matrix; performing weighted summation according to the correlation function, the traffic state level matter elements and all entropy weight coefficients to obtain a comprehensive correlation degree; and determining the maximum comprehensive association degree in all the comprehensive association degrees as a target comprehensive association degree, thereby determining the target traffic state grade of the to-be-evaluated state road section. In this way, the complexity of the traffic state can be comprehensively reflected by selecting a plurality of truck flow characteristic indexes for evaluation.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device and equipment for processing traffic data based on heterogeneous truck traffic. Background Art

[0002] Traffic status assessment includes direct assessment. The direct traffic status assessment method generally converts different levels of traffic status into one-dimensional time series data, and usually ignores the changes in different traffic parameters during the assessment. Summary of the invention

[0003] In view of this, the purpose of the present invention is to overcome the shortcomings of the prior art and to provide a traffic data processing method, device and equipment based on heterogeneous truck flow, which is used to evaluate the traffic status of a road section through multiple traffic flow characteristics, thereby avoiding ignoring the changes in different traffic parameters in the evaluation.

[0004] The present invention provides the following technical solutions: In a first aspect, the present invention proposes a traffic data processing method based on heterogeneous truck traffic, comprising: Determine multiple traffic flow characteristics according to different truck models, and use each of the traffic flow characteristics as a traffic state evaluation indicator; and set a classic domain and a section domain according to the preset traffic state level and each of the traffic state evaluation indicators, the classic domain is used to indicate the kth traffic state evaluation indicator and its corresponding indicator value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index and its corresponding index value range under the preset traffic state level, where: , , The number of evaluation indicators for the traffic state; Determine, according to the classical domain and the section domain, a traffic state level matter-element of the i-th road section to be evaluated and a correlation function of the k-th traffic state evaluation index under the i-th road section to be evaluated; Constructing a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate the target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; Determine the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix; A weighted sum is performed according to the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients to obtain a comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels; The maximum comprehensive correlation degree among all comprehensive correlation degrees is determined as the target comprehensive correlation degree; and the preset traffic state level corresponding to the target comprehensive correlation degree is determined as the target traffic state level corresponding to the i-th state section to be evaluated.

[0005] In one embodiment, the expression of the correlation function is: ; in, , , ; In the formula, for arrive The distance between for arrive The distance between For the i The next section of the road to be evaluated k The correlation function value of the traffic status evaluation index is is the first j The indicator value range corresponding to the preset traffic status level is is the indicator value range corresponding to the kth traffic state evaluation indicator under all preset traffic state levels in the node domain, and They are The upper and lower limits of and They are The upper and lower limits of is the number of the road sections in the state to be evaluated.

[0006] In one implementation, determining the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix includes: Determine the entropy of the kth traffic state evaluation index according to the judgment matrix; According to the entropy of the kth traffic state evaluation index, an entropy weight coefficient of the kth traffic state evaluation index is determined.

[0007] In one implementation, determining the entropy of the kth traffic state evaluation index according to the judgment matrix includes: Standardization is performed according to the judgment matrix to obtain a standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; Calculating the entropy of the kth traffic state evaluation index according to the entropy calculation formula; The calculation formula of the entropy is: ; In the formula, is the entropy of the k-th traffic state evaluation index, It is the standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level.

[0008] In one implementation, determining the entropy weight coefficient of the kth traffic state evaluation index according to the entropy of the kth traffic state evaluation index includes: Calculating the entropy weight coefficient of the kth traffic state evaluation index according to the calculation formula of the entropy weight coefficient; The calculation formula of the entropy weight coefficient is: , ; In the formula, is the entropy weight coefficient of the kth traffic state evaluation index, is the entropy of the k-th traffic state evaluation index.

[0009] In one embodiment, the weighted summation of the correlation function, the traffic state level matter-element of the i-th state section to be evaluated, and all entropy weight coefficients to obtain the comprehensive correlation degree of the i-th state section to be evaluated under each of the traffic state levels includes: Calculating the correlation function value of the kth traffic state evaluation index under the i-th road section to be evaluated according to the correlation function and the traffic state level matter-element of the i-th road section to be evaluated; The comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels is obtained by performing a weighted summation based on the entropy weight coefficients of all traffic state evaluation indicators and all correlation function values.

[0010] In one implementation, the calculation formula for the comprehensive correlation degree is: ; In the formula, is the comprehensive correlation degree of the i-th road section to be evaluated under the j-th preset traffic state level, is the entropy weight coefficient of the kth traffic state evaluation index.

