Road maintenance monitoring method and system

Abstract

The invention relates to a road maintenance monitoring method and system. The method comprises the following steps: acquiring historical road data of road segments of a road to be monitored; assigning a value to the topological structure diagram based on each piece of historical road data; setting edge attribute values in the topological structure diagram based on previous assignment results; if the strong relation sets of the nodes are satisfied, determining that the road segment corresponding to the current node is a normal road segment; and otherwise, determining the road segment as a quasi abnormal road segment. According to the method, the attribute value change influence caused by the difference influence is eliminated based on the attribute value relationship between the corresponding nodes of the road segments, and the road segment condition change condition contained in the big data is found, so that road maintenance monitoring and early warning are performed.

Description

[Technical field]

[0001] The present invention belongs to the field of intelligent transportation technology, and in particular relates to a road maintenance monitoring method and system. [Background technology]

[0002] Road maintenance monitoring is the first step of road maintenance. The maintenance and upkeep of roads is to maintain roads and structures and facilities on them, maintain road performance as much as possible, restore damaged parts in time, ensure safe, comfortable and smooth driving, save transportation costs and time; take correct technical measures to improve engineering quality, extend the service life of roads, and postpone reconstruction time. The integration of equipment is getting higher and higher now, and new automated monitoring technologies such as LiDAR, visual 3D, neural networks and deep learning have been initially applied. Based on the monitoring and assessment of highway technical conditions, maintenance demand analysis, and maintenance plan determination, follow the concept of optimal comprehensive benefits throughout the life cycle, comprehensively consider technical, economic, safety, environmental protection and other factors, and reasonably determine maintenance engineering projects. Keep the road and its ancillary facilities in good condition, improve road capacity and service level. Extend the service life of roads and reduce maintenance costs. Improve road safety and reduce the incidence of traffic accidents. With the gradual improvement of scientific decision-making technology, the continuous deepening of the application of automated monitoring technology and information analysis technology, preventive maintenance technology has gradually become a system, high-performance modified asphalt has formed a series of products, the pavement structure and construction technology have been further optimized, and the pavement service life and service level have been extended and improved. The ability to make scientific decisions in highway maintenance projects has been significantly improved, and it is gradually shifting from traditional experience judgment to a data-driven scientific decision-making management model. The intelligent data access platform connects road intelligent inspection and diagnosis equipment and the smart maintenance management platform, and supports technologies such as big data mining and analysis, artificial intelligence, and feature recognition to provide intelligent auxiliary decision support for highway management and maintenance. Accelerate the research and development of highway technical condition monitoring and maintenance equipment, focusing on the research and development of automated rapid monitoring equipment and unmanned maintenance and construction equipment for highway bridges and tunnels, traffic safety facilities, etc.

[0003] The application of emerging technologies in highway maintenance is important for the sustainability, efficiency and quality of highway transportation infrastructure. Emerging technologies, such as automated robots, drones and sensors, can speed up maintenance work and reduce the need for manual operations, thereby reducing maintenance costs. This helps extend the life of roads and reduce the need for recurring maintenance. Automation and remote sensing technologies can be used to monitor the safety of roads. This helps identify potential safety risks early and reduce the occurrence of accidents. Emerging technologies help reduce the environmental impact of highway maintenance processes. Emerging technologies help highway managers collect large amounts of data that can be used for decision-making. Emerging technologies can improve the disaster resistance of highways, enabling them to better respond to natural disasters such as floods, earthquakes and hurricanes. Specifically, artificial intelligence and big data analysis have been widely used in intelligent road maintenance decisions, and intelligent identification of road surface flatness, skid resistance, rutting and cracks based on artificial intelligence algorithms has also made great progress; in the future, the integrated technology of intelligent identification of multiple diseases can be used to monitor the disease of the road surface throughout the entire process and in all time and space, and can also further conduct fully automatic and efficient analysis of road service performance, road maintenance strategy optimization and other fields, but a lot of research is still needed in the areas of intelligent decision-making training samples and deep learning algorithms.

