A method and system for intelligent maintenance management of urban road network

Abstract

The present invention relates to the technical field of road network maintenance management, and discloses a smart maintenance management method and system for urban road networks, the system comprising: an image acquisition module for acquiring real-time images of each road section in the area to be maintained. An information acquisition module for acquiring data information of each road section. A model building module for establishing a road condition model. An evaluation module for determining the state score of each road section based on the state data and the relationship between deformation data and preset state data within a preset time period. An analysis module for acquiring characteristic data of each lesion type in the lesion data, determining the label of the road section by matching the state data with the characteristic data, and determining the maintenance level of each road section based on the relationship between the average daily traffic volume, the label of the road section and the state score. A message sending module for sending the maintenance level of each road section to a road network maintenance platform. The present invention determines the maintenance level of each road section through the joint cooperation of each module, thereby effectively improving the accuracy of urban road network maintenance management.

Description

Technical Field

[0001] The present invention relates to the technical field of road network maintenance management, and in particular to a method and system for intelligent maintenance management of an urban road network. Background Art

[0002] With the continuous acceleration of urbanization, the construction and maintenance of urban road networks have become an important task to ensure smooth, safe and efficient operation of urban traffic. The development of modern cities requires an efficient transportation system to support daily economic activities and residents' travel. As the core component of the urban transportation system, the health of roads directly affects the operating efficiency of the entire transportation network. With the surge in urban population and the number of vehicles, the intensity of road use is also increasing, and the maintenance of the road network faces greater challenges. Especially in some old urban road sections, long-term use, natural environmental impact, traffic pressure and other factors have caused varying degrees of damage to the roads. Road network maintenance is not only related to the flatness and durability of the road surface, but also involves the safety, comfort and environmental adaptability of the road, and has extremely high social and economic value. Therefore, how to improve the level of road network maintenance management through effective technical means has become a practical problem that needs to be solved urgently.

[0003] At present, the traditional road network maintenance management method relies on manual inspection and experience judgment. Although this method has certain practicality in the past, with the expansion of urban scale and the increase of road management tasks, the traditional model has gradually exposed many shortcomings. Manual inspection has problems such as low efficiency, narrow coverage, large errors, and cannot monitor the changes of road sections in real time. Maintenance plans are often based on historical experience and regular inspections, lacking data support, resulting in lag and inaccuracy in maintenance measures. In addition, the standards of manual judgment are usually subjective, which easily leads to waste of maintenance resources or untimely decision-making, thus affecting the overall service quality of the road. With the continuous increase in urban traffic demand and the extension of the service life of the road surface, the damage of the road continues to worsen, and the traditional maintenance method is gradually unable to meet the growing demand for road network maintenance. The identification of pavement lesions, the grasp of maintenance timing, and the accuracy and timeliness of maintenance work are still the key problems in the current road network management. The traditional method has huge defects in obtaining the lesion information of the road section in real time, so the maintenance work lacks accurate data support, which ultimately affects the service life and traffic safety of the road.

[0004] Therefore, there is an urgent need to invent a road network maintenance management technology to solve the problem that traditional road network maintenance management relies on manual inspections and experience-based judgments, resulting in low efficiency, narrow coverage, large errors, lack of real-time data support, and inability to accurately identify road surface lesions and formulate maintenance measures in a timely manner, which affects the maintenance effect of the road network. Summary of the invention

[0005] In view of this, the present invention proposes an intelligent maintenance management method and system for urban road networks, aiming to solve the problem that traditional road network maintenance management relies on manual inspections and experience-based judgments, resulting in low efficiency, narrow coverage, large errors, lack of real-time data support, and inability to accurately identify road lesions and formulate maintenance measures in a timely manner, which affects the maintenance effect of the road network.

