Highway closed state monitoring method, device and equipment and storage medium

Abstract

The invention discloses a highway closed state monitoring method, device and equipment and a storage medium. Comprising the steps of determining a detection area based on a difference between real-time traffic and historical traffic at a monitoring node on a highway; counting the real-time flow of the nodes and the road sections in the detection area, and taking the nodes and the road sections with the real-time flow meeting the flow closing characteristics as alternative closed nodes and alternative closed road sections; performing multi-data source fusion verification and spatial correlation verification on the alternative closed nodes and the alternative closed road sections to obtain closed nodes and closed road sections; and carrying out full-life-cycle management on the closed nodes and the closed road sections until the closed state is released. According to the method, on-off of the high-speed infrastructure is rapidly and accurately monitored based on the traffic characteristics on the expressway, false alarms can be avoided by means of fusion verification and space-time correlation verification of the two data characteristics, and road closing information is completely tracked and monitored through life cycle management.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and more specifically, to a method, device, equipment and storage medium for monitoring the closed state of a highway. Background Art

[0003] At present, the method of using floating vehicle GPS data to detect road closures has certain errors in calculation results because GPS data is sampled data; detecting road closures based on toll data has a relatively rough calculation granularity because the distance between gantries (toll booths) is too far, and it is difficult to obtain high-precision road operation status; there may be problems in both data collection and data transmission, leading to the erroneous extraction of road closure information. Objectively, there are problems such as untimely, inaccurate, and incomplete information reporting, and it is necessary to establish technical capabilities such as rapid discovery, accurate evaluation, and full life cycle management of infrastructure opening and closing information. Summary of the invention

[0004] The embodiments of the present application provide a method, device, equipment and storage medium for monitoring the closed status of a highway, so as to at least solve the technical problem in the related art that it is difficult to quickly and accurately detect the closure of highway infrastructure.

[0005] According to one aspect of an embodiment of the present application, a method for monitoring a closed state of a highway is provided, comprising:

[0006] Determine the detection area based on the difference between real-time traffic and historical traffic at monitoring nodes on the highway;

[0007] Counting the real-time traffic of nodes and sections in the detection area, and taking nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections;

[0008] Performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections;

[0009] The closed nodes and closed sections are managed throughout their life cycle until the closure is lifted.

[0010] In one embodiment, determining a detection zone based on the difference between real-time traffic and historical traffic at a monitoring node on a highway includes:

[0011] Calculate the difference between the real-time flow value and the historical flow characteristic value at the monitoring node;

[0012] When the difference is greater than a preset threshold, the monitoring node is used as a node to be detected;

[0013] The nodes to be detected and the associated road sections that have a connection relationship are aggregated to obtain one or more detection areas.

[0014] In one embodiment, based on the difference between the real-time traffic and the historical traffic at the monitoring node on the highway, before determining the detection zone, the method further includes:

[0015] Statistics are collected on the total traffic volume passing through the gantry nodes and toll station nodes within a preset time period, as well as the OD traffic volume passing through the gantry nodes and toll station nodes to reach each downstream gantry node and toll station node;

[0016] Statistics are collected on the total traffic volume passing through the current road section within the preset time, as well as the OD traffic volume passing through the current road section to reach each downstream road section;

[0017] Divide the date into multiple characteristic days, divide the characteristic days into multiple time slices according to the preset time length, and obtain the node total flow, node OD flow, section total flow, and section OD flow corresponding to each time slice in each characteristic day;

[0018] Based on the mathematical expectations of the node overall flow, node OD flow, section overall flow, and section OD flow of multiple identical characteristic days and identical time slices, the historical flow characteristic values ​​corresponding to each time slice in each characteristic day are obtained.

[0019] In one embodiment, before counting the real-time traffic of nodes and road sections in the detection area, the method further includes:

[0020] The overall traffic volume of all toll booth nodes in all statistical periods of the previous day is taken as the first sample set;

[0021] If the overall flow of the current toll station node is greater than or equal to the median of the first sample set, the current toll station node is a high-value toll station node;

[0022] If the overall flow of the current toll station node is less than the median of the first sample set, the current toll station node is a low-value node;

[0023] The total flow of all gantry nodes in all statistical periods of the previous day is taken as the second sample set;

[0024] If the total flow of the current gantry node is greater than or equal to the median of the second sample set, the current gantry node is a high-value gantry node;

[0025] If the total flow of the current gantry node is less than the median of the second sample set, the current gantry node is a low-value node.