[0011] In a second aspect, the present invention provides a traffic data processing device based on heterogeneous truck traffic, comprising: The setting module is used to determine multiple traffic flow characteristics according to different truck models, and use each of the traffic flow characteristics as a traffic state evaluation indicator; and set a classic domain and a section domain according to the preset traffic state level and each of the traffic state evaluation indicators, wherein the classic domain is used to indicate the kth traffic state evaluation indicator and its corresponding indicator value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index and its corresponding index value range under the preset traffic state level, where: , , The number of evaluation indicators for the traffic state; A first determination module is used to determine the correlation function between the traffic state level matter-element of the i-th road section to be evaluated and the k-th traffic state evaluation index under the i-th road section to be evaluated according to the classical domain and the section domain; A construction module, used to construct a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate a target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; A second determination module is used to determine the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix; A calculation module, used for performing weighted summation according to the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients, to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels; The processing module is used to determine the maximum comprehensive correlation degree among all comprehensive correlation degrees as the target comprehensive correlation degree; and determine the preset traffic state level corresponding to the target comprehensive correlation degree as the target traffic state level corresponding to the i-th state section to be evaluated.

[0012] In a third aspect, the present invention proposes a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the traffic data processing method based on heterogeneous truck flow as described in the first aspect is implemented.

[0013] In a fourth aspect, the present invention proposes a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the traffic data processing method based on heterogeneous truck traffic as described in the first aspect.

[0014] The present invention discloses a traffic data processing method, device and equipment based on heterogeneous truck traffic, which determines multiple traffic flow characteristics according to different truck models, and uses each of the traffic flow characteristics as a traffic state evaluation index; and sets a classical domain and a section domain according to a preset traffic state level and each of the traffic state evaluation indicators; determines the traffic state level object element of the i-th state section to be evaluated, and the correlation function of the k-th traffic state evaluation index under the i-th state section to be evaluated according to the classical domain and the section domain; constructs a judgment matrix, and the judgment matrix is ​​used to indicate the target value corresponding to the k-th traffic state evaluation index under the j-th preset traffic state level; determines the entropy weight coefficient of the k-th traffic state evaluation index according to the judgment matrix; performs weighted summation according to the correlation function, the traffic state level object element of the i-th state section to be evaluated and all entropy weight coefficients, and obtains the comprehensive correlation degree of the i-th state section to be evaluated under each of the traffic state levels; determines the maximum comprehensive correlation degree among all the comprehensive correlation degrees as the target comprehensive correlation degree; and determines the target traffic state level corresponding to the i-th state section to be evaluated according to the target comprehensive correlation degree. In this way, by selecting multiple truck flow characteristic indicators for evaluation, the complexity of traffic status can be fully reflected; by setting the classical domain and the node domain, the uncertainty and ambiguity problems in traffic status evaluation can be flexibly handled; the weight of each indicator is calculated by the entropy weight method, which avoids the uncertainty of subjective weighting and improves the objectivity and scientificity of the evaluation; the matching degree of each indicator of the road section to be evaluated is quantified by the correlation function; by calculating the comprehensive correlation degree, the influence of each indicator is combined, and the traffic status level of the road section can be more accurately judged. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solution of the present invention, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be regarded as limiting the scope of protection of the present invention. In each of the drawings, similar components are numbered similarly.

[0016] Figure 1 A schematic diagram of a flow chart of a traffic data processing method based on heterogeneous truck traffic proposed in this embodiment is shown; Figure 2 Another schematic diagram of the process of the traffic data processing method based on heterogeneous truck traffic proposed in this embodiment is shown; Figure 3 Another schematic diagram of a flow chart of a traffic data processing method based on heterogeneous truck traffic proposed in this embodiment is shown; Figure 4 A schematic diagram showing the accuracy of traffic status assessment proposed in this embodiment; Figure 5A schematic diagram of the structure of a traffic data processing device based on heterogeneous truck traffic proposed in this embodiment is shown.

[0017] Description of main figures: 500 - a traffic data processing device based on heterogeneous truck traffic; 501 - a setting module; 502 - a first determination module; 503 - a construction module; 504 - a second determination module; 505 - a calculation module; 506 - a processing module. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0019] The components of the embodiments of the present invention generally described and shown in the drawings herein may be arranged and designed in a variety of different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected 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 work are within the scope of protection of the present invention.

