Large-scale road network state studying and judging method based on adaptive macroscopic fundamental diagram

Abstract

According to the large-scale road network state studying and judging method based on the self-adaptive macroscopic fundamental diagram, the self-adaptive macroscopic fundamental diagram is constructed by means of flow and speed data in a statistical period of a large-scale road network section, and the critical state of the self-adaptive macroscopic fundamental diagram is obtained; and acquiring the real-time road section average speed and the real-time road section average flow of the road section, studying and judging the road network state of the large-scale road network based on the real-time road section average speed, the real-time road section average flow and the critical state, and studying and judging the road network state of the large-scale road network based on the critical state.

Description

Technical Field

[0001] This application relates to the field of urban road traffic, and in particular to a method for assessing the state of large-scale road networks based on an adaptive macroscopic basic map. Background Technology

[0002] Urban transportation, as a core infrastructure supporting socio-economic operation and ensuring residents' daily travel, directly impacts the functioning of cities and the well-being of the people. With the accelerated pace of urbanization and the continuous increase in motor vehicle ownership, traffic flow on large-scale road networks has experienced explosive growth, leading to increasingly prominent problems such as traffic congestion and low traffic efficiency. A prerequisite for effective regional traffic organization and management is the description and characterization of the regional road network's condition; however, describing the condition of a regional road network presents numerous challenges.

[0003] The macroscopic fundamental diagram (MFD), as a core tool for characterizing the average state of a region, establishes a functional relationship between the average flow rate and average density of the region. It can intuitively reflect the overall traffic operation patterns of the road network, providing important theoretical support for road network status assessment. However, the macroscopic fundamental diagram is only applicable to homogeneous road networks. In homogeneous road networks, the traffic flow characteristics (such as speed, density, and flow rate) of each road segment are relatively similar, and macroscopic indicators such as the average flow rate and density of the region can accurately characterize the overall operating state of the road network. Therefore, the macroscopic fundamental diagram exhibits high stability and reliability.

[0004] However, the application of macroscopic basic maps in large-scale road network scenarios faces severe challenges. Actual large-scale road networks often have significant heterogeneity, which is mainly manifested in the following aspects: First, the heterogeneity of road network structure. Large-scale road networks include roads of different levels, such as arterial roads, secondary arterial roads, and local roads. The design standards, traffic capacity, and functional positioning of roads of different levels are fundamentally different. Second, the heterogeneity of traffic flow characteristics. The distribution of traffic flow in different road segments is uneven, and the traffic flow status of core areas and peripheral areas is significantly different.

[0005] The heterogeneity of road networks leads to anomalies in the description of road network conditions in macro-level basic maps. These maps fail to adequately consider the functional and traffic flow differences among different road segments within the network, resulting in scattered points and distorted curves, making it difficult to accurately capture the true operational patterns of the road network. This problem directly leads to two major consequences: First, traditional macro-level basic maps struggle to obtain reliable critical states of the road network (such as critical flow, critical density, and critical speed). These critical states are key thresholds for distinguishing between different operational stages, such as smooth traffic flow and congestion, and their accuracy directly impacts the scientific nature of traffic control decisions. Second, traditional macro-level basic maps have significant errors in state assessment, easily leading to situations where congestion is misjudged as smooth traffic flow or vice versa, failing to provide accurate decision support for traffic management departments and consequently affecting the effectiveness of traffic control measures. Summary of the Invention

[0006] This application provides a method for assessing the state of a large-scale road network based on an adaptive macroscopic basic graph. The method aims to construct an adaptive macroscopic basic graph through a series of innovative means such as time stage division, road segment clustering, and weight optimization, and to obtain critical states based on the adaptive macroscopic basic graph. Based on the critical states, the method can achieve accurate road network state assessment in a large-scale road network.