[0026] In one embodiment, the nodes and sections whose real-time traffic meets the traffic closure feature are used as candidate closed nodes and candidate closed sections, including:

[0027] When the real-time overall flow of the high-value node has a zero return feature or a sudden drop feature, it is determined that the high-value node meets the flow closure feature, and the closure type is completely closed;

[0028] When the real-time overall flow of the low-value node has a zeroing feature, it is determined that the low-value node meets the flow closure feature, and the closure type is completely closed;

[0029] It is determined in turn whether the OD flow from the current node to each downstream node has the zeroing feature, and the nodes with the flow zeroing feature are determined to meet the flow closure feature; the closure type is partial directional closure;

[0030] When the total flow through the current section to the downstream has a zero return feature, it is determined that the current section meets the flow closure feature, and the closure type is completely closed;

[0031] It is determined in turn whether the OD flow from the current section to each downstream section has a zeroing feature, and the sections with flow zeroing features are determined to meet the flow closure feature, and the closure type is partial direction closure.

[0032] In one embodiment, performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain the closed nodes and the closed sections includes:

[0033] Obtain a set of candidate closed nodes and candidate closed sections that are directly associated with the topology. If the candidate closed nodes and the candidate closed sections are both completely closed, or both are partially closed and have the same closed direction, both pass the data source fusion verification and are determined to be closed nodes and closed sections.

[0034] Obtain any gantry closed node, obtain the gantry nodes adjacent to the gantry closed node on the upstream and downstream of the highway, if the adjacent gantry node is a target candidate node that has not passed the data source fusion verification, then determine that the target candidate node has passed the spatial correlation test, and use the target candidate node as a closed node;

[0035] Obtain any toll station closed node, obtain the toll station nodes adjacent to the toll station closed node on the upstream and downstream of the highway. If the adjacent toll station node is a target candidate node that fails the data source fusion check, then determine that the target candidate node passes the spatial correlation check and use the target candidate node as a closed node.

[0036] In one embodiment, the closed nodes and closed sections are managed throughout their life cycle, including:

[0037] Monitoring the detection, updating, splitting, merging, and dissipation processes of the closed nodes and closed sections to obtain life cycle information of the closed nodes and closed sections;

[0038] Send the life cycle information of closed nodes and closed sections to the application platform.

[0039] According to another aspect of the embodiment of the present application, there is provided a highway closure status monitoring device, comprising:

[0040] A detection zone extraction module is used to determine the detection zone based on the difference between the real-time flow rate and the historical flow rate at the monitoring node on the highway;

[0041] A detection module, used to count the real-time traffic of nodes and sections in the detection area, and use the nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections;

[0042] A verification module, used for performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections;

[0043] The management module is used to perform full life cycle management on the closed nodes and closed sections until the closed state is released.

[0044] According to another aspect of an embodiment of the present application, there is also provided an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the above-mentioned highway closed status monitoring method through the above-mentioned computer program.

[0045] According to another aspect of the embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned highway closure status monitoring method when running.

[0046] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0047] The highway closure status monitoring method provided in the embodiment of the present application can quickly and accurately discover closed nodes and closed sections based on the characteristics of traffic changes. Specifically, by constructing the detection area, the perception calculation range is reduced, the calculation efficiency is improved, and the needs of real-time calculation and monitoring are met. The node flow data and section flow data feature fusion verification and spatiotemporal correlation verification methods can be used to avoid false alarms caused by data collection and transmission problems, and improve the accuracy of the results; and the road closure information is fully tracked and monitored through full life cycle management, which is conducive to data management and analysis, and the dynamic changes of closure information can be perceived in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0049] Figure 1 is a flow chart of an optional highway closure status monitoring method according to an embodiment of the present application;

[0050] Figure 2 is a flow chart of an optional highway closure status monitoring method according to an embodiment of the present application;

[0051] Figure 3 is a flow rate change schematic diagram according to an embodiment of the present application;

[0052] Figure 4 It is a schematic diagram of detecting a sudden drop in traffic flow using a Bollinger Band method according to an embodiment of the present application;

[0053] Figure 5 is a schematic diagram of a detected closed road section and closed node provided according to an embodiment of the present application;

[0054] Figure 6 is a schematic diagram of a highway closure status monitoring device according to an embodiment of the present application;

[0055] Figure 7 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0057] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0058] The following is combined with Figure 1 The highway closure status monitoring method of the embodiment of the present application is described in detail. It should be noted that the following application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the implementation of the present application is not limited in this respect. On the contrary, the implementation of the present application can be applied to any applicable scenario. Figure 1 As shown, the method mainly includes the following steps:

[0059] S101 determines a detection area based on the difference between the real-time flow rate and the historical flow rate at the monitoring node on the highway.