[0004] However, the monitoring of road maintenance in the prior art is often still focused on how to perform image processing and image analysis, and how to perform autocorrelation analysis and prediction based on the time series characteristics of the road to be monitored. It fails to fully utilize the differences between road segment data to monitor the entire road. How to fully utilize the differentiated information of road segments and deeply mine and utilize existing maintenance and operation data resources is a technical problem to be solved. In order to solve the problems in the prior art, the present invention segments the roads to be monitored, and through a graph representation of the roads to be monitored, integrates the connection relationship and geographical distribution relationship of the monitored roads, while considering the impact of these two actual physical conditions on road monitoring; based on the attribute value relationship between the corresponding nodes of the road segments, the attribute value change impact caused by the difference is eliminated, and the changes in the road segment conditions contained in the big data are discovered, so as to perform road maintenance monitoring and early warning. [Summary of the invention]

[0005] In order to solve the above problems in the prior art, the present invention proposes a road maintenance monitoring method and system, the method comprising:

[0006] Step S1: For the road segments to be monitored, organize each road segment according to the connection relationship and / or geographical location distribution to obtain a topological structure diagram of the road to be monitored G = {S, C} = ({s n},{c n1_n2}); where: S is the node set, C is the edge set; the node s in the graph n Indicates road segment n, edge c n1_n2Indicates that there is a connection relationship or a geographical location distribution relationship between road segments n1 and n2;

[0007] Step S2: Obtain historical road data of road segments of the road to be monitored; determine the strong relationship set and node s of the topological structure diagram based on each historical road data n The strong relationship set includes the following steps:

[0008] Step S2A1: obtaining a piece of unprocessed historical road data;

[0009] Step S2A2: Obtain the node attribute value for each road segment; n =(s n，k );s n，k is the kth element in the node attribute value;

[0010] Step S2A3: Obtain the relationship value f(s) between every two road segments n1 ,s n2 )=(f k (s n1 ,s n2 )); where: f k (s n1 ,s n2 ) is the sub-relation for the k-th attribute;

[0011] Step S2A4: if there is still unprocessed historical road data, return to step S2A1; otherwise, proceed to the next step;

[0012] Step S2A5: Determine the strong relationship set of the topological structure graph; specifically: if the number of simultaneous occurrences of a sub-relationship value group containing one or more sub-relationship values ​​in each sub-relationship set corresponding to each historical road data exceeds the number threshold, then the sub-relationship value group containing one or more sub-relationship values ​​is placed in a strong relationship set; if there is a sub-relationship value involving node s in the strong relationship set n When , the strong relationship set is called node s n The strong relationship set of

[0013] Step S3: Obtain the current road data of each road segment to be monitored, assign current values ​​to the topological structure diagram, and obtain the node attributes s of the current road data n =(s n，k ) and the relation value f(s n1 ,s n2 ); determine quasi-abnormal road segments based on the strong relationship set and the node attributes and relationship values ​​of the current road data.

[0014] Furthermore, a collection device is provided to collect data from the road to be monitored.

[0015] Furthermore, the acquisition device is one or more of an image acquisition device, a sound acquisition device, a radar, and a remote sensing device.

[0016] Furthermore, the road data of the road segment is obtained after local sampling of the road segment.

[0017] Furthermore, the quasi-abnormal road segmentation is determined based on the strong relationship set and the node attributes and relationship values ​​of the current road data, specifically: for each edge in the topological structure diagram, a judgment is made; for nodes n1 and n2 in any edge, if there is a sub-relationship value between the two that belongs to a strong relationship set, and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set, then the connectivity count value acv is set n =acv n +c n1_n2 ; After completing the judgment of all edges, if Then the topological structure graph is determined to be connected; if the node s n If the strong relationship sets of are satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment.

[0018] Furthermore, step S2 also includes: step S2A6: calculating the edge attribute value c of any two adjacent road segments n1 and n2 n1_n2 ;

[0019] The method of determining the quasi-abnormal road segmentation based on the strong relationship set and the node attributes and relationship values ​​of the current road data is specifically as follows: for each edge in the topological structure diagram, a judgment is made; for nodes n1 and n2 in any edge, if there is a sub-relationship value between the two that belongs to a strong relationship set, and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set, then the connectivity count value acv is set n =acv n +c n1_n2 ; After completing the judgment of all edges, if Then the topological structure graph is determined to be connected; if the node s n If the strong relationship sets of are satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment.

[0020] Furthermore, the subrelationship f k (s n1 ,s n2 ) is one or more of a ratio relationship, a difference relationship, and a linear relationship.

[0021] A road maintenance monitoring server is used to implement the road maintenance monitoring method.