[0008] In a first aspect, embodiments of this application provide a method for assessing the state of a large-scale road network based on an adaptive macroscopic basic map, comprising the following steps: S1: Collect the original average traffic flow and original average speed of all road segments in the large-scale road network at multiple time steps within the statistical period. Calculate the original average density and regional average density of each road segment at each time step based on the original average traffic flow and original average speed, and calculate the proportion of regional congested road segments at each time step based on the original average speed. S2: Based on the proportion of congested road segments in the region and the average density in the region, cluster analysis is performed on the time step to divide the day into several time periods. The road segments in each time period are clustered to obtain road segment clusters. The weights of road segments in the same time period and the same road segment cluster are set to be equal. The weights of the road segments are optimized to obtain adaptive weights. S3: Calculate the optimized regional average flow, regional average velocity, and regional average density based on adaptive weights, construct an adaptive macroscopic basic graph based on the regional average flow, regional average velocity, and regional average density, and obtain the critical state based on the adaptive macroscopic graph. S4: Obtain the real-time average speed and average traffic flow of road segments, and analyze the road network status of large-scale road networks based on the real-time average speed, average traffic flow, and critical state.

[0009] Secondly, embodiments of this application provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the large-scale road network state assessment method based on an adaptive macroscopic basic map.

[0010] The main contributions and innovations of this invention are as follows: This application provides a method for assessing the state of a large-scale road network based on an adaptive macroscopic basic map. First, using segment traffic flow and speed data from the large-scale road network, the average regional traffic flow, average regional speed, and average regional density are calculated. Simultaneously, the proportion of congested road segments in the region is calculated based on the segment speed data. Based on this, adaptive weights for the road segments are obtained through optimization using the proportion of congested road segments and the average regional traffic flow, average regional density, and average regional speed. The average regional traffic flow, average density, and average speed are then recalculated using these optimized adaptive weights, thereby constructing an adaptive macroscopic basic map. The critical state of the large-scale road network is obtained through this adaptive macroscopic basic map, and the road network state is assessed based on this critical state.

[0011] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0012] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of a large-scale road network state assessment method based on an adaptive macroscopic basic graph according to an embodiment of this application; Figure 2 This is a diagram showing the time-stage division results of Example 2; Figure 3 This is the result of constructing the adaptive macroscopic basic graph in Example 2; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0013] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0014] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.

[0015] Example 1 Figure 1 This is a schematic diagram of the large-scale road network state assessment method based on an adaptive macroscopic basic map, as presented in this scheme. The large-scale road network state assessment method based on an adaptive macroscopic basic map provided in this scheme includes the following steps: S1: Collect the original average traffic flow and original average speed of all road segments in the large-scale road network at multiple time steps within the statistical period. Calculate the original average density and regional average density of each road segment at each time step based on the original average traffic flow and original average speed, and calculate the proportion of regional congested road segments at each time step based on the original average speed. S2: Based on the proportion of congested road segments in the region and the average density in the region, cluster analysis is performed on the time step to divide the day into several time periods. The road segments in each time period are clustered to obtain road segment clusters. The weights of road segments in the same time period and the same road segment cluster are set to be equal. The weights of the road segments are optimized to obtain adaptive weights. S3: Calculate the optimized regional average flow, regional average velocity, and regional average density based on adaptive weights, construct an adaptive macroscopic basic graph based on the optimized regional average flow, regional average velocity, and regional average density, and obtain the critical state based on the adaptive macroscopic graph. S4: Obtain the real-time average speed and average traffic flow of road segments, and analyze the road network status of large-scale road networks based on the real-time average speed, average traffic flow, and critical state.

[0016] As described above, this solution provides a road network status assessment method based on an adaptive macroscopic basic map that can be applied to large-scale road networks. The critical state is obtained based on the constructed adaptive macroscopic map, and the road network status of large-scale road networks is assessed based on the critical state. This method can be less affected by regional heterogeneity and thus improve the accuracy of road network status assessment for large-scale road networks.

[0017] Specifically, regarding step S1: This scheme divides the large-scale road network into multiple road segments. A road segment is the smallest continuous road unit within the pre-defined large-scale road network research area, bounded by traffic flow monitoring breakpoints, where traffic flow and speed data can be collected independently. Typically, a road segment is defined as a section of road between two intersections.

[0018] It should be noted that road segments generally need to be manually divided, but for certain special road networks, segments can be divided according to actual needs. Furthermore, the "area" within a road segment is not a boundless, all-encompassing road network, and a "road segment" is not necessarily the "entire road," but rather a continuous, uninterrupted segment of road formed by natural boundaries such as road intersections and the locations of traffic flow / speed monitoring equipment. For example, a main road traversing a core area, if data collection equipment is installed at 3 intersections and 2 intermediate monitoring points along its route, will be divided into 4 independent road segments, each with complete traffic flow data collection capabilities.