[0020] Hereinafter, the terms "including", "having" and their cognates, which may be used in various embodiments of the present invention, are intended only to indicate specific features, numbers, steps, operations, elements, components or combinations of the foregoing items, and should not be understood as first excluding the existence of one or more other features, numbers, steps, operations, elements, components or combinations of the foregoing items or adding the possibility of one or more features, numbers, steps, operations, elements, components or combinations of the foregoing items.

[0021] Furthermore, the terms “first”, “second”, “third”, etc. are merely used for distinguishing descriptions and are not to be understood as indicating or implying relative importance.

[0022] Unless otherwise defined, all terms (including technical terms and scientific terms) used herein have the same meanings as those generally understood by those skilled in the art to which the various embodiments of the present invention belong. The terms (such as those defined in generally used dictionaries) will be interpreted as having the same meanings as the contextual meanings in the relevant technical field and will not be interpreted as having idealized meanings or overly formal meanings unless clearly defined in the various embodiments of the present invention.

[0023] Example 1 The disclosed embodiment provides a traffic data processing method based on heterogeneous truck traffic, which is used to evaluate the traffic status of a road section through multiple traffic flow characteristics, thereby avoiding ignoring the changes of different traffic parameters in the evaluation.

[0024] See also Figure 1 , a traffic data processing method based on heterogeneous truck traffic includes steps S101~S106, and each step is described in detail below.

[0025] Step S101, determining a plurality of traffic flow characteristics according to different truck models, taking each of the traffic flow characteristics as a traffic state evaluation index; and setting a classic domain and a section domain according to a preset traffic state level and each of the traffic state evaluation indexes.

[0026] The classic domain is used to indicate the kth traffic state evaluation index and its corresponding index value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index under the preset traffic state level and its corresponding index value range, where: , , is the number of traffic status evaluation indicators.

[0027] In this embodiment, among the traffic parameters, the traffic flow characteristics of trucks of different models are selected as traffic status evaluation indicators. The traffic flow characteristics include small truck flow, medium truck flow, large truck flow, extra-large truck flow, and truck flow, so that the traffic status can be more accurately described through multi-indicator comprehensive evaluation, especially in the scenario of heterogeneous truck flow.

[0028] Furthermore, the classic domain and the section domain are set according to the preset traffic state level and each traffic state evaluation index. The preset traffic state level is set as y The traffic status evaluation indicators that affect the traffic status level are n The classical domain The expression is:

[0029] In the formula, is the jth preset traffic status level; ; For the Traffic status evaluation indicators, ; is the jth preset traffic status level, The indicator value domain after dimensionless quantization of traffic status evaluation indicators; , They represent the jth preset traffic state level, The lower and upper limits of the indicator value range.

[0030] Take the maximum and minimum values ​​of the upper and lower limits of the indicator value domain of each traffic state evaluation indicator in all preset traffic state levels to form a section domain for evaluating the traffic state. , the section domain is expressed as: .

[0031] In the formula, Indicates all preset traffic status levels; Indicates that under all preset traffic status levels, The indicator value range of the traffic status evaluation index is The maximum value range of , Respectively represent the traffic status of all preset levels. The lower limit and upper limit of the indicator value domain corresponding to each traffic state evaluation indicator.

[0032] Step S102, determining the traffic state level matter-element of the i-th road section to be evaluated and the correlation function of the k-th traffic state evaluation index under the i-th road section to be evaluated according to the classical domain and the section domain.

[0033] In this embodiment, the number of road sections to be evaluated in the traffic state to be evaluated is m , then i Traffic status level matter-element of the road section to be evaluated It is expressed as:

[0034] In the formula, Indicates i Traffic status level matter-element of the road section to be evaluated; Indicates i road sections to be evaluated with traffic conditions to be evaluated; Indicates i The next section of the road to be evaluated The indicator value domain corresponding to each traffic status evaluation indicator is the actual value domain of the indicator.

[0035] Furthermore, according to the comprehensive evaluation method of the matter-element extension model, the classical domain and the node domain are used to determine the i The next section of the road to be evaluated Traffic status evaluation index j The correlation function of the preset traffic state level.

[0036] Traffic status itself is fuzzy and dynamic, and traditional methods may not accurately reflect the actual situation. However, the matter-element extension model can better handle this uncertainty by calculating the matching degree between the index value and the traffic status level through the correlation function.

[0037] Specifically, the correlation function It is expressed as: .

[0038] in, , , ; ; .

[0039] In the formula, for arrive The distance between for arrive The distance between For the i The next section of the road to be evaluated k The correlation function value of the traffic state evaluation index.

[0040] Step S103: constructing a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate a target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level.