[0022] A road maintenance monitoring system is used to implement the road maintenance monitoring method.

[0023] A road maintenance monitoring platform, characterized in that the road maintenance monitoring platform is used to implement the road maintenance monitoring method.

[0024] The beneficial effects of the present invention include:

[0025] (1) Through the graph representation of the road to be monitored, the connection relationship and geographical distribution relationship of the monitored roads can be integrated, and the impact of these two actual physical conditions on road monitoring can be considered at the same time. Based on the attribute value relationship between nodes, the impact of attribute value changes caused by the difference is eliminated, and the changes in road segment conditions contained in big data are discovered, so as to carry out road maintenance monitoring and early warning.

[0026] (2) A strong relationship set is set to perform all-round auxiliary verification of road segments. Through graph search based on the current monitoring data, under the guidance of connection relationships and geographical distribution relationships, the global coverage and local coverage of the constraint relationships presented by the current monitoring data on the big data are verified, so that road detection can be performed sensitively and accurately, and it has good compatibility with traditional monitoring methods.

Brief Description of the Drawings

[0027] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application, but do not constitute an improper limitation of the present invention. In the drawings:

[0028] Figure 1 This is a schematic diagram of the road maintenance monitoring method provided by the present invention. [Specific implementation method]

[0029] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, wherein the illustrative embodiments and descriptions are only used to explain the present invention but are not intended to limit the present invention.

[0030] The present invention provides a road maintenance monitoring method and system, as shown in the attached Figure 1 As shown, the method comprises the following steps:

[0031] Step S1: For the road segments to be monitored, organize each road segment according to the connection relationship and / or geographical location distribution to obtain a topological structure diagram of the road to be monitored G = {S, C} = ({s n},{c n1_n2}); where: S is the node set, C is the edge set; the node s in the graph n Indicates road segment n, edge c n1_n2 Indicates that there is a connection relationship or a geographical location distribution relationship between road segments n1 and n2;

[0032] Preferably: when organizing by geographical location distribution, when the geographical location distribution, road setting mode and / or road maintenance conditions of two road segments are similar, a connection relationship is set between the two road segments; when a connection relationship exists between two road segments, it indicates that their geographical locations are similar, their maintenance conditions are similar, and the abnormal correlation is strong; the road segment is not only related to its connection relationship, but also to the geographical location. Through the graphical representation of the road to be monitored, both relationships can be integrated, and the impact of these two actual physical conditions on road monitoring can be considered at the same time;

[0033] Preferably, a collection device is provided to collect data from the road to be monitored; the collection device is an image collection device, a sound collection device, a radar, a remote sensing device, etc.;

[0034] Step S2: Obtain historical road data of road segments of the road to be monitored; assign values ​​to the topological structure graph based on each historical road data; and set edge attribute values ​​in the topological structure graph based on previous assignment results;

[0035] Preferably: the road data of road segments of different road segments are acquired based on the same or different image acquisition devices; acquired under the same or different acquisition environments; the acquisition environments and acquisition devices used in different road segments are different and may change in real time, and the influence of attribute value changes caused by the difference is eliminated based on the attribute value relationship between nodes, and the changes in the road segment conditions contained in the big data are discovered, so as to carry out road maintenance monitoring and early warning;

[0036] Preferably: the historical road data includes historical normal road data and historical abnormal road data; subsequent analysis is performed based on the historical normal road data; an abnormality occurs here, which means that the road needs maintenance or road data autocorrelation analysis;

[0037] Preferably: the road segment images of different road segments are obtained by segmenting or splicing the road image to be monitored;

[0038] Preferably: the road data of the road segment is obtained by local sampling of the road segment;

[0039] The topology structure diagram is assigned values ​​based on each historical road data; the edge attribute values ​​in the topology structure diagram are set based on the previous assignment results; specifically: based on each historical road data, the node attributes s are assigned to the nodes in the topology structure diagram n =(s n，k ), assign edge attribute c to the edge n1_n2 =(c n1_n2，k ); where: k = 1 to K, is the attribute number, K is the number of attributes;

[0040] The specific steps include:

[0041] Step S2A1: obtaining an unprocessed historical road data; the historical road data includes the road data of all road segments; after obtaining the historical road data, pre-processing the historical road data and extracting feature values;

[0042] Preferably: preprocessing the historical road image data in the historical road data, wherein the preprocessing includes graying, noise removal, equalization, normalization, etc.;