[0060] The method of the embodiment of the present application also includes constructing a historical traffic feature library to determine road sections that may be closed by monitoring the difference between real-time traffic and historical traffic.

[0061] In one embodiment, based on the difference between the real-time traffic and the historical traffic at the monitoring nodes on the highway, before extracting the nodes to be detected, it also includes building a historical traffic feature library.

[0062] Specifically, firstly, based on the highway toll data, the overall flow passing through the gantry nodes and toll station nodes within a preset time period, as well as the OD flow passing through the gantry nodes and toll station nodes to reach each downstream gantry node and toll station node are counted.

[0063] In one embodiment, given a statistical time length t sta , count the total number of vehicles passing through a given gantry or toll station within the preset time, and obtain the overall flow rate f of the gantry or toll station total Define the gantry and toll booth as monitoring nodes node, and give the current monitoring node as node cur , and its downstream node set is Separate statistics t sta In, by the current node node curThe number of vehicles traveling to each downstream node can be used to obtain the OD flow set from this node to each downstream node.

[0064] Furthermore, based on the GPS floating vehicle data matched to the road section, the overall flow rate passing through the current road section within a preset time period and the OD flow rate passing through the current road section to each downstream road section are counted.

[0065] Given a target segmentlink cur , statistics t sta Internal, pathlink cur And reach the total number of vehicles in its downstream link, get link cur The total traffic flow f linkcur . Statistical analysis of t sta Internal, pathlink cur And the number of vehicles arriving at each downstream section is obtained cur OD flow collection

[0066]

[0067] Furthermore, the date is divided into multiple characteristic days, and the characteristic days are divided into multiple time slices with a preset duration to obtain the node total flow, node OD flow, section total flow, and section OD flow corresponding to each time slice in each characteristic day.

[0068] With fixed statistical duration t sta Divide the daily time into multiple slices, and use the curve noise reduction method to reduce the noise of daily traffic, and get the traffic data of a certain day.

[0069]

[0070] From Monday to Sunday, all dates are divided into seven characteristic days and statutory holidays, recorded as Day 8 is a holiday feature day. The multi-day traffic can be recorded as where fday j i Represents the traffic volume at the jth time slice on the i-th feature day.

[0071] Based on the mathematical expectations of the node overall flow, node OD flow, section overall flow, and section OD flow of multiple identical characteristic days and identical time slices, the historical flow characteristic values ​​corresponding to each time slice in each characteristic day are obtained.

[0072] For m traffics with the same characteristic days and the same time slices Find its mathematical expectation.

[0073]

[0074] It can be understood that by taking the mathematical expectation of all time-sliced ​​traffic data, a historical traffic characteristic dataset can be obtained. By calculating the mathematical expectation of the overall node flow, node OD flow, section overall flow, and section OD flow within a period of time, a complete historical flow feature database can be obtained.

[0075] Furthermore, the present application adopts the method of pre-extracting the detection area and only extracting the closed information in the detection area. In this way, only part of the road network and toll nodes are calculated, which reduces the cost of GPS matching to the road network, reduces the detection range, and greatly improves the calculation efficiency.

[0076] In one embodiment, the difference between the real-time flow value and the historical flow characteristic value at the monitoring node is calculated; when the difference is greater than a preset threshold, the monitoring node is used as a node to be detected.

[0077] The toll gate and toll station are called toll nodes, and the real-time overall flow of node is f cur_total , and its corresponding characteristic historical flow is f his_total Given a flow deviation threshold ε diff , if f his_total -f cur_total >ε diff , then the node is the node to be detected. Perform the above calculation on all nodes to obtain all the nodes to be detected, recorded as

[0078] Furthermore, the nodes to be detected and the associated road sections that have a connection relationship are aggregated to obtain one or more detection areas.

