Road frequent congestion mode identification method based on checkpoint data and storage medium

Abstract

The invention discloses a road frequent congestion mode recognition method based on checkpoint data and a storage medium, and the method comprises the steps: firstly, extracting the basic travel information of a vehicle based on basic data collected by a checkpoint, and constructing a complete travel path of the vehicle; then obtaining the road operation state of the urban road network under the preset time granularity, and extracting a road section congestion instance set; then generating an urban road network model, and traversing a road network to obtain a road section level topology adjacency information table; a space adjacent road section information table of each road section under distance constraint is obtained, and a space-time adjacent congested road section information table is finally obtained through the congested time period overlapping relation between the space adjacent road sections; and finally, time-space adjacent congested road sections in the target date range are determined, and a congested mode set in different time periods is generated. The urban road network operation state dynamic accurate evaluation method realizes urban road network operation state dynamic accurate evaluation, can accurately identify the urban road network frequent congestion mode, and can be widely applied to the technical field of intelligent traffic.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and in particular to a method for identifying frequent congestion patterns on roads based on bayonet data and a storage medium. Background Art

[0002] Frequent congestion on urban roads has become a difficult problem in current urban road traffic management. Frequent traffic congestion usually has characteristics such as relatively fixed congestion section distribution, congestion evolution, congestion dissipation, etc., and often occurs on urban main roads and surrounding roads, causing a greater impact on residents' daily lives and has become one of the main problems in current urban traffic operation. Due to the complexity of the urban road network and the transmissibility characteristics of traffic congestion, when congestion occurs on different sections, the impacts on the overall road network and other surrounding roads are different. Therefore, accurately identifying the spatio-temporal evolution characteristics of the congested sections involved in road congestion events is the key to traffic congestion governance.

[0003] With the rapid development of image recognition technology and the gradual improvement of the high-definition bayonet system for urban roads, the layout scale of road bayonet devices and the corresponding data quality have been greatly improved. Compared with traditional traffic surveys and GPS data, bayonet data has advantages such as comprehensive vehicle types, complete information content, high sampling rate, etc., and both the data scale and quality are guaranteed. Therefore, using bayonet data as the basic data can more accurately reflect the operation status of urban road traffic.

[0004] The existing basic data for urban-level road operation status assessment usually includes data sources such as geomagnetic data and floating vehicle GPS data. The data quality is average, and the sampling rate is relatively low, resulting in low accuracy in assessing the operation status of roads at the arterial level and below, and the application scenarios are limited to large cities. At the same time, the current research on frequent road congestion patterns mainly focuses on the analysis of congestion spatial distribution, lacking the description of the spatio-temporal evolution process of road congestion propagation in a complete congestion event, and it is difficult to effectively guide the work of road traffic congestion governance. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method for identifying frequent congestion patterns on roads based on bayonet data and a storage medium, so as to realize dynamic and accurate assessment of the operation status of the urban-level road network, and further accurately identify the frequent congestion patterns of the urban-level road network.

[0006] One aspect of the embodiments of the present invention provides a method for identifying frequent congestion patterns on roads based on bayonet data, including:

[0007] Extracting basic vehicle travel information based on the basic data collected by the bayonet and constructing a complete travel path of the vehicle;

[0008] Obtain the road operation status of the urban road network at a preset time granularity according to the complete travel paths of each vehicle, and extract the set of road congestion instances;

[0009] Abstract the road sections in the physical world as nodes, and the connectivity between road sections as edges, and then generate an urban road network model, and traverse the road network to obtain the topological adjacency information table at the road section level;

[0010] According to the set of road congestion instances and the topological adjacency information table at the road section level, obtain the spatial adjacent road section information table of each road section under the distance constraint, and then through the congestion time period overlap relationship between spatially adjacent road sections, finally obtain the spatio-temporal adjacent congested road section information table;

[0011] According to the spatio-temporal adjacent congested road section information table, determine the spatio-temporal adjacent congested road sections within the target date range, and then generate a set of congestion patterns at different time periods.