[0006] The present invention proposes an urban road network intelligent maintenance management system, comprising:

[0007] An image acquisition module is configured to acquire real-time images of each road section in the area to be maintained;

[0008] An information acquisition module is configured to acquire the road surface type, use environment information, preset use time after construction, and deformation data of each road section within a preset time period;

[0009] A model building module is configured to obtain the pathological data of each road surface type and build a road surface disease model;

[0010] An evaluation module is electrically connected to the image acquisition module, the information acquisition module and the model building module respectively, and is configured to obtain preset status data of the road section according to the relationship between the road surface type, the use environment information, the preset use time and the road condition model of the road section; the evaluation module is also configured to pre-process the real-time image of each of the road sections and extract the status data of each of the road sections after pre-processing; the evaluation module is also configured to determine the status score of each of the road sections according to the relationship between the status data and the deformation data within a preset time period and the preset status data;

[0011] An analysis module is electrically connected to the image acquisition module, the information acquisition module, the model building module and the evaluation module respectively, and is configured to obtain feature data of each lesion type in the lesion data, and match the state data with the feature data, wherein:

[0012] If the state data matches any of the feature data, the analysis module determines that the label of the road section is a damaged road section;

[0013] If the state data and the characteristic data do not match each other, the analysis module determines that the label of the road section is a healthy road section;

[0014] The analysis module is further configured to obtain the average daily traffic volume in the environmental information of each of the road sections, and determine the maintenance level of each of the road sections according to the relationship between the average daily traffic volume, the label of the road section and the status score;

[0015] A message sending module is electrically connected to the analysis module, and the message sending module is configured to send the maintenance level of each road section to the road network maintenance platform.

[0016] Furthermore, when the model building module builds the road condition model according to the pathological data of each road type, it includes:

[0017] The model building module is further configured to obtain the road surface material in each of the road surface types, and remove the road surface material and lesion data and duplicate data in the lesion data, wherein the lesion data includes: use environment data, road surface use data and deformation data;

[0018] The model building module is further configured to establish a disease association equation according to the relationship between the road surface material and each of the environmental data and deformation data corresponding to the road surface material;

[0019] The model building module is further configured to obtain a distance metric between each of the disease association equations, and to establish a distance matrix according to the distance metric;

[0020] The model building module is also configured to iteratively merge the disease association equations according to the distance matrix, and to build the pavement condition model according to the disease association equations of the pavement materials after iterative merging.

[0021] Furthermore, when the model building module builds the pavement condition model according to the iteratively merged disease correlation formulas of the pavement materials, it includes:

[0022] The model building module is further configured to establish various disease types of the pavement material according to the disease association formulas of the pavement material after iterative merging;

[0023] The model building module is further configured to cluster the disease association equations according to the disease types;

[0024] The model building module is further configured to obtain a linear relationship between the disease types according to the relationship between the disease association equations after clustering;

[0025] The model building module is also configured to build the pavement condition model according to the linear relationship between the disease types of the pavement materials.

[0026] Furthermore, when establishing the road condition model, the model building module further includes:

[0027] The model building module is further configured to obtain the road material of any of the road types and environmental data in the disease data, and obtain preset deformation data of the road type according to the road material, environmental data, road use data and road condition model;

[0028] The model building module is further configured to determine whether to modify the road condition model according to the relationship between the preset deformation data and the deformation data in the lesion data corresponding to the road type;

[0029] When the preset deformation data is consistent with the deformation data, the model building module determines not to modify the road condition model;

[0030] When the preset deformation data is inconsistent with the deformation data, the model building module determines to iteratively correct the distance matrix in the road condition model until the preset deformation data is consistent with the deformation data.

[0031] Furthermore, when the evaluation module preprocesses the real-time image of each road section and extracts the state data of each road section after preprocessing, it includes:

[0032] The evaluation module is further configured to remove noise from the real-time image and perform sharpening processing on the real-time image after the noise is removed;

[0033] The evaluation module is further configured to correct the real-time image after the sharpening process based on an affine transformation;

[0034] The evaluation module is further configured to extract texture data of the road section in the corrected real-time image.