[0079] It can be understood that there is connectivity between charging nodes, which is a typical directed connected graph. The nodes in form different directed connected subgraphs. Then in any directed connected subgraph, all nodes And all the links associated with the subgraph Constitute a detection area graph. According to this method, based on Extract all detection areas.

[0080] By extracting the detection area, real-time calculation is performed only within the detection area, which reduces time overhead and meets the requirements of real-time calculation monitoring.

[0081] S102 counts the real-time traffic of nodes and sections in the detection area, and uses nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections.

[0082] In one embodiment, the value of highway sections varies depending on the geographical location and time period of the road section. For nodes with high traffic, they have a greater impact on the road, and the traffic change characteristics after the road is closed are obvious, so the road closure information can be quickly perceived; on the contrary, for nodes with low traffic, the road closure has a smaller impact and the traffic change characteristics are not obvious, but such nodes account for a large proportion and are widely distributed, so sufficient accuracy needs to be guaranteed. Through the analysis of traffic, the toll nodes of the highway network are divided into high-value nodes and low-value nodes.

[0083] Specifically, the total traffic volume of all toll station nodes in all statistical periods of the previous day is taken as the first sample set; the median of the sample set is selected as the traffic value judgment threshold θ ts If the total flow of the current toll station node is greater than or equal to the median of the first sample set, the current toll station node is a high-value toll station node; if the total flow of the current toll station node is less than the median of the first sample set, the current toll station node is a low-value node.

[0084] The total flow of all gantry nodes in all statistical periods of the previous day is taken as the second sample set; the median of the sample set is selected as the flow value judgment threshold θ gantry If the total flow of the current gantry node is greater than or equal to the median of the second sample set, the current gantry node is a high-value gantry node; if the total flow of the current gantry node is less than the median of the second sample set, the current gantry node is a low-value node.

[0085] By dividing scenes into high-value and low-value scenes, differentiated scene perception is achieved, which improves the perception speed of high-value sections while ensuring the perception accuracy of low-value sections.

[0086] Furthermore, the real-time traffic of nodes and sections within the detection area is counted to determine whether the real-time traffic meets the traffic closure characteristics.

[0087] Among them, the flow closure characteristics include flow zeroing characteristics and flow sudden drop characteristics. Figure 3 As shown, Figure 3 The left side is a schematic diagram of the flow zeroing feature. Figure 3 The right side is a schematic diagram of the flow drop.

[0088] When analyzing whether the flow has the zeroing feature, statistics t sta The real-time GPS traffic of the road sections within the detection area and the real-time toll traffic of the nodes are used to calculate their closed characteristics. The real-time traffic is denoted as f cur , and the historical flow rate of the corresponding characteristic day and characteristic period is f his , when f is satisfied cur = 0 and f his >ε, the flow meets the flow zeroing feature, and ε is the historical flow threshold, which can be set according to actual conditions.

[0089] When analyzing the characteristics of sudden flow drop, the curve trend analysis method is used to analyze the flow in a certain period of time to determine whether it meets the characteristics of sudden flow drop. Common curve trend analysis methods include derivative, difference ratio, trend fitting, moving average method, etc.

[0090] The Bollinger Band algorithm uses the sliding average of the curve as the middle track, selects the upper and lower tracks based on statistical characteristics, and determines the trend of the curve by the distance between the current value and the upper and lower tracks. Figure 4 As shown, when the flow curve is lower than the lower track, it can be determined that the curve has a sudden drop trend. This application takes the Bollinger Band method as an example and extracts the sudden drop trend of flow as its sudden drop feature:

[0091] Given a Bollinger Band time window of n, it means selecting n consecutive time slice flows as the calculation object, where the last time slice is the current time slice. The moving average method is used to process the flow curve:

[0092]

[0093] Get the middle track of the Bollinger Bands. Calculate the mean flow rate f within the time window ave :

[0094]

[0095] Calculate the standard deviation σ of the flow rate within the time window:

[0096]

[0097] The upper track of the Bollinger Band is The lower track is The current flow rate drop characteristic is

[0098] Furthermore, when the real-time overall traffic of the high-value node has a zeroing feature or a sudden drop feature, the high-value node is determined to meet the traffic closure feature, and the closure type is completely closed; when the real-time overall traffic of the low-value node has a zeroing feature, the low-value node is determined to meet the traffic closure feature, and the closure type is completely closed.