[0012] Optionally, the extracting the basic travel information of vehicles based on the basic data collected by the checkpoint and constructing the complete travel path of the vehicle includes:

[0013] Sort according to the license plate number and the passing checkpoint time attribute in the checkpoint basic data, obtain the passing vehicle time difference data of all vehicles on the road network passing through adjacent checkpoints, and after sorting the passing vehicle time difference data of adjacent checkpoints from small to large, take the preset percentile of the ranking as the checkpoint travel time threshold;

[0014] According to the checkpoint basic data, judge whether the passing vehicle time difference between adjacent checkpoints is greater than the checkpoint travel time threshold. If so, determine that the two adjacent checkpoints belong to different trips. If not, determine that the adjacent checkpoint belongs to the same trip, and then determine the starting checkpoint, passing checkpoints, ending checkpoint and corresponding passing time information of a single trip record;

[0015] Construct an urban road network adjacency information table based on the urban road network topology information, reconstruct the complete passing path between adjacent checkpoints in a single vehicle trip on the urban road network, and then obtain the complete travel path of the vehicle. The complete travel path includes the starting and ending points of a single trip, the passing road sections, the time of entering and leaving the passing road sections, and the road section travel speed information.

[0016] Optionally, the obtaining the road operation status of the urban road network at a preset time granularity according to the complete travel paths of each vehicle and extracting the set of road congestion instances includes:

[0017] According to the complete travel paths of each vehicle, count the median of the travel speeds of all vehicles passing through the road section at the preset time granularity, and use this median as the operating speed of the road section at this time granularity, and then determine the basis for judging the road section operation status;

[0018] If the operating speed of a road section is greater than or equal to the first threshold of the operating speed of the road section, determine that the operating state is the unobstructed level; if the operating speed of the road section is less than the first threshold of the operating speed of the road section and greater than or equal to the second threshold of the operating speed of the road section, determine that the operating state is the slow-moving level; if the operating speed of the road section is less than the second threshold of the operating speed of the road section, determine that the operating state is the congested level;

[0019] Based on the preset time granularity, obtain the congestion instance sets of all road sections during the morning peak, afternoon peak, evening peak, and off-peak periods within the target date range respectively.

[0020] Optionally, according to the road section congestion instance set and the road section level topological adjacency information table, obtain the spatial adjacency road section information table of each road section under the distance constraint, and then through the congestion time period overlap relationship between spatially adjacent road sections, finally obtain the spatio-temporal adjacent congested road section information table, including:

[0021] According to the urban road network model, establish the sorting of road sections in the minimum heap temporary marked road network section set, and obtain the spatial adjacency road section information table under the path distance constraint;

[0022] According to the spatial adjacency road section information table, if there are congestion time periods between spatial adjacency road sections, obtain the congestion time period correlation between spatially adjacent road sections through the time period overlap rate calculation formula. If the congestion time period correlation result is greater than the time proximity correlation threshold, determine that there is a time proximity relationship between the spatially adjacent road sections;

[0023] Traverse each spatial adjacency road section in the spatial adjacency road section information table, and then obtain the spatio-temporal adjacent congested road section information table.

[0024] Optionally, the calculation formula for the congestion time period correlation is:

[0025]

[0026] Where S is the congestion time period correlation; Δt is the congestion propagation time threshold; t1 and t2 are two given consecutive congestion time periods; len[] represents the time period length.

[0027] Optionally, according to the spatio-temporal adjacent congested road section information table, determine the spatio-temporal adjacent congested road sections within the target date range, and then generate a congestion pattern set for different time periods, including:

[0028] According to the spatio-temporal adjacent congested road section information table, generate and extract the congestion pattern sets for the morning peak, afternoon peak, evening peak, and off-peak periods through the spatial vector connection method; where the congestion pattern set includes information such as the duration of each congestion pattern, the congestion road section propagation sequence, and the road section congestion duration.

[0029] Calculate the second-order congestion patterns with the number of congested road sections within the target date range being 2, and obtain the occurrence probabilities of the second-order congestion patterns during the morning peak, noon peak, evening peak, and off-peak periods respectively. If the occurrence probability of the second-order congestion pattern is greater than the probability threshold of the frequently-occurring congestion pattern, then this congestion pattern is considered a frequently-occurring congestion pattern;

[0030] Circularly and stepwise calculate the frequently-occurring higher-order congestion patterns in different periods to obtain the set of congestion patterns in different periods.

[0031] Optionally, the calculation formula for the occurrence probability of the congestion pattern is:

[0032]

[0033] Wherein, is the occurrence probability of congestion pattern A, and A i is the congestion instance included in congestion pattern A.