[0019] In some embodiments, the original average traffic flow and original average speed of each road segment within each time step are obtained. That is, the average traffic flow of the road segment within a time step is obtained as the original average traffic flow of the road segment in the current time step, and the average speed of the road segment within a time step is obtained as the original average speed of the road segment in the current time step.

[0020] It should be noted that this scheme takes the average flow rate and average speed of the original road segment within a time step. The advantage of this is that it smooths out instantaneous traffic fluctuations and eliminates abnormal interference items, so that the analysis data is more in line with the normal traffic flow characteristics of the road segment.

[0021] In some embodiments, a time step is 5 min, 10 min, or 15 min.

[0022] In some embodiments, the average of the original road segment average speeds of all road segments at each time step is taken as the regional average speed, and the average of the original road segment average traffic flows of all road segments at each time step is taken as the regional average traffic flows.

[0023] In some embodiments, the quotient of the original road segment's average flow rate and the original road segment's average speed is taken as the original road segment's average density, calculated using the following formula: ; in k it Let be the original average density of the i-th road segment at the t-th time step. q it Let be the original average traffic flow of the i-th road segment at the t-th time step. v it Let be the original average speed of the i-th road segment at the t-th time step.

[0024] Similarly, the quotient of the regional average flow and the regional average velocity is taken as the regional average density.

[0025] Furthermore, this scheme calculates the free-flow speed of road segments based on the original average speed of road segments, calculates the congestion situation of each road segment at each time step based on the free-flow speed of road segments and the original average speed of road segments, and calculates the proportion of regional congested road segments at each time step based on the congestion situation of each road segment at each time step and the congestion situation of all road segments.

[0026] In some embodiments, the original average speed of each road segment at all time steps is taken as the free flow speed of the road segment after sorting the original average speed of the road segment in ascending order.

[0027] Furthermore, the average speed of the original road segment at the 95th percentile after sorting the original road segment average speeds at all time steps of each road segment from smallest to largest is taken as the free flow speed of the road segment.

[0028] Specifically, the formula for calculating the proportion of congested road sections in a region is as follows: ; Where v it v is the original average speed of the i-th road segment at the t-th time step. fi Let cong be the free-flow velocity at time step t for the i-th road segment. it Let t represent the congestion status of the i-th road segment at time t, where 1 indicates congestion and 0 indicates no congestion. thre It sets the parameter, r t Let be the proportion of congested road segments in the region at time step t.

[0029] Regarding step S2: This scheme uses the regional average density and the proportion of congested road segments at each time step as feature vectors to automatically divide a day into several time periods with similar regional traffic conditions. It abandons the coarseness of subjective fixed time period division, accurately adapts to the time heterogeneity of the road network, and provides a stable temporal analysis unit for subsequent independent road segment clustering and optimization of the adaptive weights corresponding to "time stage - road segment cluster". This reduces the interference of mixed traffic characteristics at different time periods on weight optimization and macro basic map construction, thereby improving the accuracy of large-scale road network status assessment.

[0030] Specifically, in order to eliminate the interference of abnormal daily fluctuations on time period division, this scheme takes the average of the regional congestion road segment ratio at the same time step of each day within the statistical period as the daily average regional congestion road segment ratio at the current time step, and takes the average of the regional average density at the same time step of each day within the statistical period as the daily average regional average density at the current time step. The daily average regional congestion road segment ratio and the daily average regional average density at each time step are used as feature vectors to perform ordered sample clustering analysis to divide a day into several time periods.

[0031] In some embodiments, the number of time periods is set, and the time steps are clustered using ordered sample clustering analysis to divide a day into several time periods, each time period consisting of several time steps with similar regional traffic conditions.

[0032] Specifically, the time steps of each day are arranged in chronological order, and the feature vector of each time step is the daily average proportion of congested road segments and the daily average density of road segments. The number of time periods is set as the number of clusters. The sum of squared Euclidean distances is used to measure the feature similarity of all time steps within a time period as the intra-class dissimilarity. The goal is to minimize the total intra-class dissimilarity and perform ordered sample clustering on all time steps to cluster all time steps within a day into multiple time periods.

[0033] It should be emphasized again that this scheme uses time steps as ordered samples and congestion coverage and congestion level as characteristics. It uses dynamic programming to find the division scheme with the smallest difference within the general category, so as to divide the day into multiple time periods with similar traffic conditions in multiple areas, in order to ensure adaptation to the temporal heterogeneity of the road network.