[0099] Determine in turn whether the OD flow from the current node to each downstream node has the zeroing feature, and determine the nodes with the flow zeroing feature to meet the flow closure feature; the closure type is partial directional closure. The nodes whose real-time flow meets the flow closure feature are selected as candidate closure nodes.

[0100] Furthermore, when the total flow through the current section to the downstream has a zeroing feature, it is determined that the current section meets the flow closure feature, and the closure type is complete closure.

[0101] It is determined in turn whether the OD flow from the current section to each downstream section has a zeroing feature, and the sections with flow zeroing features are determined to meet the flow closure feature, and the closure type is partial direction closure.

[0102] The road sections whose real-time traffic meets the traffic closure characteristics are selected as candidate closed sections.

[0103] S103 performs multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections.

[0104] In one implementation, a multi-data source fusion verification is first performed.

[0105] Get a set of topologically directly associated candidate closed nodes and candidate closed sections. If the candidate closed nodes and the candidate closed sections are both completely closed, or both are partially closed and have the same closed direction, both pass the data source fusion verification and are determined to be closed nodes and closed sections.

[0106] The topological direct association relationship means that the node and the road section are in the closest proximity relationship on the same highway, and there are no other nodes between them.

[0107] Perform multi-data source fusion verification on all candidate closed nodes and candidate closed sections to obtain valid closed nodes

[0108] Furthermore, a spatial correlation check is performed. In general, the closure range of a road section is often large, and due to its conduction effect on upstream and downstream traffic flows, its impact range will be further expanded. In addition, the closure of road sections and toll stations often do not appear alone. Specifically, multiple toll stations are closed in a section of highway, or toll stations within a closed section are also closed at the same time. Therefore, spatial correlation analysis can be used as an important means of checking the effectiveness of closed objects.

[0109] Specifically, obtain any gantry closed node, obtain the gantry nodes adjacent to the gantry closed node on the upstream and downstream of the highway, if the adjacent gantry node is a target candidate closed node that has not passed the data source fusion check, then determine that the target candidate closed node has passed the spatial correlation test, and use the target candidate node as a closed node.

[0110] Get any toll station closed node, get the toll station nodes adjacent to the toll station closed node in the upstream and downstream of the highway. If the adjacent toll station node is the target candidate closed node that fails the data source fusion check, then determine that the target candidate closed node passes the spatial correlation test and use the target candidate node as the closed node.

[0111] This application utilizes two data feature fusion verification methods and spatiotemporal correlation verification methods to avoid false alarms caused by data collection and transmission problems and improve the accuracy of the results.

[0112] S104 performs full life cycle management of closed nodes and closed road sections until the closure status is lifted.

[0113] Road closures and toll booth closures often last for a long time and change with the development of the reasons for the closures. In order to fully monitor and manage road closures and toll booth closures, this application performs lifecycle management on both.

[0114] The life cycle management of closed road sections includes processes such as detection, update, splitting, merging, and dissipation.

[0115] Specifically, the detection of closed sections includes: defining the continuous sections associated with continuous valid closed gantries on the same highway as a closed section. Extracting continuous adjacent valid closed gantries on the same highway. Obtaining the first road fork, confluence or GPS alternative closed section outside the boundary gantries as the boundary of the closed section. Obtaining the nodes, continuous sections and detection time within the boundary range is the detected closed section.

[0116] Specifically, a continuous section associated with continuous valid closed gantries on the same highway is defined as a closed section, such as Figure 5 shown.

[0117] Given a valid closed portal node valid _ gantry , search upstream and downstream along the highway where it is located, and you can get a continuous set of valid closed gantry frames Search The topological adjacent toll stations of all gantries in the , and taking the valid closed toll stations among them, we can get the closed toll station set of the closed section. like Figure 5 As shown in Figure 1, the boundary gantry is searched outward until a road fork or an alternative closed section extracted based on GPS traffic is encountered, which is the boundary of the closed section. All ordered links between the two boundaries constitute the link set of the closed section. The above three sets and the closed section detection time t start A complete closed section

[0118]

[0119] According to the above method, all valid closed door frames can be searched to detect all closed sections.