[0043] Step S2A2: Obtain the node attribute value for each road segment; n =(s n，k )=(s n，1 ,…,s n，K );s n，k It is the kth element in the node attribute value, that is, the kth attribute corresponds to the kth eigenvalue; each type of road data corresponds to a unary or multiary attribute;

[0044] Preferably: the historical road data also includes data such as sound monitoring, radar monitoring, remote sensing monitoring, etc.; extracting feature values ​​for these monitoring data, and creating corresponding node attribute elements;

[0045] Step S2A3: Obtain the relationship value f(s) between every two road segments n1 ,s n2 )=(f k (s n1 ,s n2 )); where: f k (s n1 ,s n2 ) is the sub-relationship for the k-th attribute; further: calculate the total relationship value fa(s) between each two road segments n1 ,s n2 )=∑ k a k ×f k (s n1 ,s n2 );Among them: a k is the comprehensive coefficient of the kth attribute;

[0046] Preferably: the sub-relationship f k (s n1 ,s n2 ) is one or more of a ratio relationship, a difference relationship, a linear relationship, etc.; when it is a ratio relationship, or When it is a difference relationship, f k (s n1 ,sn2 )=s max(n1，n2)，k -s min(n1，n2)，k ; When it is a linear relationship, f k (s n1 ,s n2 )=b1s max(n1,n2)，k +b2s min(n1,n2)，k , b1, b2 are correlation coefficients; a variety of relationship functions can be used to describe this, even based on time series relationships; the total relationship value is regarded as a sub-relationship, in this case f(s n1 ,s n2 )=(f k (s n1 ,s n2 ), fa(s n1 ,s n2 ));

[0047] Step S2A4: if there is still unprocessed historical road data, return to step S2A1; otherwise, proceed to the next step;

[0048] Step S2A5: Determine the strong relationship set of the topological structure graph; specifically: if the number of simultaneous occurrences (ratio) of a sub-relationship value group containing one or more sub-relationship values ​​in each sub-relationship set corresponding to each historical road data exceeds the number threshold (ratio threshold), then the sub-relationship value group containing one or more sub-relationship values ​​is placed in a strong relationship set; if there is a sub-relationship value involving node s in the strong relationship set n When , the strong relationship set is called node s n The strong relation set {f k (s n1 ,s n2 ), fa(s n1 ,s n2 )}; Here, a sub-relationship value group containing one or more sub-relationship values ​​corresponds to a strong relationship set; for example: a strong relationship set {f1(s n1 ,s n2 )=0.5,f2(s n2 ,s n3 )=1.9,f3(s n1 ,s n2 )=0.1}, the sub-relationship value of the first attribute between nodes n1 and n2 is 0.5, the sub-relationship value of the second attribute between nodes n2 and n2 is 1.9, and the sub-relationship value of the third attribute is 0.1, which expresses that two strong relationships that appear at the same time constitute a strong relationship set; the strong relationship set involves nodes n1, n2, and n3, so the strong relationship set is also the strong relationship set of nodes n1, n2, and n3; it can be seen that the strong relationship set of each node is 0 or more;

[0049] Step S2A6: Calculate the edge attribute value of any two adjacent road segments n1 and n2; specifically: in the sub-relationship value set corresponding to a historical road data, when there are one or more sub-relationship values ​​between the adjacent road segments n1 and n2 belonging to any strong relationship set (it can be more strictly limited that more than a certain proportion of sub-relationship values ​​between the adjacent road segments n1 and n2 belong to the strong relationship set), and the historical road data satisfies the strong relationship set, increment the edge attribute count value ct n1_n2 =ct n1_n2 +1; Repeat this step until all historical road data are processed; Set edge attribute value based on edge attribute count value; Set edge attribute value Among them: NH is the number of historical road data; nh = 1 ~ NH is the historical road data number; it can be seen that the edge attribute value is a unary value;

[0050] Preferred: edge attribute count value ct n1_n2 The initial value of is 0;

[0051] Preferably: the node attribute is a feature value obtained by performing image analysis on a road segment image of a road segment corresponding to the node; the feature value includes one or more of color feature, shape feature, texture feature, spatial feature, frequency domain feature, statistical feature, depth feature, etc.; further, when the historical road data also includes data such as sound monitoring, radar monitoring, remote sensing monitoring, etc., the node attribute also includes extracting feature values ​​for these monitoring data and creating corresponding node attribute element values;