[0034] Furthermore, this scheme divides the road segments into multiple time periods and then performs spatial clustering on the road segments within each time period to obtain road segment clusters. This allows the road segment clusters within each time period to accurately reflect the functional differences of the road segments under that time period, effectively eliminating the interference caused by the dynamic changes in spatial heterogeneity at different time periods, making road segment classification more targeted, and accurately adapting to the spatial heterogeneity of large-scale road networks.

[0035] In some embodiments, the average original road segment flow rate, average original road segment speed, and average original road segment density at each time step within the current time period are used as feature vectors to cluster the road segments to obtain road segment clusters.

[0036] Specifically, the number of road segment clusters is set, and the mean values ​​of the original road segment average traffic flow, original road segment average speed, and original road segment average density at each time step in the current time period are used as feature vectors. The k-means algorithm is used to cluster the road segments to divide the road segments in each time period into multiple road segment clusters.

[0037] This scheme, after clustering time periods and road segments, assigns equal weights to road segments within the same time period and road segment cluster. It then performs objective optimization on the road segment weights and solves for adaptive weights. ; in w it w represents the weight of the i-th segment at time step t. mn This represents the weight of the m-th road segment cluster in the n-th time period.

[0038] In some embodiments, the weights of road segments in a road segment cluster are optimized by setting objectives and constraints, and adaptive weights are obtained by solving the problem. In some embodiments, the constraints include weight normalization constraints, weight non-negativity constraints, and macro-basic graph constraints. The weight normalization constraints limit the sum of the weights of all road segments at each time step to 1. The weight non-negativity constraints limit the weight of each optimized road segment to a non-negative number. The macro-basic graph constraints limit the construction of a macro-basic graph according to the adaptive weights, and the critical state is obtained based on this macro-basic graph.

[0039] In some embodiments, the differential evolution algorithm is used to optimize the weights of road segments in a road segment cluster and solve for adaptive weights.

[0040] Specifically, the target for optimization is expressed as follows: ; The constraints are:

[0041] ; in N It is the number of time steps within a time period. order(xt) The function is for { xt Sort the sequence. xt The sorting number it belongs to. The parameters to be fitted are... uf For the region's theoretical free flow velocity, Qop For regional theoretical accessibility, Kj For theoretical blockage density, The theoretical congestion wave dissipation velocity, Qt Let be the regional average flow rate at time step t. wit Let i be the weight of the i-th segment at time step t. qit Let be the original average traffic flow of the i-th segment at time step t. kit Let be the original average road segment density of the i-th road segment at time step t. Kt Let be the region average density at time step t. rc-uThe percentage of time steps where a congested situation is misjudged as a non-congested situation based on the macro-level baseline map. ru-c α represents the percentage of time steps in which a non-congested situation is misjudged as a congested situation based on the macro-level baseline graph, and is a weighting coefficient.

[0042] In some embodiments, a threshold β is set. If the time step meets a first condition, the current time step is the time step where the congestion situation is misjudged as a non-congestion situation; if the time step meets a second condition, the current time step is the time step where the non-congestion situation is misjudged as a congestion situation. The first condition is: ; The second condition is: ; in Kc The critical density of the fitted macroscopic fundamental graph. Kt Let be the regional average density of the road segment cluster at time step t. rt Let be the proportion of congested road segments in the region at time step t.

[0043] In some embodiments, the proportion of time steps in which a congestion situation is misjudged as a non-congestion situation out of all time steps in the current time period is taken as the proportion of time steps in which a congestion situation is misjudged as a non-congestion situation based on the macro basic map, and the proportion of time steps in which a non-congestion situation is misjudged as a congestion situation out of all time steps in the current time period is taken as the proportion of time steps in which a non-congestion situation is misjudged as a congestion situation based on the macro basic map.

[0044] As mentioned above, the objective of this scheme is to minimize the difference between 1 and the Spearman correlation coefficient of the proportion of congested road segments and the average density, as well as the weighted congestion misclassification rate. The optimization objective aims to make the macro-basic map and the results of the proportion of congested road segments as consistent as possible, and sets constraints to ensure that the optimized weights conform to traffic flow theory and avoid physical contradictions in the indicators.