[0035] Furthermore, when the evaluation module determines the status score of each of the road sections according to the status data and the relationship between the deformation data within a preset period and the preset status data, it includes:

[0036] The evaluation module is further configured to obtain the defect type of the road section and defect data of each defect type according to the relationship between the state data and the preset state data;

[0037] The evaluation module is further configured to obtain a status score of the road section based on Formula I, deformation data within a preset period, defect types of the road section, and a relationship between defect data of each defect type, wherein Formula I is as follows:

[0038] ;

[0039] Wherein, S is the state score of the road section, N is the total number of defects of the road section, wi is the weight of the i-th damage type, Di is the degree measure of the i-th damage, α and β are weight coefficients, and both α and β are not zero, and F is the deformation score of the deformation data;

[0040] The evaluation module is further configured to obtain a preset deformation amount of the road section within a preset period of time based on the road condition model; the evaluation module is further configured to obtain the deformation amount of the road section within a preset period of time according to the deformation data within the preset period of time, and determine the deformation score F of the deformation data based on Formula II, the relationship between the preset deformation amount and the deformation amount, wherein Formula II is as follows:

[0041] ;

[0042] Among them, ei is the weight coefficient of the i-th deformation type in the deformation data, H is the preset deformation amount of the deformation type, and h is the deformation amount of the deformation type.

[0043] Furthermore, when the analysis module determines the maintenance level of each road section according to the relationship between the average daily traffic volume, the label of the road section and the status score, it includes:

[0044] The analysis module is also configured with a preset status score;

[0045] The analysis module is further configured to determine the maintenance level of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic volume, and adjust the maintenance level of the road section according to the label of the road section, wherein:

[0046] The analysis module is further configured to determine the maintenance score of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic volume, and determine the maintenance level of the road section according to the relationship between the maintenance score and the first preset maintenance score and the second preset maintenance score preconfigured in the analysis module:

[0047] When the maintenance score is lower than the first preset maintenance score, the analysis module determines that the maintenance level of the road section is a low level;

[0048] When the maintenance score is higher than or equal to the first preset maintenance score, and the maintenance score is lower than the second preset maintenance score, the analysis module determines that the maintenance level of the road section is medium;

[0049] When the maintenance score is higher than or equal to the second preset maintenance score, the analysis module determines that the maintenance level of the road section is a high level;

[0050] Among them, the first preset maintenance score is lower than the second preset maintenance score, and the maintenance levels are arranged in order of high level, medium level and low level.

[0051] Furthermore, when the analysis module determines the maintenance score of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic flow, it includes:

[0052] The analysis module is further configured with a first preset score difference and a second preset score difference, and determines the basic score of the maintenance score according to the relationship between the score difference and the first preset score difference and the second preset score difference:

[0053] When the score difference is lower than the first preset score difference, the analysis module determines that the basic score is Q1;

[0054] When the score difference is higher than or equal to the first preset score difference, and the score difference is lower than the second preset score difference, the analysis module determines that the basic score is Q2;

[0055] When the score difference is higher than or equal to the second preset score difference, the analysis module determines that the basic score is Q3;

[0056] Wherein, the first preset score difference is less than the second preset score difference, and Q1<Q2<Q3;

[0057] When the analysis module determines that the basic score is Qi, i=1, 2, 3, the analysis module is further configured to obtain the average of the daily average traffic flow of each of the road sections, and determine the average as the preset daily average traffic flow of the road section;

[0058] The analysis module is further configured to determine whether to adjust the basic score Qi according to the relationship between the average daily traffic flow and the preset average daily traffic flow, wherein:

[0059] When the average daily traffic volume is lower than or equal to the preset average daily traffic volume, the analysis module determines the basic score Qi as the maintenance score of the road section;

[0060] When the average daily traffic volume is higher than the preset average daily traffic volume, the analysis module determines an adjustment coefficient according to the traffic volume difference between the average daily traffic volume and the preset average daily traffic volume, and determines the basic score Qi adjusted according to the adjustment coefficient as the maintenance score of the road section, wherein the value range of the adjustment coefficient is (0,1).