[0034] On the other hand, an embodiment of the present invention also provides a device for identifying frequently-occurring congestion patterns of roads based on bayonet data, including:

[0035] The first module is used to extract the basic travel information of vehicles based on the basic data collected by the bayonet and construct the complete travel path of the vehicles;

[0036] The second module is used to obtain the road operation status of the urban road network under the preset time granularity according to the complete travel path of each vehicle, and extract the set of road section congestion instances;

[0037] The third module is used to abstract the road sections in the physical world into nodes, and the connectivity between road sections into edges, and then generate an urban road network model, and traverse the road network to obtain the topological adjacency information table at the road section level;

[0038] The fourth module is used to obtain the spatial adjacent road section information table of each road section under the distance constraint according to the set of road section congestion instances and the topological adjacency information table at the road section level, and then finally obtain the spatio-temporal adjacent congested road section information table through the congestion time period overlap relationship between spatially adjacent road sections;

[0039] The fifth module is used to determine the spatio-temporal adjacent congested road sections within the target date range according to the spatio-temporal adjacent congested road section information table, and then generate a set of congestion patterns in different periods.

[0040] On the other hand, an embodiment of the present invention also provides an electronic device, including a processor and a memory;

[0041] The memory is used to store programs;

[0042] The processor executes the program to implement the method as described above.

[0043] On the other hand, an embodiment of the present invention further provides a computer-readable storage medium, which stores a program, and the program is executed by a processor to implement the method described above.

[0044] An embodiment of the present invention also discloses a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method described above.

[0045] An embodiment of the present invention first extracts basic vehicle travel information based on the basic data collected at the checkpoints to construct a complete travel path of the vehicle; then, according to the complete travel paths of each vehicle, obtains the road operation status of the urban road network under a preset time granularity, and extracts a set of road congestion instances; then abstracts the road segments in the physical world as nodes, and the connectivity between road segments as edges, and then generates an urban road network model, and traverses the road network to obtain a road segment-level topological adjacency information table; then, according to the set of road congestion instances and the road segment-level topological adjacency information table, obtains a spatial adjacency road segment information table for each road segment under a distance constraint, and then, through the congestion period overlap relationship between spatially adjacent road segments, finally obtains a spatio-temporal adjacent congestion road segment information table; finally, according to the spatio-temporal adjacent congestion road segment information table, determines the spatio-temporal adjacent congestion road segments within the target date range, and then generates a set of congestion patterns at different times. The present invention realizes the dynamic and accurate evaluation of the operation status of the urban-level road network, and can accurately identify the frequent congestion patterns of the urban-level road network. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0047] Figure 1 It is the overall step flowchart provided by the embodiment of the present invention;

[0048] Figure 2 It is a schematic diagram for extracting road segment congestion instances during the morning rush hour on a certain day under a 5-minute time granularity provided by the embodiment of the present invention;

[0049] Figure 3 It is a schematic diagram of the urban road network mode constructed based on the Space C complex network model provided by the embodiment of the present invention;

[0050] Figure 4Schematic diagram of the improved Dijkstra algorithm process provided by the embodiment of the present invention;

[0051] Figure 5 Schematic diagram of the hardware structure of an electronic device provided by the embodiment of the present invention. Detailed implementation manners

[0052] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0053] The method for identifying frequently-occurring congestion patterns on roads based on bayonet data provided by the embodiments of the present application relates to fields such as computers and intelligent transportation. The method for identifying frequently-occurring congestion patterns on roads based on bayonet data provided by the embodiments of the present application can be applied to a terminal, can also be applied to a server, or can also be software running on a terminal or a server. In some embodiments, the terminal can be a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, a vehicle-mounted terminal, etc., but is not limited thereto; the server side can be configured as an independent physical server, can also be configured as a server cluster or a distributed system composed of multiple physical servers, and can also be configured as a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network; the software can be an application for implementing the method for identifying frequently-occurring congestion patterns on roads based on bayonet data, etc., but is not limited to the above forms.

[0054] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, small computers, large computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0055] Specifically, refer to Figure 1, the method for identifying the frequently-occurring traffic congestion patterns on roads based on bayonet data of the present invention includes but is not limited to the following steps:

[0056] Step S1: Extract the basic vehicle travel information based on the basic data collected by bayonets, including information such as the starting bayonet, passing bayonets, ending bayonet of each trip and the corresponding passing time, etc., and reconstruct the complete vehicle travel path extracted above through the shortest path algorithm. Specifically, it includes three steps: calculating the bayonet travel time threshold, extracting vehicle travel records, and reconstructing the complete vehicle travel path.

[0057] Step S1-1: Sort according to the license plate number and passing bayonet time attribute in the bayonet basic data to obtain the passing time difference data of all vehicles on the road network passing through adjacent bayonets. After further sorting the passing time difference data of adjacent bayonets from small to large, take the preset percentile of the ranking as the bayonet travel time threshold, and the preset percentile can be set as needed, preferably set as the 85th percentile.