[0052] Further: color features are one or more of the statistics such as pixel value of feature pixels, color histogram, color mean, variance, skewness and kurtosis; shape features are one or more of boundary descriptors, region descriptors, geometric moments, etc.; texture features are one or more of gray-level co-occurrence matrix (contrast, energy, entropy, uniformity, etc.), texture spectrum; spatial features are spatial relations or spatial pyramid features; frequency domain features are multi-scale and multi-directional features of road segmentation images; statistical features are statistics of pixel values ​​(mean, variance, skewness, kurtosis, etc.) or statistics of regions (mean, variance, etc. of regions); depth features (extracted by convolutional neural network deep learning model);

[0053] Step S3: Obtain the current road data of each road segment to be monitored, assign current values ​​to the topological structure diagram, and obtain the node attributes s of the current road data n =(s n，k ) and the relation value f(s n1 ,s n2 ); determining quasi-abnormal road segments based on the node attributes and relationship values ​​of the topological structure diagram and the current road data;

[0054] The method determines the quasi-abnormal road segmentation based on the node attributes and relationship values ​​of the topological structure diagram and the current road data; specifically: for each edge in the topological structure diagram, a judgment is made; for nodes n1 and n2 in any edge, if there is a sub-relationship value between the two that belongs to a strong relationship set, and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set, then the connectivity count value acv is set n =acv n +c n1_n2 ; After completing the judgment of all edges, if Then the topological structure graph is determined to be connected; if the node s n If the strong relationship sets of are satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment;

[0055] The nodes n The strong relationship set is satisfied if the node attribute s of the current road data n =(s n，k ) and the relation value f(s n1 ,s n2 ) conforms to each relationship in the strong relationship set of the node; for example: the strong relationship set of n1 is {f1(s n1 ,s n2 )=0.5,f2(s n2 ,s n3 )=1.9,f3(s n1 ,s n2 )=0.1}, then substitute the current road data node attributes and relationship values ​​into f1(s n1 ,s n2 )=0.5,f2(s n2 ,s n3 )=1.9,f3(s n1 ,s n2 )=0.1, are all satisfied; satisfy means, equal or approximately equal; here approximately equal means that the value deviation is within the preset deviation range; for example: 0.1~5%;

[0056] Alternatively: the quasi-abnormal road segmentation is determined based on the node attributes and relationship values ​​of the topological structure diagram and the current road data; specifically: if the node s n The strong relationship sets of all satisfy; get node s n All other nodes s involved in the strong relationship set nx , if all other nodes s nx When all strong relationship sets of are satisfied or the satisfied ratio exceeds the first auxiliary ratio, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment;

[0057] Alternatively: the node attributes and relationship values ​​based on the topological structure diagram and the current road data determine the quasi-abnormal road segment; specifically: if the node s n The strong relationship sets of all satisfy; get node s n All other nodes s involved in the strong relationship set nx , if any other node s nx If at least one of the strong relations is satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment;

[0058] Preferably: the first auxiliary ratio is 50-90%;

[0059] Alternatively: the method of determining the quasi-abnormal road segment based on the node attributes and relationship values ​​of the topological structure diagram and the current road data is specifically: searching the topological structure diagram for global coverage and local coverage verification; performing auxiliary verification based on the strong relationship set; determining the quasi-abnormal road segment based on the auxiliary verification, global coverage and / or local coverage verification; specifically comprising the following steps:

[0060] Step S3A1: Get an unprocessed node as the current node s n ; is the current node s n Create a search node set ac n , put the current node into the search node set; set the verification value acv n =0;

[0061] Step S3A2: If there is a node s nx , the node s nx and search for any node s in the node set nv There is a connection relationship, and node s nx and nodes nv There is a sub-relationship value between them that belongs to any strong relationship set (and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set); then the node s nx Put it into the search node set; and set the search verification value acv n =acv n +c n1_n2 , repeat the process until there are no more nodes to be placed;

[0062] Preferably: before performing this step, pruning the topological structure graph is performed first; if there is a sub-relationship value between a node and any adjacent node that belongs to any strong relationship set of the node (or the proportion of belonging exceeds the second auxiliary proportion), and the node attribute and relationship value of the current road data satisfy the strong relationship set, then the connection relationship between the node and the adjacent node is retained in the topological structure graph, otherwise, the corresponding connection relationship is deleted; wherein: the second auxiliary proportion is less than or equal to the first auxiliary proportion;