[0120] Closed section update: Check the boundary nodes of the existing closed section. If the boundary node is no longer closed, delete the boundary node. Otherwise, search for the outer adjacent nodes along the same highway. If it is a valid closed node, include it in the closed section range. Recalculate the boundary position based on the updated closed node and update the section range.

[0121] Specifically, given a closed road section to be updated Check whether the boundary gantry is a valid closed gantry. If so, search for adjacent continuous valid closed gantry along the current highway to the outside and include it in the If not, continue to search inside for unclosed door frames and remove them from the According to the updated Recalculate and Complete the road close Updates.

[0122] Closed section splitting: If some nodes inside a closed section are no longer closed, resulting in the closed section no longer having topological continuity, these nodes will be deleted and the node set will be split into two connected subsets. The ranges of the two sub-closed sections will be recalculated based on the two connected subsets.

[0123] Specifically, given a closed section to be split like The China-Africa border portal is no longer closed, so the following splitting operations are performed on it:

[0124] delete k consecutive unblocked state portals in The portals in are no longer continuous and are split into upstream continuous portal sets and downstream continuous gantry assembly

[0125]

[0126] Based on and Calculate its closed boundary, closed toll booth set, and closed link set to obtain the two closed sections after splitting. and

[0127]

[0128] Closed section merging: If two closed sections are on the same highway and the boundary gantries are adjacent gantries, the two are merged: the nodes of the two are merged and the scope of the closed section is re-determined based on the node set.

[0129] Specifically, given the closed road segment to be merged

[0130] If the two are on the same highway and the boundary gantries are adjacent gantries, the two will be merged: road c close =road a close ∪road c close ,in:

[0131]

[0132] The closed road section after merging is

[0133]

[0134] Closed section dissipates: When the number of frame nodes inside a closed section is 0, the closed section dissipates.

[0135] Specifically, given a closed section If the closed section meets the current If all the gantries in the road have been released from the closed state, the closed road section will be dissipated. close delete.

[0136] To monitor the full life cycle information of toll station closure, the start time, closure type, and closure information are recorded in chronological order from the time the toll station is closed until the station is unclosed. The life cycle information of closed nodes and closed sections is sent to the application platform. For example, it is sent to the vehicle management platform, the traffic management platform, and the vehicle terminal. This ensures that high-speed closure information is shared quickly and in a timely manner.

[0137] The highway closure status monitoring method provided in the embodiment of the present application can quickly and accurately discover closed nodes and closed sections based on the characteristics of traffic changes. Specifically, by constructing the detection area, the perception calculation range is reduced, the calculation efficiency is improved, and the needs of real-time calculation and monitoring are met. The node flow data and section flow data feature fusion verification and spatiotemporal correlation verification methods can be used to avoid false alarms caused by data collection and transmission problems, and improve the accuracy of the results; and the road closure information is fully tracked and monitored through full life cycle management, which is conducive to data management and analysis, and the dynamic changes of closure information can be perceived in real time.

[0138] In order to facilitate understanding of the method of the embodiment of the present application, Figure 2 Further description.

[0139] Specifically, historical charging data and historical GPS data are obtained, historical traffic features are extracted based on the historical charging data and historical GPS data, and a historical traffic feature library is constructed based on the extracted historical traffic features.

[0140] Acquire real-time charging data and real-time GPS data, extract real-time traffic characteristics based on the real-time charging data and real-time GPS data, and update the historical traffic characteristics library based on the real-time traffic characteristics.

[0141] Furthermore, the detection area is obtained, the node value is analyzed, the nodes are divided into high-value nodes and low-value nodes, the flow closure features are extracted, and the nodes and sections whose real-time flow meets the flow closure features are selected as candidate closed nodes and candidate closed sections. Further feature fusion verification is performed, and multi-data source fusion verification and spatial association verification are performed on the candidate closed nodes and candidate closed sections to obtain closed nodes and closed sections. Life cycle management is performed on closed sections and closed toll booths. The closure information is stored in the closure information result database.

[0142] The characteristics of this method are: by extracting the inspection area, real-time calculation is only performed within the inspection area, which reduces time overhead and meets the requirements of real-time calculation monitoring; by fusing and verifying the features extracted by the two data sources, erroneous extraction caused by data anomalies is avoided; through spatial correlation analysis, the accuracy of the results is further improved; combined with the relatively precise spatial location characteristics of GPS data, the perception results are relatively accurate; through life cycle management, complete information monitoring of closed sections and toll stations is achieved, which is conducive to data management and analysis.