[0061] Furthermore, when the analysis module adjusts the maintenance level of the road section according to the label of the road section, it includes:

[0062] When the label of the road section is a healthy road section, the analysis module does not adjust the maintenance level of the road section;

[0063] When the label of the road section is a damaged road section, the analysis module increases the maintenance level of the road section, wherein:

[0064] If the maintenance level of the road section is low, the analysis module upgrades the maintenance level of the road section to medium;

[0065] If the maintenance level of the road section is medium, the analysis module upgrades the maintenance level of the road section to high;

[0066] If the maintenance level of the road section is high, the analysis module will not increase the maintenance level of the road section.

[0067] Compared with the prior art, the beneficial effect of the present invention is that: through the image acquisition module, the image data of each road section in the maintenance area can be captured in real time, providing basic visual information for subsequent lesion analysis and evaluation. The information acquisition module further supplements the detailed information of the road section, including the road surface type, use environment, construction time and deformation data, etc., which lays the foundation for establishing an accurate road condition model. Secondly, the evaluation module can accurately capture the changes in the road section by preprocessing the real-time image and extracting the status data. The image preprocessing includes steps such as noise removal, sharpening, and transformation, which not only improves the image quality, but also better identifies the subtle lesion features. Based on the extracted status data, the health status of each road section can be evaluated in real time, and the status score of each road section can be calculated by comparing it with the deformation data within a preset time period. This process transforms the inefficiency and error problems of traditional manual inspections into efficient data analysis, making the maintenance work more scientific and accurate. In addition, the analysis module can automatically identify the disease status of the road section by matching the characteristic data of each lesion type in the lesion data, and clearly mark it as a diseased section or a healthy section. This intelligent marking method avoids the subjectivity of manual judgment, so that maintenance work can be performed based on real and objective data. At the same time, the analysis module also comprehensively considers the average daily traffic volume of each section, and dynamically calculates the maintenance level based on the relationship between traffic volume and the disease status and score of the section, so as to achieve differentiated maintenance strategies in different sections and different time periods, ensuring that maintenance resources are reasonably allocated and optimized. Finally, the message sending module transmits the maintenance level of each section to the road network maintenance platform in real time by connecting with the analysis module. This mechanism not only ensures that maintenance work can respond quickly to actual conditions, but also provides a comprehensive monitoring and feedback system for the long-term maintenance of the road network.

[0068] On the other hand, the present application also provides a method for intelligent maintenance and management of urban road networks, including:

[0069] Acquire real-time images of each road section in the area to be maintained, as well as the road surface type, use environment information, preset use time after construction, and deformation data of each road section within a preset time period;

[0070] Acquiring preset state data of the road section according to the relationship between the road surface type, usage environment information, preset usage time and a pre-established road condition model of the road section;

[0071] Preprocessing the real-time image of each road section, extracting the state data of each road section after preprocessing, and determining the state score of each road section according to the state data and the relationship between the deformation data within a preset time period and the preset state data;

[0072] Acquire characteristic data of each lesion type in the lesion data, match the state data with the characteristic data, and determine a label of each of the road sections according to the matching result;

[0073] The average daily traffic volume in the environmental information of each of the road sections is obtained, and the maintenance level of each of the road sections is determined according to the relationship between the average daily traffic volume, the label of the road section and the status score.

[0074] It can be understood that the urban road network intelligent maintenance management method and system in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0076] Figure 1 A functional block diagram of an urban road network intelligent maintenance management system provided by an embodiment of the present invention;

[0077] Figure 2 A flowchart of a method for intelligent maintenance and management of urban road networks provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0078] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to be able to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0079] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides an urban road network intelligent maintenance management system, including: an image acquisition module, an information acquisition module, a model building module, an evaluation module, an analysis module and a message sending module.