[0058] Step S1-2: According to the bayonet basic data, judge whether the passing time difference between the vehicle passing through adjacent bayonets is greater than the obtained bayonet travel time threshold. If so, it is considered that the two adjacent bayonets belong to different trips, and if not, it is considered that the adjacent bayonets belong to the same trip, and then determine the starting bayonet, passing bayonets, ending bayonet of a single trip record and the corresponding passing time and other information.

[0059] Step S1-3: Construct an adjacency information table of the urban road network based on the urban road network topology information, reconstruct the complete passing path of adjacent bayonets in the urban road network during a single vehicle trip, and then obtain the complete single vehicle trip path, including the starting and ending points of a single trip, passing sections, and the time and section travel speed of entering and leaving the passing sections. Specifically, the complete passing path can be reconstructed through the shortest path algorithm, such as Dijkstra, bidirectional Dijkstra, Floyed and other algorithms.

[0060] Step S2: Obtain the road operation status of the urban road network under a given time granularity based on the travel path data, and extract the set of road congestion instances. Specifically, it includes calculating the road operation status under a given time granularity and extracting the set of congestion instances of a single section during the morning peak, noon peak, evening peak, and off-peak periods.

[0061] Step S2-1: Based on the road network vehicle travel path data obtained above, calculate the median of the travel speeds of all vehicles passing through a road section at a given time granularity, and use it as the operating speed of the road section at this time granularity. Then, use this as the basis for determining the operating state of the road section. If the operating speed of the road section is greater than or equal to the first threshold of the road section operating speed, the operating state is the unobstructed level; if the operating speed of the road section is less than the first threshold of the road section operating speed and greater than or equal to the second threshold of the road section operating speed, the operating state is the slow-moving level; if the operating speed of the road section is less than the second threshold of the road section operating speed, the operating state is the congested level.

[0062] Step S2-2: Based on a given time granularity, respectively obtain the congestion instance sets C = [Y1, Y2, Y3…Y n of all road sections within the target date range during the morning peak, midday peak, evening peak, and off-peak periods. Among them, the congestion instances are sorted and numbered according to the date and start time. The time periods of the morning peak, midday peak, and evening peak can be set as needed. For example, the morning peak is from 7:30 to 9:30, the midday peak is from 11:00 to 13:00, the evening peak is from 17:00 to 19:00, and other time periods are off-peak periods. A congestion instance refers to a road section whose operating state is at the congested level within a continuous time period.

[0063] Step S3: Establish an urban road network model based on the classical SpaceC complex network model. Abstract the road sections in the physical world as nodes and the connectivity between road sections as edges, and then generate an urban road network model. Further, traverse the road network through the classical depth-first search algorithm to obtain the topological adjacency information table at the road section level. In addition to the classical SpaceC, the modeling methods of entity networks in complex networks also include SpaceL, SpaceP, SpaceB methods, etc., which can be selected as needed.

[0064] Step S4: Obtain the spatial adjacent road section information table of each road section under the distance constraint through the improved Dijkstra algorithm. Based on the spatial adjacent road section information table, finally obtain the spatio-temporal adjacent congested road section information table through the congestion time period overlap relationship between spatially adjacent road sections. Specifically, it includes obtaining the spatial adjacent road section information table through the improved Dijkstra algorithm and generating the spatio-temporal adjacent congested road section information table.

[0065] Step S4-1: Based on the urban road network model generated above, sort the road sections in the minimum heap temporary marked road network section set established by the traditional Dijkstra algorithm. Each time a road section is searched, there is no need to traverse the entire network, which improves the path search speed. Then, obtain the spatial adjacent road section information table under the path distance constraint.

[0066] Step S4-2: Based on the obtained spatial adjacent road segment information table above, if there are congestion periods between all spatial adjacent road segments, calculate the congestion period correlation between spatially adjacent road segments through the time period overlap rate calculation formula. If the congestion period correlation result is greater than the time proximity correlation threshold, it is considered that there is a temporally adjacent relationship between these spatially adjacent road segments. Traverse the spatial adjacent road segment information table by this method to obtain the spatio-temporal adjacent congested road segment information table. Among them, given two consecutive congestion periods t1 and t2, the calculation method of their congestion period correlation is as follows:

[0067]

[0068] Among them, Δt is the congestion propagation time threshold; t1 and t2 are two given consecutive congestion periods; len[] represents the period length; S is the congestion period correlation, and the value range is [0,1].