[0041] In this embodiment, the judgment matrix is ​​a matrix used to describe the values ​​of each indicator at each traffic state level. It is usually determined by preset traffic parameters composed of expert experience, historical data or experimental data. The construction of the judgment matrix is ​​to quantify the typical characteristic values ​​of each traffic state evaluation indicator at each preset traffic state level, so as to provide basic data for the subsequent. Its form is: , , .

[0042] It should be noted that the target values ​​in the judgment matrix are the typical characteristics of each indicator under each preset traffic state level. i The actual value range of the indicators under the road section to be evaluated is the actual observed value of each indicator of the road section to be evaluated.

[0043] Step S104: determining the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix.

[0044] In this embodiment, the entropy weight coefficient is used to reflect the importance of the kth traffic state evaluation index and is obtained according to the judgment matrix.

[0045] See also Figure 2, step S104 includes steps S1041~S1042, and each step is described in detail below.

[0046] Step S1041, determining the entropy of the kth traffic state evaluation index according to the judgment matrix.

[0047] In this embodiment, the judgment matrix is ​​first standardized, and then the entropy of the kth traffic state evaluation index is determined using the standardized judgment matrix to measure the information content of the index.

[0048] In a specific embodiment, step S1041 includes: performing standardization according to the judgment matrix to obtain a standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; calculating the entropy of the kth traffic state evaluation index according to the entropy calculation formula; wherein the entropy calculation formula is: ; In the formula, is the entropy of the k-th traffic state evaluation index, It is the standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level.

[0049] In this embodiment, the judgment matrix is ​​standardized to obtain a standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; and the entropy of the kth traffic state evaluation index is further calculated according to the entropy calculation formula.

[0050] The calculation formula of entropy is: ; In the formula, is the entropy of the kth traffic state evaluation index, is the standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level, is a normalization factor used to limit the entropy value to the range [0,1][0,1], It reflects the amount of information of the kth traffic state evaluation index at the jth preset traffic state level.

[0051] Step S1042: Determine the entropy weight coefficient of the kth traffic state evaluation index according to the entropy of the kth traffic state evaluation index.

[0052] In this embodiment, the entropy weight coefficient of the kth traffic state evaluation index is calculated according to the entropy of the kth traffic state evaluation index. Meanwhile, the entropy weight coefficients of all traffic state evaluation indexes must satisfy the condition that the sum value is 1.

[0053] In a specific embodiment, step S1042 includes: calculating the entropy weight coefficient of the kth traffic state evaluation index according to the calculation formula of the entropy weight coefficient; wherein the calculation formula of the entropy weight coefficient is: , ; In the formula, is the entropy weight coefficient of the kth traffic state evaluation index, is the entropy of the k-th traffic state evaluation index.

[0054] In this embodiment, the entropy weight coefficient of the kth traffic state evaluation index is calculated according to the calculation formula of the entropy weight coefficient; wherein the calculation formula of the entropy weight coefficient is: , ; In the formula, is the entropy weight coefficient of the kth traffic state evaluation index, is the entropy of the kth traffic state evaluation index, It represents the information content of the kth traffic state evaluation index. The smaller the entropy value, the greater the information content. It is the sum of the entropy values ​​of all traffic state evaluation indicators.

[0055] Step S105, performing weighted summation based on the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients, to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels.

[0056] In this embodiment, a correlation function is used to calculate the traffic status level object element of the i-th road section to be evaluated, and multiple correlation function values ​​corresponding to the i-th road section to be evaluated can be obtained; further, each correlation function value is weightedly summed with each entropy weight coefficient, so as to obtain the comprehensive correlation degree of the i-th road section to be evaluated at each traffic status level, that is, the weighted correlation degree.

[0057] The comprehensive correlation degree indicates the comprehensive matching degree of the i-th road section to be evaluated under each traffic state level. By combining the correlation degree and entropy weight coefficient of each indicator, it can comprehensively reflect the matching degree between the road section to be evaluated and each traffic state level.

[0058] See also Figure 3 In a specific embodiment, step S105 includes steps S1051 to S1052, and each step is described in detail below.

[0059] Step S1051, calculating the correlation function value of the kth traffic state evaluation index of the i-th road section to be evaluated according to the correlation function and the traffic state level matter-element of the i-th road section to be evaluated.

[0060] In this embodiment, the traffic state level object element of the i-th road section to be evaluated is substituted into the correlation function, and the correlation function value of the j-th preset traffic state level of each traffic state evaluation indicator under the i-th road section to be evaluated is calculated respectively.