[0080] Specifically, the image acquisition module is configured to acquire real-time images of each road section in the area to be maintained; the information acquisition module is configured to acquire the road surface type, usage environment information, preset usage time after construction and deformation data of each road section within a preset time period of each road section; the model establishment module is configured to acquire the lesion data of each road surface type and establish a road surface condition model; the evaluation module is electrically connected to the image acquisition module, the information acquisition module and the model establishment module respectively, and the evaluation module is configured to acquire preset status data of the road section based on the relationship between the road surface type, usage environment information, preset usage time and road surface condition model of the road section; the evaluation module is also configured to pre-process the real-time images of each road section and extract the status data of each road section after pre-processing; the evaluation module is also configured to evaluate the status data of each road section based on the relationship between the status data and the deformation data within a preset time period and the preset status data system, determine the status score of each road section; the analysis module is electrically connected to the image acquisition module, the information acquisition module, the model building module and the evaluation module respectively, the analysis module is configured to obtain the characteristic data of each lesion type in the lesion data, and match the state data with the characteristic data, wherein: if the state data matches any characteristic data, the analysis module determines that the label of the road section is a diseased section; if the state data matches each characteristic data inconsistently, the analysis module determines that the label of the road section is a healthy section; the analysis module is also configured to obtain the average daily traffic volume in the environmental information of each road section, and determine the maintenance level of each road section according to the relationship between the average daily traffic volume, the label of the road section and the status score; the message sending module is electrically connected to the analysis module, and the message sending module is configured to send the maintenance level of each road section to the road network maintenance platform.

[0081] It can be seen that the image acquisition module is responsible for acquiring real-time images of each road section in the area to be maintained, and these images provide visual data of road lesions. Through modern image processing technology, the acquired images are pre-processed such as denoising, enhancement and texture extraction to clearly identify the lesion area on the road surface. The image data can not only accurately reflect the current condition of the road section, but also capture the changing trend of the road section status through continuous monitoring. Next, the information acquisition module collects environmental information, road surface type, service life and deformation data of the road section through a variety of sensors and equipment. These data provide an important basis for the accurate assessment of the road condition. In particular, by acquiring the use environment and road surface material of different road sections, the law of road lesions under different conditions can be identified, thereby providing data support for the subsequent establishment of disease models. By accurately collecting deformation data within a preset time period, the changes of the road section in different time periods can be accurately grasped, further improving the accuracy of maintenance prediction. In the model establishment stage, the road condition model is established by using the existing lesion data and road use data. The model establishment module analyzes the lesion data of different road types, associates the lesion type with the road section status, and generates a lesion prediction model. These pathological data include usage environment data, pavement usage and deformation data. Taking these factors into consideration, the system can predict the probability of occurrence of diseases of different pavement types and provide a theoretical basis for maintenance decisions. The evaluation module conducts a comprehensive evaluation based on the model, pavement type, usage environment and historical data, generates a status score for each road section, and reflects the maintenance needs of the road section in real time. In addition, the analysis module automatically determines whether a road section has a disease by comparing the matching relationship between the road section status data and the pathological characteristic data. For example, when the status data of a road section highly matches the characteristic data of a certain pathological type, the road section will be marked as a diseased road section, otherwise, it will be marked as a healthy road section. This function greatly improves the degree of automation of road maintenance and avoids the subjectivity and errors of human judgment. In addition, the analysis module will further optimize the maintenance plan by combining factors such as the average daily traffic volume. Through the analysis of traffic volume, the system can dynamically adjust the maintenance strategy to ensure the reasonable allocation and efficient use of maintenance resources. Finally, the message sending module will transmit the maintenance level information of each road section to the road network maintenance platform to realize real-time information sharing and feedback. This function enables the road network maintenance platform to timely understand the actual maintenance needs of road sections and optimize resource scheduling and decision support.

[0082] It is understandable that by integrating multiple modules such as image acquisition, information collection, lesion data modeling, status assessment, and data analysis, it is possible to achieve real-time monitoring of road sections, automated assessment, and precise maintenance decisions. By automatically acquiring and processing road section images, environmental information, and deformation data, and combining lesion data to establish a road condition model, the real-time and accuracy of maintenance work is effectively improved. At the same time, based on the matching analysis of lesion data and road section status, it is possible to automatically determine whether a road section has a disease, and determine maintenance priorities based on traffic volume and road section status, ensuring the rational allocation and efficient use of maintenance resources, thereby extending the service life of the road, reducing maintenance costs, and improving traffic safety.