[0063] Step S3A3: verifying the global coverage and / or local coverage based on the coverage of the search node set in the topological structure graph; specifically comprising the following steps:

[0064] Step S3A31: If the search verification value acv n If it is greater than or equal to the search verification threshold, proceed to the next step; otherwise, determine that the global coverage and local coverage verification have failed; verify the probability of the relationship occurring to ensure that the topological structure diagram is basically satisfied, and then perform subsequent verification operations; specifically: set the search verification threshold If the search verification value acv n If it is approximately equal to (equal to, greater than or equal to) the search verification threshold, then proceed to the next step; otherwise, it is determined that the global coverage and local coverage verifications have failed;

[0065] Step S3A32: global coverage verification; specifically: calculate global coverage, If Hca n When it is greater than the global coverage threshold, it is determined that the global coverage verification has passed;

[0066] Step S3A33: local coverage verification; specifically: set the local range, obtain the search node set ac n The search node subset ac′ that falls into the local range n , get the node set s n The node subset s′ that falls into the local range n , if the local coverage When it is greater than the local coverage threshold, it is determined that the local coverage verification has passed;

[0067] Preferably: the global coverage threshold and the local coverage threshold are preset values; for example: the global coverage threshold is 40-80%; the local coverage threshold is 80-95%; the local range is the actual physical distribution range of the road segment corresponding to the node; the collection environment and maintenance conditions of the road segments within the local range are the same or similar;

[0068] Step S3A4: If all sub-relationships in any (or more than a preset proportion) strong relationship set in the topological structure diagram are satisfied, all nodes involved in the strong relationship set are placed in the auxiliary verification set; repeat this step until all strong relationship sets are processed; if the auxiliary verification set is approximately equal to the node set, it is determined that the auxiliary verification has passed; of course, approximately equal can be limited by a threshold, for example: the difference in the number of elements in the two sets is very small, such as accounting for 5-10%,

[0069] Preferred: Set the initial value of the auxiliary validation set to be empty;

[0070] Step S3A5: if the auxiliary verification, global coverage and / or local coverage verification are passed, the road segment corresponding to the current node is determined to be a normal road segment, otherwise it is determined to be a quasi-abnormal road segment; if there are still unprocessed nodes, return to step S3A1;

[0071] Preferably, the method further comprises step S4: for the quasi-abnormal road segment, further image analysis or on-site inspection is performed to determine whether road maintenance is required;

[0072] Preferably: for quasi-abnormal road segments, autocorrelation analysis is performed to determine whether road maintenance is required;

[0073] Based on the same inventive concept, the present invention also provides a road maintenance monitoring system, the system is used to implement the above-mentioned road maintenance monitoring method; the system includes a server and a collection device distributed in the road sections, the collection device is used to obtain various types of road data, and send the various types of road data to the server, the server is used to execute the above-mentioned road maintenance monitoring method; the server stores historical road data;

[0074] Alternatively: the server is provided with an intelligent data access platform for acquiring historical road data;

[0075] Based on the same inventive concept, the present invention also provides a road maintenance monitoring server, the system is used to implement the above-mentioned road maintenance monitoring method;

[0076] Based on the same inventive concept, the present invention also provides a road maintenance monitoring client, the system is used to implement the above-mentioned road maintenance monitoring method;

[0077] A computer program (also referred to as a program, software, software application, script, or code) can be written in any form of a programming language, including an assembled or interpreted language, a declarative or procedural language, and it can be deployed in any form, including as a stand-alone program or as a module, component, subroutine, object, or other unit suitable for use in a computing environment. A computer program may, but need not, correspond to a file in a file system. A program can be stored in a portion of a file that holds other programs or data (e.g., one or more scripts stored in a markup language document), in a single file dedicated to the program, or in multiple collaborative files (e.g., files storing one or more modules, subroutines, or code portions). A computer program can be deployed to execute on one computer or on multiple computers located at one site or distributed across multiple sites and interconnected by a communication network.