[0061] Step S1052, performing weighted summation based on the entropy weight coefficients of all traffic state evaluation indicators and all correlation function values, to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels.

[0062] In this embodiment, for each preset traffic state level, the entropy weight coefficient of each traffic state evaluation index and the various correlation function values ​​corresponding to the traffic state level are weighted and summed respectively to obtain the comprehensive correlation degree of the i-th road section to be evaluated at the preset traffic state level, and further obtain the comprehensive correlation degree of the i-th road section to be evaluated at each preset traffic state level.

[0063] In a specific embodiment, the calculation formula of the comprehensive correlation degree is: ; In the formula, is the comprehensive correlation degree of the i-th road section to be evaluated under the j-th preset traffic state level, is the entropy weight coefficient of the kth traffic state evaluation index.

[0064] In this embodiment, the calculation formula of the comprehensive correlation degree is: ; In the formula, is the comprehensive correlation degree of the i-th road section to be evaluated under the j-th preset traffic state level, is the entropy weight coefficient of the kth traffic state evaluation index.

[0065] Step S106, determining the maximum comprehensive correlation degree among all comprehensive correlation degrees as the target comprehensive correlation degree; and determining the preset traffic state level corresponding to the target comprehensive correlation degree as the target traffic state level corresponding to the i-th state section to be evaluated.

[0066] In this embodiment, according to the maximum correlation recognition principle, the maximum value of each comprehensive correlation degree is determined and used as the target comprehensive correlation degree, and the preset traffic state level corresponding to the target comprehensive correlation degree is used as the target traffic state level of the i-th state section to be evaluated. The specific expression is: , is the target traffic status level corresponding to the i-th road section to be evaluated.

[0067] By identifying the maximum comprehensive correlation degree, the preset traffic state level with the highest matching degree for the i-th road section to be evaluated is determined, so as to accurately judge the target traffic state level to which the road section to be evaluated belongs, avoiding the misjudgment that may be caused by a single indicator or a simple threshold method; at the same time, by utilizing the existing traffic flow data, combined with the matter-element extension model and the entropy weight method, efficient traffic state evaluation can be achieved at a lower cost.

[0068] As an example, the truck traffic flow data of a small road network consisting of 6 road sections in a certain city was selected for traffic status assessment. The descriptive statistics of the data are shown in Table 1.

[0069] Table 1:

[0070] The traffic status level is set to 5 levels, namely, unimpeded, basically unimpeded, slightly congested, moderately congested, and severely congested. The range of heterogeneous truck flow indicators in the region under different traffic conditions is obtained by the fuzzy evaluation method, as shown in Table 2.

[0071] Table 2:

[0072] Heterogeneous truck traffic flow is evaluated using a truck traffic flow evaluation model based on operation and spatiotemporal characteristics. The obtained evaluation value is used as the input of a traffic data processing model based on heterogeneous truck traffic, and the evaluated traffic state value is calculated through the model.

[0073] Furthermore, the traffic status results of heterogeneous truck traffic are evaluated, and the accuracy of model evaluation is defined. The evaluated traffic status is compared with the traffic status estimated by the full traffic characteristics in the indicator set. If the results are consistent, it is recorded as 1, and if the results are inconsistent, it is recorded as 0. The number of traffic statuses with consistent judgment results g is recorded. The accuracy is the number of traffic statuses with consistent judgment results and the total number of samples. G The ratio of is expressed as: Accuracy .

[0074] The actual traffic state estimation results are used as comparison objects, and compared with different traffic state evaluation results and the overall traffic state evaluation results. The traffic state evaluation accuracy is as follows: Figure 4 shown.

[0075] from Figure 4 It can be seen that the overall accuracy of the traffic state assessment results considering heterogeneous truck traffic flow is 80.99%. The accuracy of traffic state judgment under different states is slightly different. The highest accuracy of traffic state judgment for smooth levels is 87.00%; the judgment accuracy for light congestion and moderate congestion is relatively low, at 76.54% and 75.87% respectively. Analysis shows that the fuzzy range union range of the traffic flow characteristics of light congestion and moderate congestion is large, resulting in a low accuracy rate of traffic state assessment; the judgment accuracy of traffic states of basically smooth and severely congested traffic exceeds 80%, and the traffic state assessment effect is good.

[0076] It should be noted that when it comes to national and provincial trunk roads and expressway-grade roads, the GPS data of trucks can be used to more reliably assess traffic conditions when the equipment does not collect enough data and the speed and flow parameters of the entire vehicle section cannot be obtained.