[0069] Step S5: According to the spatio-temporal adjacent congested road segments within the target date range, generate a set of congestion patterns for different time periods through the spatial vector connection algorithm, including information such as the duration of each congestion pattern, the congestion road segment propagation sequence, and the duration of road segment congestion. Finally, generate the frequently occurring congestion patterns through the probability tree method. Specifically, it includes the set of congestion patterns generated based on the spatial vector connection algorithm and the frequently occurring congestion patterns generated through the probability tree method.

[0070] Step S5-1: Based on the spatio-temporal adjacent congested road segment information table, generate and extract the congestion pattern sets for the morning peak, noon peak, evening peak, and off-peak periods through the spatial vector connection method, including information such as the duration of each congestion pattern, the congestion road segment propagation sequence, and the duration of road segment congestion.

[0071] Step S5-2: Optimize the probability tree method through a phased calculation method, which can significantly improve the calculation efficiency of the probability tree method when the number of events is large. First, calculate the second-order congestion patterns with 2 congested road segments within the target date range, and obtain the occurrence probabilities of the second-order congestion patterns during the morning peak, noon peak, evening peak, and off-peak periods respectively. If the occurrence probability of the second-order congestion pattern is greater than the frequently occurring congestion pattern probability threshold, it is considered that this congestion pattern is a frequently occurring congestion pattern. On this basis, loop and ascend to calculate the frequently occurring higher-order congestion patterns for different time periods. The method for calculating the occurrence probability of the congestion pattern based on the probability method is as follows:

[0072]

[0073] Among them, is the occurrence probability of congestion pattern A, and A i is the congestion instance included in congestion pattern A.

[0074] Taking a specific application scenario as an example below, the specific implementation process of the present invention will be described in detail:

[0075] In an embodiment of the present invention, the preset implementation conditions are as follows: 1. The detection quality of the bayonet and the data status are good, without too many license plate omissions or license plate recognition errors. 2. The layout density of the bayonet devices cannot be too low.

[0076] Step S1: Sort according to the license plate number and the passing time attribute of the bayonet in the basic bayonet data to obtain the passing time difference data of all vehicles on the road network passing through adjacent bayonets. After further sorting the passing time difference data of adjacent bayonets from small to large, take the 85th percentile of the ranking as the bayonet travel time threshold. According to the basic bayonet data, judge whether the passing time difference between the vehicles passing through adjacent bayonets is greater than the obtained bayonet travel time threshold. If so, it is considered that the two adjacent bayonets belong to different trips; if not, it is considered that the adjacent bayonets belong to the same trip, and then determine the starting bayonet, passing bayonets, ending bayonet and corresponding passing times and other information of a single trip record. Based on the urban road network topology information, construct an urban road network adjacency information table, and reconstruct the complete passing path of adjacent bayonets in the urban road network during a single vehicle trip through the Dijkstra shortest path algorithm, and then obtain the complete single vehicle trip path, including the starting and ending points of a single trip, the passing sections, and the time and section travel speed of entering and leaving the passing sections. The relevant information of the single vehicle trip record information can be shown in Tables 1 and 2:

[0077] Table 1

[0078]

[0079] Table 2

[0080]

[0081] Step S2: Based on the obtained road network vehicle travel path data above, statistically calculate the median of the travel speeds of all vehicles passing through the section at a given time granularity as the running speed of the section at this time granularity, and use this as the basis for judging the section running state. If the section running speed is greater than or equal to the first threshold of the section running speed, the running state is the smooth level; if the section running speed is less than the first threshold of the section running speed and greater than or equal to the second threshold of the section running speed, the running state is the slow level; if the section running speed is less than the second threshold of the section running speed, the running state is the congestion level. Based on a given time granularity, respectively obtain the congestion instance sets C = [Y1, Y2, Y3... Y n during the morning rush hour, noon rush hour, evening rush hour, and off-peak period of all sections within the target date range, where the congestion instances are sorted and numbered according to the date and start time.

[0082] Reference Figure 2The extracted information of the road congestion instance during the morning rush hour of a certain day at a 5-minute time granularity and the comparison table of the relationship between the road section operation status and the operating speed in the embodiment of the present invention can be shown in Table 3:

[0083] Table 3

[0084]

[0085] Step S3: Reference Figure 3 Based on the classic Space C complex network model, an urban road network model is established. Road sections in the physical world are abstracted as nodes, and the connectivity between road sections is abstracted as edges, thereby generating an urban road network model. The road network is further traversed through the classic depth-first search algorithm to obtain a road section-level topological adjacency information table.