[0078] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0079] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A road maintenance monitoring method, characterized in that: The method comprises: Step S1: For the road segments to be monitored, organize each road segment according to the connection relationship and / or geographical location distribution to obtain a topological structure diagram of the road to be monitored G = {S, C} = ({s n },{c n1_n2 }); where: S is the node set, C is the edge set; the node s in the graph n Indicates road segment n, edge c n1_n2 Indicates that there is a connection relationship or a geographical location distribution relationship between road segments n1 and n2; Step S2: Obtain historical road data of road segments of the road to be monitored; determine the strong relationship set and node s of the topological structure diagram based on each historical road data n The strong relationship set includes the following steps: Step S2A1: obtaining a piece of unprocessed historical road data; Step S2A2: Obtain the node attribute value for each road segment; n =(s n，k );s n，k is the kth element in the node attribute value; Step S2A3: Obtain the relationship value f(s) between every two road segments n1 ,s n2 )=(f k (s n1 ,s n2 )); where: f k (s n1 ,s n2 ) is the sub-relation for the k-th attribute; Step S2A4: if there is still unprocessed historical road data, return to step S2A1; otherwise, proceed to the next step; Step S2A5: Determine the strong relationship set of the topological structure graph; specifically: if the number of simultaneous occurrences of a sub-relationship value group containing one or more sub-relationship values ​​in each sub-relationship set corresponding to each historical road data exceeds the number threshold, then the sub-relationship value group containing one or more sub-relationship values ​​is placed in a strong relationship set; if there is a sub-relationship value involving node s in the strong relationship set n When , the strong relationship set is called node s n The strong relationship set of Step S3: Obtain the current road data of each road segment to be monitored, assign current values ​​to the topological structure diagram, and obtain the node attributes s of the current road data n =(s n，k ) and the relation value f(s n1 ,s n2 ); determine quasi-abnormal road segments based on the strong relationship set and the node attributes and relationship values ​​of the current road data.

2. The road maintenance monitoring method according to claim 1, characterized in that: A collection device is set up to collect data from the road to be monitored.

3. The road maintenance monitoring method according to claim 2, characterized in that: The acquisition device is one or more of an image acquisition device, a sound acquisition device, a radar, and a remote sensing device.

4. The road maintenance monitoring method according to claim 3, characterized in that: The road data of the road segment is obtained by performing local sampling on the road segment.

5. The road maintenance monitoring method according to claim 4, characterized in that: The method of determining the quasi-abnormal road segmentation based on the strong relationship set and the node attributes and relationship values ​​of the current road data is specifically as follows: for each edge in the topological structure diagram, a judgment is made; for nodes n1 and n2 in any edge, if there is a sub-relationship value between the two that belongs to a strong relationship set, and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set, then the connectivity count value acv is set n =acv n +c n1_n2 ; After completing the judgment of all edges, if Then the topological structure graph is determined to be connected; if the node s n If the strong relationship sets of are satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment.

6. The road maintenance monitoring method according to claim 5, characterized in that: Step S2 also includes: Step S2A6: Calculate the edge attribute value c of any two adjacent road segments n1 and n2 n1_n2 ; The method of determining the quasi-abnormal road segmentation based on the strong relationship set and the node attributes and relationship values ​​of the current road data is specifically as follows: for each edge in the topological structure diagram, a judgment is made; for nodes n1 and n2 in any edge, if there is a sub-relationship value between the two that belongs to a strong relationship set, and the node attributes and relationship values ​​of the current road data satisfy the strong relationship set, then the connectivity count value acv is set n =acv n +c n1_n2 ; After completing the judgment of all edges, if Then the topological structure graph is determined to be connected; if the node s n If the strong relationship sets of are satisfied, the road segment corresponding to the current node is determined to be a normal road segment; otherwise, it is determined to be a quasi-abnormal road segment.

7. The road maintenance monitoring method according to claim 6, characterized in that: The sub-relation f k (s n1 ,s n2 ) is one or more of a ratio relationship, a difference relationship, and a linear relationship.

8. A road maintenance monitoring server, characterized in that: The road maintenance monitoring server is used to implement the road maintenance monitoring method described in any one of claims 1 to 7.

9. A road maintenance monitoring system, characterized in that: The road maintenance monitoring system is used to implement the road maintenance monitoring method described in any one of claims 1 to 7.

10. A road maintenance monitoring platform, characterized in that: The road maintenance monitoring platform is used to implement the road maintenance monitoring method described in any one of claims 1 to 7.

Images