[0143] According to another aspect of the embodiment of the present application, a highway closure status monitoring device for implementing the above-mentioned highway closure status monitoring method is also provided. Figure 6 As shown, the device comprises:

[0144] The detection zone extraction module 601 is used to determine the detection zone based on the difference between the real-time flow rate and the historical flow rate at the monitoring node on the highway;

[0145] The detection module 602 is used to count the real-time traffic of nodes and sections in the detection area, and use the nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections;

[0146] Verification module 603, used for performing multi-data source fusion verification and spatial association verification on candidate closed nodes and candidate closed sections to obtain closed nodes and closed sections;

[0147] The management module 604 is used to manage the closed nodes and closed sections throughout their life cycle until the closed state is released.

[0148] It should be noted that the highway closed state monitoring device provided in the above embodiment only uses the division of the above functional modules as an example when executing the highway closed state monitoring method. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the highway closed state monitoring device provided in the above embodiment and the highway closed state monitoring method embodiment belong to the same concept, and the implementation process thereof is detailed in the method embodiment, which will not be repeated here.

[0149] According to another aspect of the embodiments of the present application, an electronic device corresponding to the highway closure status monitoring method provided in the aforementioned embodiments is also provided to execute the aforementioned highway closure status monitoring method.

[0150] Please refer to Figure 7 , which shows a schematic diagram of an electronic device provided by some embodiments of the present application. Figure 7 As shown, the electronic device includes: a processor 700, a memory 701, a bus 702 and a communication interface 703, and the processor 700, the communication interface 703 and the memory 701 are connected via the bus 702; the memory 701 stores a computer program that can be run on the processor 700, and when the processor 700 runs the computer program, it executes the highway closed status monitoring method provided in any of the aforementioned embodiments of the present application.

[0151] The memory 701 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 703 (which may be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. may be used.

[0152] The bus 702 may be an ISA bus, a PCI bus, or an EISA bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 701 is used to store programs, and the processor 700 executes the programs after receiving the execution instructions. The highway closure status monitoring method disclosed in any implementation of the aforementioned embodiment of the present application may be applied to the processor 700, or implemented by the processor 700.

[0153] The processor 700 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 700. The above processor 700 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor to be executed, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory 701, and the processor 700 reads the information in the memory 701 and completes the steps of the above method in combination with its hardware.

[0154] The electronic device provided in the embodiment of the present application and the highway closure status monitoring method provided in the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, operated or implemented therein.

[0155] According to another aspect of the embodiments of the present application, a computer-readable storage medium corresponding to the highway closure status monitoring method provided in the aforementioned embodiments is also provided, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it will execute the highway closure status monitoring method provided in any of the aforementioned embodiments.

[0156] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical or magnetic storage media, which are not listed here one by one.

[0157] The computer-readable storage medium provided in the above-mentioned embodiments of the present application and the highway closure status monitoring method provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are 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.

[0159] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the attached claims.

Claims

1. A method for monitoring the closed state of a highway, characterized in that: include: Determine the detection area based on the difference between real-time traffic and historical traffic at monitoring nodes on the highway; Counting the real-time traffic of nodes and sections in the detection area, and taking nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections; Performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections; The closed nodes and closed sections are managed throughout their life cycle until the closure is lifted.

2. The method according to claim 1, characterized in that: Based on the difference between real-time traffic and historical traffic at monitoring nodes on the highway, the detection area is determined, including: Calculate the difference between the real-time flow value and the historical flow characteristic value at the monitoring node; When the difference is greater than a preset threshold, the monitoring node is used as a node to be detected; The nodes to be detected and the associated road sections that have a connection relationship are aggregated to obtain one or more detection areas.

3. The method according to claim 1, characterized in that Based on the difference between real-time traffic and historical traffic at monitoring nodes on the highway, before determining the detection area, it also includes: Statistics are collected on the total traffic volume passing through the gantry nodes and toll station nodes within a preset time period, as well as the OD traffic volume passing through the gantry nodes and toll station nodes to reach each downstream gantry node and toll station node; Statistics are collected on the total traffic volume passing through the current road section within the preset time, as well as the OD traffic volume passing through the current road section to reach each downstream road section; Divide the date into multiple characteristic days, divide the characteristic days into multiple time slices according to the preset time length, and obtain the node total flow, node OD flow, section total flow, and section OD flow corresponding to each time slice in each characteristic day; Based on the mathematical expectations of the node overall flow, node OD flow, section overall flow, and section OD flow of multiple identical characteristic days and identical time slices, the historical flow characteristic values ​​corresponding to each time slice in each characteristic day are obtained.