[0045] Regarding step S3 of this plan: After obtaining the adaptive weights, this scheme calculates the optimized regional average flow, regional average speed, and regional average density based on these weights. Specifically, the optimized regional average flow is obtained by weighting the original average flow of each road segment at the current time step with the adaptive weights; the optimized regional average speed is obtained by weighting the original average speed of each road segment at the current time step with the adaptive weights; and the regional average density is obtained by the quotient of the regional average flow and the regional average speed. The corresponding calculation formulas are as follows:

[0046]

[0047]

[0048] in Kt ' is the optimized region average density at time step t. For adaptive weights, kit Let be the original average density of the i-th road segment at the t-th time step; Qt ' is the optimized regional average flow at time step t. qit Let be the original average traffic flow of the i-th segment at time step t. Vt ' is the optimized region average velocity at time step t. vit Let be the original average speed of the i-th road segment at the t-th time step.

[0049] Furthermore, this scheme constructs an adaptive macroscopic basic map based on the optimized regional average flow, regional average velocity, and regional average density. The formula for constructing the adaptive macroscopic basic map is as follows:

[0050] in The parameters to be fitted are... uf For the region's theoretical free flow velocity, Qop For regional theoretical accessibility, Kj For theoretical blockage density, Let K be the theoretical congestion wave dissipation velocity, and K be the regional average density.

[0051] In some embodiments, after obtaining the adaptive macroscopic basic map, this scheme can obtain the critical state of the large-scale road network, wherein the critical state includes the critical velocity V. c Critical density K c Critical flow rate Q c .

[0052] Regarding step S4 of this plan: This solution obtains the real-time average speed and average traffic flow of road segments, and analyzes the road network status of large-scale road networks based on the real-time average speed, average traffic flow, and critical states.

[0053] Specifically, this scheme obtains the real-time speed and real-time traffic flow of road segments at the current time step, and calculates the real-time regional average speed, real-time regional average traffic flow, and real-time regional average density of a large-scale road network based on adaptive weights. That is, the real-time regional average traffic flow is obtained by weighting the real-time average traffic flow of each road segment at the current time step with adaptive weights, the optimized real-time regional average speed is obtained by weighting the real-time average speed of each road segment at the current time step with adaptive weights, and the quotient of the real-time regional average traffic flow and the real-time regional average speed is used as the real-time regional average density.

[0054] The road network status of a large-scale road network is assessed based on the real-time regional average speed and density at multiple time steps and the critical state of the macroscopic basic map. The assessment rules are as follows: If the conditions for severe road network congestion are met, then the current road network status of the large-scale road network is severe road network congestion; If the conditions for minor road network congestion are met, then the current road network status of the large-scale road network is minor road network congestion. If the conditions for severe road network congestion and slight road network congestion are not met, then the current road network status of the large-scale road network is smooth.

[0055] The conditions for severe road network congestion are as follows: ; The conditions for minor road network congestion are: ; in V t ' is the real-time regional average velocity at time step t. K t ' is the real-time average density of the region at time step t. V t-1 ' is the real-time regional average velocity at time step t-1. K t-1 ' is the real-time average density of the region at time step t-1. V t-2 ' is the real-time regional average velocity at time step t-2. K t-2 ' is the real-time regional average density at time step t-2. Parameters set by humans. Vc The critical velocity, K c This is the critical density.

[0056] Example 2 This study selects the three horizontal and three vertical urban areas in the center of Kunming as the research object. Based on the traffic flow and speed data of road segments collected by Kunming City Brain from February 28 to March 10, 2022, an adaptive macro basic map is constructed. The road network traffic situation is analyzed using March 1, 2022 as an example. The specific methods and steps are as follows: 1. Calculation of the proportion of congested road sections in a region: Based on the collected traffic flow and speed data of road segments, road segment density is calculated to obtain flow density and velocity data for each road segment at each time step (5 minutes). Then, the 95th percentile of all time steps for each road segment is obtained as the free-flow velocity value for that road segment. Based on this, the proportion of congested road segments in the region at each time step is calculated using the free-flow velocity and road segment velocity for each road segment. t thre Set it to 0.4.