[0086] Step S4: Reference Figure 4 Based on the urban road network model generated above, by establishing a minimum heap temporary marking network segment sorting method for the traditional Dijkstra algorithm, there is no need to traverse the entire network each time a segment is searched, thereby improving the path search speed and obtaining a spatial adjacent segment information table under the path distance constraint. Based on the spatial adjacent segment information table obtained above, if there are congested periods between spatially adjacent segments, the congested period correlation between spatially adjacent segments is obtained through the period overlap rate calculation formula. If the congested period correlation result is greater than the temporal proximity correlation threshold, it is considered that the spatially adjacent segments also have a temporal proximity relationship. By traversing the spatial adjacent segment information table through this method, a spatiotemporal adjacent congested segment information table is obtained. Given two consecutive congested periods t1 and t2, the congested period correlation calculation method is as follows:

[0087]

[0088] Among them, Δt is the congestion propagation time threshold; S is the congestion period correlation, and its value range is [0,1].

[0089] The contents of the road segment spatial adjacency information of the embodiment of the present invention are shown in Table 4:

[0090] Table 4

[0091]

[0092] Step 5: Based on the spatio-temporal proximity congested road section information table, generate and extract the congested pattern sets during the morning rush hour, noon rush hour, evening rush hour, and off-peak hours through the spatial vector connection method, including information such as the duration of each congested pattern, the propagation sequence of congested road sections, and the duration of road section congestion. By optimizing the probability tree method through a phased calculation method, the calculation efficiency of the probability tree method can be significantly improved when the number of events is large. First, calculate the second-order congested patterns with 2 congested road sections within the target date range, and obtain the occurrence probabilities of the second-order congested patterns during the morning rush hour, noon rush hour, evening rush hour, and off-peak hours respectively. If the occurrence probability of the second-order congested pattern is greater than the probability threshold of the frequently occurring congested pattern, then this congested pattern is considered a frequently occurring congested pattern. On this basis, loop and step up to calculate the frequently occurring higher-order congested patterns in different time periods. The method for calculating the occurrence probability of the congested pattern based on the probability method is as follows:

[0093]

[0094] Among them, is the occurrence probability of congested pattern A, and A i is the congested instance included in congested pattern A.

[0095] The content of the congested pattern information during the morning rush hour in the embodiment of the present invention is shown in Table 5:

[0096] Table 5

[0097]

[0098]

[0099] In summary, the method for identifying frequently occurring congested road patterns based on bayonet data in the embodiment of the present invention has the following characteristics:

[0100] 1. Extract the basic travel information of vehicles based on the basic data collected by bayonets, and reconstruct the complete travel path of vehicles through the shortest path algorithm.

[0101] 2. Obtain the road operation status of the urban road network based on the complete travel path data, and extract the set of road section congestion instances.

[0102] 3. Build an urban road network model based on the Space C complex network model to obtain the spatial adjacency relationship between road sections.

[0103] 4. Obtain the spatial adjacency congested road section information table of each road section under the distance constraint through the improved Dijkstra algorithm, and further calculate the congestion period correlation between the spatial adjacency congested road sections to obtain the spatio-temporal proximity congested road section information table.

[0104] 5. Generate a set of congested patterns through the spatial vector connection algorithm, and finally extract the frequently occurring congested patterns based on the phased probability tree method.

[0105] Compared with the prior art, the present invention has the following advantages:

[0106] 1. The current research on the frequently occurring road congestion mode mainly focuses on the analysis of the congestion spatial distribution, lacking the description of the spatio-temporal evolution process of the road congestion propagation in the complete congestion event. Based on the idea of trajectory mining for constructing the spatio-temporal correlation of congested sections, the present invention proposes a method for efficiently identifying the frequently occurring congestion mode of the urban-level road network, which can completely restore the spatio-temporal evolution process of the frequently occurring congestion event on the road network.

[0107] 2. The prior art usually uses data sources such as geomagnetic data and floating car GPS data, with general data quality and low accuracy in evaluating the operation status of roads at the arterial road level and below. The application scenarios are limited to large cities. The present invention has a wide range of applications and can be applied to cities from megacities to small and medium-sized cities.

[0108] The embodiment of the present application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned method for identifying the frequently occurring road congestion mode based on bayonet data. The electronic device can be any intelligent terminal including a tablet computer, an in-vehicle computer, etc.

[0109] It can be understood that the content in the above method embodiment is applicable to the device embodiment of the present application. The functions specifically implemented by the device embodiment of the present application are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method embodiment.