4. The method according to claim 1, characterized in that Before counting the real-time traffic of nodes and sections in the detection area, the method further includes: The overall traffic volume of all toll booth nodes in all statistical periods of the previous day is taken as the first sample set; If the overall flow of the current toll station node is greater than or equal to the median of the first sample set, the current toll station node is a high-value toll station node; If the overall flow of the current toll station node is less than the median of the first sample set, the current toll station node is a low-value node; The total flow of all gantry nodes in all statistical periods of the previous day is taken as the second sample set; If the total flow of the current gantry node is greater than or equal to the median of the second sample set, the current gantry node is a high-value gantry node; If the total flow of the current gantry node is less than the median of the second sample set, the current gantry node is a low-value node.

5. The method according to claim 4, characterized in that The nodes and sections whose real-time traffic meets the traffic closure characteristics are used as candidate closed nodes and candidate closed sections, including: When the real-time overall flow of the high-value node has a zero return feature or a sudden drop feature, it is determined that the high-value node meets the flow closure feature, and the closure type is completely closed; When the real-time overall flow of the low-value node has a zeroing feature, it is determined that the low-value node meets the flow closure feature, and the closure type is completely closed; It is determined in turn whether the OD flow from the current node to each downstream node has the zeroing feature, and the nodes with the flow zeroing feature are determined to meet the flow closure feature; the closure type is partial directional closure; When the total flow through the current section to the downstream has a zero return feature, it is determined that the current section meets the flow closure feature, and the closure type is completely closed; It is determined in turn whether the OD flow from the current section to each downstream section has a zeroing feature, and the sections with flow zeroing features are determined to meet the flow closure feature, and the closure type is partial direction closure.

6. The method according to claim 1, characterized in that Performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections includes: Obtain a set of candidate closed nodes and candidate closed sections that are directly associated with the topology. If the candidate closed nodes and the candidate closed sections are both completely closed, or both are partially closed and have the same closed direction, both pass the data source fusion verification and are determined to be closed nodes and closed sections. Obtain any gantry closed node, obtain the gantry nodes adjacent to the gantry closed node on the upstream and downstream of the highway, if the adjacent gantry node is a target candidate node that has not passed the data source fusion verification, then determine that the target candidate node has passed the spatial correlation test, and use the target candidate node as a closed node; Obtain any toll station closed node, obtain the toll station nodes adjacent to the toll station closed node on the upstream and downstream of the highway. If the adjacent toll station node is a target candidate node that fails the data source fusion check, then determine that the target candidate node passes the spatial correlation check and use the target candidate node as a closed node.

7. The method according to claim 1, characterized in that The closed nodes and closed sections are managed throughout their life cycle, including: Monitoring the detection, updating, splitting, merging, and dissipation processes of the closed nodes and closed sections to obtain life cycle information of the closed nodes and closed sections; Send the life cycle information of closed nodes and closed sections to the application platform.

8. A highway closure status monitoring device, characterized in that: include: A detection zone extraction module is used to determine the detection zone based on the difference between the real-time flow rate and the historical flow rate at the monitoring node on the highway; A detection module, used to count the real-time traffic of nodes and sections in the detection area, and use the nodes and sections whose real-time traffic meets the traffic closure characteristics as candidate closed nodes and candidate closed sections; A verification module, used for performing multi-data source fusion verification and spatial association verification on the candidate closed nodes and the candidate closed sections to obtain closed nodes and closed sections; The management module is used to perform full life cycle management on the closed nodes and closed sections until the closed state is released.

9. An electronic device, characterized in that: The invention comprises a processor and a memory storing program instructions, wherein the processor is configured to execute the highway closed state monitoring method as claimed in any one of claims 1 to 7 when executing the program instructions.

10. A computer-readable medium, characterized in that Computer-readable instructions are stored thereon, and the computer-readable instructions are executed by a processor to implement a highway closure status monitoring method as described in any one of claims 1 to 7.

Images