[0057] 2. Divide the day into several time periods based on regional traffic conditions: First, average the data for all times in the region over the days to obtain the average flow density and velocity data for each time step of the day. Then, set the number of time stage divisions. k s Here, the value is set to 7. The ordered sample clustering algorithm is used to divide the day into 7 time periods. The feature vectors of the ordered sample clustering algorithm are selected from the average density of the region and the proportion of congested road segments at each time step. After cluster analysis using the ordered sample clustering algorithm, the day is divided into 7 time periods: 00:00-07:15, 07:15-09:35, 09:35-13:55, 13:55-17:35, 17:35-19:00, 19:00-22:20, and 22:20-24:00. The time period division results are visualized as follows: Figure 2 As shown.

[0058] 3. Cluster the data for each time period based on regional traffic conditions: For each time period, clustering is performed based on regional traffic conditions. First, the average flow rate, density, and speed data of road segments at each time step within the same time period are averaged. Then, the average flow rate, average density, and average speed for that time period are used as feature vectors, and the number of clusters is set to [value missing]. k n Here we set it to 10, and perform cluster analysis based on the kmeans algorithm to divide all road segments in each time stage into 10 clusters.

[0059] 4. Optimize the calculation weights for average density and average flow in the solution area, and construct an adaptive macroscopic basic graph: Setting parameters α =4, β =0.45, and the differential evolution algorithm is used to optimize the algorithm, obtaining the weights for calculating the regional average density and average flow. Then, the regional average flow, average density, and average velocity are recalculated using the optimized weights. Finally, a macroscopic basic map is fitted to obtain an adaptive macroscopic basic map. The result of the adaptive macroscopic basic map construction is as follows. Figure 3As shown, the correlation coefficient between the proportion of congested road sections and the regional average density increased from 0.90 to 0.92, and the error rate of congestion judgment based on critical state decreased from 12.8% to 9.1%.

[0060] 5. Road network status assessment Based on the constructed adaptive macroscopic basic map, the critical state of the road network is obtained as follows: critical flow rate 0.077veh / s, critical speed 3.11m / s, and critical density 0.025veh / m.

[0061] Taking March 1, 2022 as an example, the road network status was analyzed, and the following settings were made: , , , The road network status assessment results are as follows: Severe congestion periods: 08:05-09:05; 14:00-15:25; 17:20-19:05; Slight congestion periods: 07:50-08:05; 09:05-09:40; 15:25-17:20; 19:05-19:15; The road network remains open during other times of the day.

[0062] Example 3 This embodiment also provides an electronic device, see reference. Figure 4 It includes a memory 404 and a processor 402, the memory 404 storing a computer program and the processor 402 being configured to run the computer program to perform the steps in any of the embodiments of the large-scale road network state assessment method based on the adaptive macroscopic basic map described above.

[0063] Specifically, the processor 402 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0064] The memory 404 may include a large-capacity memory 404 for data or instructions. The memory 404 can be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 402.

[0065] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any of the methods for generating or analyzing the adaptive macroscopic basic map of a large-scale road network in the above embodiments.

[0066] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408, wherein the transmission device 406 is connected to the processor 402, and the input / output device 408 is connected to the processor 402.

[0067] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 406 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0068] The input / output device 408 is used to input or output information. In this embodiment, the input information may be the original average flow rate and the original average speed of the road segment, and the output information may be a macroscopic basic map, etc.

[0069] Optionally, in this embodiment, the processor 402 can be configured to perform the following steps via a computer program: S1: Collect the original average traffic flow and original average speed of all road segments in the large-scale road network at multiple time steps within the statistical period. Calculate the original average density and regional average density of each road segment at each time step based on the original average traffic flow and original average speed, and calculate the proportion of regional congested road segments at each time step based on the original average speed. S2: Based on the proportion of congested road segments in the region and the average density in the region, cluster analysis is performed on the time step to divide the day into several time periods. The road segments in each time period are clustered to obtain road segment clusters. The weights of road segments in the same time period and the same road segment cluster are set to be equal. The weights of the road segments are optimized to obtain adaptive weights. S3: Calculate the optimized regional average flow, regional average velocity, and regional average density based on adaptive weights, construct an adaptive macroscopic basic graph based on the regional average flow, regional average velocity, and regional average density, and obtain the critical state based on the adaptive macroscopic graph. S4: Obtain the real-time average speed and average traffic flow of the road segment. Based on the real-time average speed, average traffic flow, and critical state, analyze the road network status of the large-scale road network. It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations. This embodiment will not repeat them here.