[0110] Please refer to Figure 5 , Figure 5 which schematically shows the hardware structure of the electronic device in another embodiment. The electronic device includes:

[0111] A processor 901, which can be implemented in a general-purpose CPU (Central Processing Unit, central processor), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided by the embodiment of the present application;

[0112] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902 and are called by the processor 901 to execute the method for identifying the frequently-occurring congestion patterns on roads based on bayonet data in the embodiments of this application;

[0113] The input / output interface 903 is used to implement information input and output;

[0114] The communication interface 904 is used to implement the communication interaction between this device and other devices. It can communicate through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.);

[0115] The bus 905 transmits information between various components of the device (such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904);

[0116] Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 achieve the communication connection among themselves inside the device through the bus 905.

[0117] The embodiments of this application also provide a computer-readable storage medium. This computer-readable storage medium stores a computer program, and when this computer program is executed by a processor, it implements the above method.

[0118] It can be understood that the content in the above method embodiments is applicable to the embodiments of this storage medium. The functions specifically implemented by the embodiments of this storage medium are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those of the above method embodiments.

[0119] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include but are not limited to the Internet, enterprise intranets, local area networks, mobile communication networks, and their combinations.

[0120] It should be noted that in each specific embodiment of the present application, when it comes to performing relevant processing based on data related to the user's identity or characteristics, such as user information, user behavior data, user historical data, and user location information, the user's permission or consent will be obtained first. Moreover, the collection, use, and processing of these data will comply with relevant laws, regulations, and standards. In addition, when the embodiments of the present application need to obtain the user's sensitive personal information, the user's separate permission or separate consent will be obtained through methods such as pop-up windows or redirecting to a confirmation page. After clearly obtaining the user's separate permission or separate consent, the necessary user-related data for the normal operation of the embodiments of the present application will be obtained.

[0121] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order mentioned in the operation diagrams. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated where the order of various operations is changed and where sub-operations described as part of a larger operation are executed independently.

[0122] Furthermore, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features described may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It can also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. Rather, considering the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the ordinary skills of an engineer. Therefore, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It can also be understood that the specific concepts disclosed are illustrative only and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0123] When the above-mentioned functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0124] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0125] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or processing it in other suitable ways if necessary, and then storing it in a computer memory.

[0126] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0127] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0128] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0129] The above is a specific description of the preferred embodiments of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for identifying common road congestion patterns based on checkpoint data, characterized in that: Including: Extract the basic travel information of vehicles based on the basic data collected by the checkpoints, and construct the complete travel paths of vehicles; According to the complete travel paths of each vehicle, obtain the road operation status of the urban road network at the preset time granularity, and extract the set of section congestion instances; Abstract the sections in the physical world as nodes, and the connectivity between sections as edges, and then generate an urban road network model, and traverse the road network to obtain the topological adjacency information table at the section level; According to the set of section congestion instances and the topological adjacency information table at the section level, obtain the spatial adjacent section information table of each section under the distance constraint, and then through the congestion period overlap relationship between spatially adjacent sections, finally obtain the spatio-temporal adjacent congestion section information table; According to the spatio-temporal adjacent congestion section information table, determine the spatio-temporal adjacent congestion sections within the target date range, and then generate a set of congestion patterns at different times.

2. The method for identifying frequent traffic congestion patterns on roads based on bayonet data according to claim 1, wherein The extracting the basic travel information of vehicles based on the basic data collected by the checkpoints and constructing the complete travel paths of vehicles includes: Sort according to the license plate number and the passing checkpoint time attribute in the checkpoint basic data, obtain the passing time difference data of all vehicles on the road network passing through adjacent checkpoints, after sorting the passing time difference data of adjacent checkpoints from small to large, take the preset percentile of the ranking as the checkpoint travel time threshold; According to the checkpoint basic data, judge whether the passing time difference between the vehicle passing through adjacent checkpoints is greater than the checkpoint travel time threshold. If so, determine that the two adjacent checkpoints belong to different trips. If not, determine that the adjacent checkpoint belongs to the same trip, and then determine the starting checkpoint, passing checkpoints, ending checkpoint and corresponding passing time information of a single trip record; Construct an urban road network adjacency information table based on the urban road network topological information, reconstruct the complete passing path of adjacent checkpoints in the vehicle's single trip on the urban road network, and then obtain the complete travel path of the vehicle. The complete travel path includes the starting and ending points of a single trip, passing sections, the time of entering and leaving the passing sections, and the section travel speed information.