[0077] The present embodiment proposes a traffic data processing method based on heterogeneous truck traffic, which determines multiple traffic flow characteristics according to different truck models, and uses each of the traffic flow characteristics as a traffic state evaluation index; and sets a classical domain and a section domain according to a preset traffic state level and each of the traffic state evaluation indicators; determines the traffic state level object element of the i-th state section to be evaluated, and the correlation function of the k-th traffic state evaluation index under the i-th state section to be evaluated according to the classical domain and the section domain; constructs a judgment matrix, and the judgment matrix is ​​used to indicate the target value corresponding to the k-th traffic state evaluation index under the j-th preset traffic state level; determines the entropy weight coefficient of the k-th traffic state evaluation index according to the judgment matrix; performs weighted summation according to the correlation function, the traffic state level object element of the i-th state section to be evaluated, and all entropy weight coefficients to obtain the comprehensive correlation degree of the i-th state section to be evaluated under each of the traffic state levels; determines the maximum comprehensive correlation degree among all the comprehensive correlation degrees as the target comprehensive correlation degree; and determines the target traffic state level corresponding to the i-th state section to be evaluated according to the target comprehensive correlation degree. In this way, by selecting multiple truck flow characteristic indicators for evaluation, the complexity of traffic status can be fully reflected; by setting the classical domain and the node domain, the uncertainty and ambiguity problems in traffic status evaluation can be flexibly handled; the weight of each indicator is calculated by the entropy weight method, which avoids the uncertainty of subjective weighting and improves the objectivity and scientificity of the evaluation; the matching degree of each indicator of the road section to be evaluated is quantified by the correlation function; by calculating the comprehensive correlation degree, the influence of each indicator is combined, and the traffic status level of the road section can be more accurately judged.

[0078] Example 2 In addition, the present disclosure provides a traffic data processing device 500 based on heterogeneous truck traffic, see Figure 5 ,include: The setting module 501 is used to determine multiple traffic flow characteristics according to different truck models, and use each of the traffic flow characteristics as a traffic state evaluation indicator; and set a classic domain and a section domain according to the preset traffic state level and each of the traffic state evaluation indicators, wherein the classic domain is used to indicate the kth traffic state evaluation indicator and its corresponding indicator value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index and its corresponding index value range under the preset traffic state level, where: , , The number of evaluation indicators for the traffic state; A first determination module 502 is used to determine the correlation function between the traffic state level matter-element of the i-th road section to be evaluated and the k-th traffic state evaluation index under the i-th road section to be evaluated according to the classical domain and the section domain; A construction module 503 is used to construct a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate a target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; A second determination module 504 is used to determine the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix; A calculation module 505 is used to perform weighted summation according to the correlation function, the traffic state level matter-element of the i-th state section to be evaluated and all entropy weight coefficients to obtain the comprehensive correlation degree of the i-th state section to be evaluated under each of the traffic state levels; The processing module 506 is used to determine the maximum comprehensive correlation degree among all comprehensive correlation degrees as the target comprehensive correlation degree; and determine the preset traffic state level corresponding to the target comprehensive correlation degree as the target traffic state level corresponding to the i-th state section to be evaluated.

[0079] Optionally, the expression of the correlation function is: ;in, , , ; In the formula, for arrive The distance between for arrive The distance between For the i The next section of the road to be evaluated k The correlation function value of the traffic status evaluation index is is the first j The indicator value range corresponding to the preset traffic status level is is the indicator value range corresponding to the kth traffic state evaluation indicator under all preset traffic state levels in the node domain, and They are The upper and lower limits of and They are The upper and lower limits of is the number of the road sections in the state to be evaluated.

[0080] Optionally, the second determination module 504 is used to determine the entropy of the kth traffic state evaluation index according to the judgment matrix; and determine the entropy weight coefficient of the kth traffic state evaluation index according to the entropy of the kth traffic state evaluation index.

[0081] Optionally, the second determination module 504 is used to perform standardization according to the judgment matrix to obtain a standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; and calculate the entropy of the kth traffic state evaluation index according to an entropy calculation formula; wherein the entropy calculation formula is: ; In the formula, is the entropy of the k-th traffic state evaluation index, It is the standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level.

[0082] Optionally, the second determination module 504 is used to calculate the entropy weight coefficient of the kth traffic state evaluation index according to the calculation formula of the entropy weight coefficient; wherein the calculation formula of the entropy weight coefficient is: , ; In the formula, is the entropy weight coefficient of the kth traffic state evaluation index, is the entropy of the k-th traffic state evaluation index.