[0070] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented by firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0071] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products), including software routines, applets, and / or macros, can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer-executable components configured to perform embodiments when the program is run. One or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted that any block in the logical flow of the figures may represent a program step, or interconnected logical circuitry, blocks and functions, or a combination of program steps and logical circuitry, blocks and functions. The software may be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.

[0072] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0073] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for assessing the state of a large-scale road network based on an adaptive macroscopic basic map, characterized in that, include: S1: Collect the original average traffic flow and original average speed of all road segments in the large-scale road network at multiple time steps within the statistical period. Calculate the original average density and regional average density of each road segment at each time step based on the original average traffic flow and original average speed, and calculate the proportion of regional congested road segments at each time step based on the original average speed. S2: Based on the proportion of congested road segments in the region and the average density in the region, cluster analysis is performed on the time step to divide the day into several time periods. The road segments in each time period are clustered to obtain road segment clusters. The weights of road segments in the same time period and the same road segment cluster are set to be equal. The weights of the road segments are optimized to obtain adaptive weights. S3: Calculate the optimized regional average flow, regional average velocity, and regional average density based on adaptive weights, construct an adaptive macroscopic basic graph based on the regional average flow, regional average velocity, and regional average density, and obtain the critical state based on the adaptive macroscopic graph. S4: Obtain the real-time average speed and average traffic flow of road segments, and analyze the road network status of large-scale road networks based on the real-time average speed, average traffic flow, and critical state.

2. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, Critical states include critical velocity, critical density, and critical flow rate.

3. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, The system obtains the real-time speed and real-time traffic of the road segment at the current time step, and calculates the real-time regional average speed, real-time regional average traffic, and real-time regional average density based on adaptive weights.

4. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 3, characterized in that, The road network status of a large-scale road network is assessed based on real-time regional average speed and density at multiple time steps and critical states. The assessment rules are as follows: If the conditions for severe road network congestion are met, then the current road network status of the large-scale road network is severe road network congestion; If the conditions for minor road network congestion are met, then the current road network status of the large-scale road network is minor road network congestion. If the conditions for severe road network congestion and slight road network congestion are not met, then the current road network status of the large-scale road network is smooth.

5. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 4, characterized in that, The conditions for severe road network congestion are as follows: ； The conditions for minor road network congestion are: ； in V t ' is the real-time regional average velocity at time step t. K t ' is the real-time regional average density at time step t. V t-1 ' is the real-time regional average velocity at time step t-1. K t-1 ' is the real-time average density of the region at time step t-1. V t-2 ' is the real-time regional average velocity at time step t-2. K t-2 ' is the real-time regional average density at time step t-2. Parameters set by humans. Vc The critical velocity, K c This is the critical density.

6. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, The free-flow speed of the road segment is calculated based on the original average speed of the road segment. The congestion of each road segment at each time step is calculated based on the free-flow speed of the road segment and the original average speed of the road segment. The proportion of regional congested road segments at each time step is calculated based on the congestion of each road segment at each time step and the congestion of all road segments.

7. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, The average proportion of regional congested road segments at the same time step each day within the statistical period is taken as the daily average proportion of regional congested road segments at the current time step. The average regional average density at the same time step each day within the statistical period is taken as the daily average regional average density at the current time step. The daily average proportion of regional congested road segments and the daily average regional average density at each time step are used as feature vectors to perform ordered sample clustering analysis to divide a day into several time periods.

8. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, The road segments are clustered into road segment clusters by using the mean values ​​of the original average traffic flow, original average speed, and original average density of each road segment at each time step within the current time period as feature vectors.

9. The method for large-scale road network state assessment based on adaptive macroscopic basic map according to claim 1, characterized in that, The weights of road segments in a road segment cluster are optimized by setting objectives and constraints, and adaptive weights are obtained by solving the problem. The constraints include weight normalization constraints, weight non-negativity constraints, and macro-basic graph constraints. Among them, the weight normalization constraint restricts the sum of the weights of all road segments at each time step to be 1, the weight non-negativity constraint restricts the weight of each optimized road segment to be a non-negative number, and the macro-basic graph constraint restricts the construction of a macro-basic graph according to the adaptive weights, and the critical state is obtained based on this macro-basic graph.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to execute the large-scale road network state assessment method based on an adaptive macroscopic basic map as described in any one of claims 1 to 9.

Images