3. The method for identifying common road congestion patterns based on checkpoint data according to claim 1, characterized in that: The obtaining the road operation status of the urban road network at the preset time granularity according to the complete travel paths of each vehicle and extracting the set of section congestion instances includes: According to the complete travel paths of each vehicle, calculate the median of the travel speeds of all vehicles passing through the section at the preset time granularity, and use this median as the operating speed of the section at this time granularity, and then determine the basis for judging the section operation status; If the section operating speed is greater than or equal to the first threshold of the section operating speed, determine that the operating status is the smooth level; if the section operating speed is less than the first threshold of the section operating speed and greater than or equal to the second threshold of the section operating speed, determine that the operating status is the slow-moving level; if the section operating speed is less than the second threshold of the section operating speed, determine that the operating status is the congestion level; Based on the preset time granularity, obtain the set of congestion instances of all sections during the morning rush hour, noon rush hour, evening rush hour, and off-peak period within the target date range respectively.

4. The method for identifying common road congestion patterns based on checkpoint data according to claim 1, characterized in that: Based on the set of road congestion instances and the road section - level topological adjacency information table, obtain the spatial adjacent road section information table for each road section under distance constraints, and then, through the congestion period overlap relationship between spatially adjacent road sections, finally obtain the spatio - temporal adjacent congested road section information table, including: Based on the urban road network model, establish the sorting of road sections in the minimum heap temporary marked road network section set, and obtain the spatial adjacent road section information table under path distance constraints; According to the spatial adjacent road section information table, if there are congestion periods between spatial adjacent road sections, obtain the congestion period correlation between spatially adjacent road sections through the period overlap rate calculation formula. If the congestion period correlation result is greater than the time - adjacent correlation threshold, it is determined that there is a time - adjacent relationship between the spatially adjacent road sections; Traverse each spatial adjacent road section in the spatial adjacent road section information table, and then obtain the spatio - temporal adjacent congested road section information table.

5. The method for identifying common road congestion patterns based on checkpoint data according to claim 4, characterized in that: The calculation formula for the congestion period correlation is: Where S is the congestion period correlation; Δt is the congestion propagation time threshold; t1 and t2 are two given consecutive congestion periods; len[] represents the period length.

6. The method for identifying common road congestion patterns based on checkpoint data according to claim 1, characterized in that: Based on the spatio - temporal adjacent congested road section information table, determine the spatio - temporal adjacent congested road sections within the target date range, and then generate a set of congestion patterns for different periods, including: Based on the spatio - temporal adjacent congested road section information table, generate and extract sets of congestion patterns for morning rush hour, noon rush hour, evening rush hour, and off - peak hours through the spatial vector connection method; where the set of congestion patterns includes information such as the duration of each congestion pattern, the congestion road section propagation sequence, and the duration of road section congestion. Calculate the second - order congestion patterns with 2 congested road sections within the target date range, and respectively obtain the occurrence probabilities of the second - order congestion patterns during morning rush hour, noon rush hour, evening rush hour, and off - peak hours. If the occurrence probability of the second - order congestion pattern is greater than the frequent congestion pattern probability threshold, then this congestion pattern is considered a frequent congestion pattern; Cyclically and hierarchically calculate the frequent higher - order congestion patterns for different periods to obtain a set of congestion patterns for different periods.

7. A method for identifying frequently-occurring traffic congestion patterns on roads based on bayonet data according to claim 6, characterized in that, The calculation formula for the congestion pattern occurrence probability is: Among them, is the occurrence probability of congestion mode A, and A i is the congestion instance included in congestion mode A.

8. An apparatus for identifying frequently-occurring road congestion patterns based on bayonet data, characterized in that, Including: The first module is used to extract the basic vehicle travel information based on the basic data collected at the checkpoint and construct the complete travel path of the vehicle; The second module is used to obtain the road operation status of the urban road network under a preset time granularity according to the complete travel paths of each vehicle, and extract the set of road congestion instances; The third module is used to abstract road sections in the physical world as nodes and the connectivity between road sections as edges, and then generate an urban road network model, and traverse the road network to obtain the road section - level topological adjacency information table; The fourth module is used to obtain the spatial adjacent road section information table for each road section under distance constraints according to the set of road congestion instances and the road section - level topological adjacency information table, and then, through the congestion period overlap relationship between spatially adjacent road sections, finally obtain the spatio - temporal adjacent congested road section information table; The fifth module is used to determine the spatio - temporal adjacent congested road sections within the target date range according to the spatio - temporal adjacent congested road section information table, and then generate a set of congestion patterns for different periods.

9. An electronic device, characterized in that, including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images