[0083] Optionally, the calculation module 505 is used to calculate the correlation function value of the kth traffic state evaluation index of the i-th road section to be evaluated based on the correlation function and the traffic state level object element of the i-th road section to be evaluated; and to perform weighted summation based on the entropy weight coefficients of all traffic state evaluation indicators and all correlation function values ​​to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels.

[0084] Optionally, the calculation formula of the comprehensive correlation degree is: ; In the formula, is the comprehensive correlation degree of the i-th road section to be evaluated under the j-th preset traffic state level, is the entropy weight coefficient of the kth traffic state evaluation index.

[0085] The device provided in the embodiment of the present disclosure can execute the steps of the traffic data processing method based on heterogeneous truck flow provided in Example 1, which will not be described again to avoid repetition.

[0086] The traffic data processing device based on heterogeneous truck traffic proposed in this embodiment determines multiple traffic flow characteristics according to different truck models, and uses each of the traffic flow characteristics as a traffic state evaluation index; and sets a classical domain and a section domain according to a preset traffic state level and each of the traffic state evaluation indicators; determines the traffic state level object element of the i-th state section to be evaluated and the correlation function of the k-th traffic state evaluation index under the i-th state section to be evaluated according to the classical domain and the section domain; constructs a judgment matrix, and the judgment matrix is ​​used to indicate the target value corresponding to the k-th traffic state evaluation index under the j-th preset traffic state level; determines the entropy weight coefficient of the k-th traffic state evaluation index according to the judgment matrix; performs weighted summation according to the correlation function, the traffic state level object element of the i-th state section to be evaluated, and all entropy weight coefficients to obtain the comprehensive correlation degree of the i-th state section to be evaluated under each of the traffic state levels; determines the maximum comprehensive correlation degree among all the comprehensive correlation degrees as the target comprehensive correlation degree; and determines the target traffic state level corresponding to the i-th state section to be evaluated according to the target comprehensive correlation degree. In this way, by selecting multiple truck flow characteristic indicators for evaluation, the complexity of traffic status can be fully reflected; by setting the classical domain and the node domain, the uncertainty and ambiguity problems in traffic status evaluation can be flexibly handled; the weight of each indicator is calculated by the entropy weight method, which avoids the uncertainty of subjective weighting and improves the objectivity and scientificity of the evaluation; the matching degree of each indicator of the road section to be evaluated is quantified by the correlation function; by calculating the comprehensive correlation degree, the influence of each indicator is combined, and the traffic status level of the road section can be more accurately judged.

[0087] Example 3 In addition, an embodiment of the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the traffic data processing method based on heterogeneous truck flow described in Example 1 is implemented.

[0088] The device provided in the embodiment of the present disclosure can execute the steps of the traffic data processing method based on heterogeneous truck flow provided in Example 1, which will not be described again to avoid repetition.

[0089] Example 4 The disclosed embodiment proposes a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the method for processing traffic data based on heterogeneous truck traffic described in Embodiment 1 is implemented.

[0090] In this embodiment, the computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0091] The computer-readable storage medium provided in this embodiment can implement the traffic data processing method based on heterogeneous truck traffic provided in Example 1, and will not be described again here to avoid repetition.

[0092] In all examples shown and described herein, any specific values ​​should be interpreted as merely exemplary and not as limiting, and thus other examples of the exemplary embodiments may have different values.

[0093] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0094] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A traffic data processing method based on heterogeneous truck traffic, characterized in that: include: Determine a plurality of traffic flow characteristics according to different truck models, and use each of the traffic flow characteristics as a traffic state evaluation indicator; According to the preset traffic state level and each of the traffic state evaluation indicators, a classic domain and a section domain are set, wherein the classic domain is used to indicate the kth traffic state evaluation indicator and its corresponding indicator value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index under the preset traffic state level and its corresponding index value range, where: , , The number of evaluation indicators for the traffic state; Determine, according to the classical domain and the section domain, a traffic state level matter-element of the i-th road section to be evaluated and a correlation function of the k-th traffic state evaluation index under the i-th road section to be evaluated; Constructing a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate the target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; Determine the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix; A weighted sum is performed according to the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients to obtain a comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels; The maximum comprehensive correlation degree among all comprehensive correlation degrees is determined as the target comprehensive correlation degree; and the preset traffic state level corresponding to the target comprehensive correlation degree is determined as the target traffic state level corresponding to the i-th state section to be evaluated.

2. The traffic data processing method based on heterogeneous truck traffic according to claim 1 is characterized in that: The expression of the correlation function is: ; in, , , ; In the formula, for arrive The distance between for arrive The distance between For the i The next section of the road to be evaluated k The correlation function value of the traffic status evaluation index is is the first j The indicator value range corresponding to the preset traffic status level is is the indicator value range corresponding to the kth traffic state evaluation indicator under all preset traffic state levels in the node domain, and They are The upper and lower limits of and They are The upper and lower limits of is the number of the road sections in the state to be evaluated.

3. The traffic data processing method based on heterogeneous truck traffic according to claim 1 is characterized in that: Determining the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix includes: Determine the entropy of the kth traffic state evaluation index according to the judgment matrix; According to the entropy of the kth traffic state evaluation index, an entropy weight coefficient of the kth traffic state evaluation index is determined.

4. The traffic data processing method based on heterogeneous truck traffic according to claim 3 is characterized in that: The step of determining the entropy of the kth traffic state evaluation index according to the judgment matrix includes: Standardization is performed according to the judgment matrix to obtain a standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; Calculating the entropy of the kth traffic state evaluation index according to the entropy calculation formula; The calculation formula of the entropy is: ; In the formula, is the entropy of the k-th traffic state evaluation index, It is the standardized value corresponding to the kth traffic state evaluation index under the jth preset traffic state level.

5. The traffic data processing method based on heterogeneous truck traffic according to claim 3 is characterized in that: Determining the entropy weight coefficient of the kth traffic state evaluation index according to the entropy of the kth traffic state evaluation index includes: Calculating the entropy weight coefficient of the kth traffic state evaluation index according to the calculation formula of the entropy weight coefficient; The calculation formula of the entropy weight coefficient is: , ; In the formula, is the entropy weight coefficient of the kth traffic state evaluation index, is the entropy of the k-th traffic state evaluation index.

6. The traffic data processing method based on heterogeneous truck traffic according to claim 1 is characterized in that: The weighted summation of the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each traffic state level includes: Calculating the correlation function value of the kth traffic state evaluation index under the i-th road section to be evaluated according to the correlation function and the traffic state level matter-element of the i-th road section to be evaluated; The comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels is obtained by performing a weighted summation based on the entropy weight coefficients of all traffic state evaluation indicators and all correlation function values.

7. The traffic data processing method based on heterogeneous truck traffic according to claim 6 is characterized in that: The calculation formula of the comprehensive correlation degree is: ; In the formula, is the comprehensive correlation degree of the i-th road section to be evaluated under the j-th preset traffic state level, is the entropy weight coefficient of the kth traffic state evaluation index.

8. A traffic data processing device based on heterogeneous truck traffic, characterized in that: include: A setting module, for determining a plurality of traffic flow characteristics according to different truck models, and using each of the traffic flow characteristics as a traffic state evaluation indicator; According to the preset traffic state level and each of the traffic state evaluation indicators, a classic domain and a section domain are set, wherein the classic domain is used to indicate the kth traffic state evaluation indicator and its corresponding indicator value domain under the jth preset traffic state level, and the section domain is used to indicate y The kth traffic state evaluation index under the preset traffic state level and its corresponding index value range, where: , , The number of evaluation indicators for the traffic state; A first determination module is used to determine the correlation function between the traffic state level matter-element of the i-th road section to be evaluated and the k-th traffic state evaluation index under the i-th road section to be evaluated according to the classical domain and the section domain; A construction module, used to construct a judgment matrix according to preset traffic parameters, wherein the judgment matrix is ​​used to indicate a target value corresponding to the kth traffic state evaluation index under the jth preset traffic state level; A second determination module is used to determine the entropy weight coefficient of the kth traffic state evaluation index according to the judgment matrix; A calculation module, used for performing weighted summation according to the correlation function, the traffic state level matter-element of the i-th road section to be evaluated and all entropy weight coefficients, to obtain the comprehensive correlation degree of the i-th road section to be evaluated under each of the traffic state levels; The processing module is used to determine the maximum comprehensive correlation degree among all comprehensive correlation degrees as the target comprehensive correlation degree; and determine the preset traffic state level corresponding to the target comprehensive correlation degree as the target traffic state level corresponding to the i-th state section to be evaluated.

9. A computer device, characterized in that: It includes a memory and a processor, the memory stores a computer program, and when the computer program is executed by the processor, the traffic data processing method based on heterogeneous truck flow as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the traffic data processing method based on heterogeneous truck traffic as described in any one of claims 1 to 7.

Images