[0083] Specifically, when the model building module establishes the pavement condition model based on the lesion data of each pavement type, it includes: the model building module is also configured to obtain the pavement material in each pavement type, and eliminate the pavement material and lesion data and duplicate data in the lesion data, wherein the lesion data includes: usage environment data, pavement usage data and deformation data. The model building module is also configured to establish a disease association formula based on the relationship between the pavement material and the environmental data and deformation data corresponding to the pavement material. The model building module is also configured to obtain the distance measurement between each disease association formula, and establish a distance matrix based on the distance measurement. The model building module is also configured to iteratively merge each disease association formula based on the distance matrix, and establish a pavement condition model based on each disease association formula of each pavement material after iterative merging.

[0084] Specifically, when the model building module builds the pavement condition model according to the disease correlation formulas of each pavement material after iterative merging, it includes: the model building module is also configured to build each disease type of the pavement material according to the disease correlation formulas of the pavement material after iterative merging. The model building module is also configured to cluster each disease correlation formula according to each disease type. The model building module is also configured to obtain the linear relationship of the disease type according to the relationship between the disease correlation formulas after clustering. The model building module is also configured to build the pavement condition model according to the linear relationship of each disease type of each pavement material.

[0085] Specifically, when the model building module builds the pavement condition model, it also includes: the model building module is also configured to obtain the pavement material of any pavement type and the environmental data in the disease data, and obtain the preset deformation data of the pavement type according to the pavement material, environmental data, pavement use data and the pavement condition model. The model building module is also configured to determine whether to modify the pavement condition model according to the relationship between the preset deformation data and the deformation data in the lesion data corresponding to the pavement type: when the preset deformation data is consistent with the deformation data, the model building module determines not to modify the pavement condition model. When the preset deformation data is inconsistent with the deformation data, the model building module determines to iteratively modify the distance matrix in the pavement condition model until the preset deformation data is consistent with the deformation data.

[0086] It can be seen that by eliminating duplicate data and establishing disease associations, the model building module can clearly present the relationship between different pavement materials and their corresponding environment and deformation data, effectively avoiding information redundancy and accurately locating the potential causes of the disease. This precise association analysis provides reliable basic data for subsequent pavement condition assessment, thereby improving the accuracy and scientificity of maintenance work. In addition, the model building module can better capture the similarities and differences between diseases by establishing a distance matrix and iteratively merging disease associations. Through cluster analysis of disease types, the module can identify the linear relationship between different disease types, thereby further optimizing the construction of the pavement condition model. In this way, the model can not only refine different types of pavement lesions, but also form an efficient disease identification mechanism to help maintenance personnel better judge maintenance needs and priorities. Finally, the model building module can continuously optimize and correct the pavement condition model by comparing the difference between the preset deformation data and the actual deformation data. When the preset deformation data is inconsistent with the actual data, the module will automatically perform iterative corrections to ensure the accuracy of the disease model. This adaptive correction function enables the pavement condition model to reflect the actual condition of the pavement in real time, and thus effectively identify and analyze the occurrence and development of pavement lesions.

[0087] It is understandable that the model building module first cleans and optimizes the data set by eliminating unnecessary duplicate data, so that the subsequent model building process will not be disturbed by invalid information. This link directly improves the efficiency of data processing and reduces the waste of computing resources. By combining the pavement material, use environment and deformation data, the model building module can construct a more accurate disease correlation, which makes the maintenance requirements of different pavement materials clearly layered, thereby providing maintenance personnel with targeted repair strategies. The establishment of the disease correlation not only provides a scientific basis for subsequent disease analysis, but also helps to design maintenance standards for different pavement types in a targeted manner, avoiding the "one-size-fits-all" phenomenon in traditional maintenance methods. Secondly, the model building module can measure and evaluate the similarity between different disease correlations by using distance metrics and distance matrix technologies. In this way, the model building module can continuously iterate and merge similar disease data, remove redundant information, and improve the accuracy and applicability of the disease model. The application of the distance matrix can systematically display the similarity relationship between diseases and provide a quantitative perspective for the correlation between disease types. This processing method not only enables the identification of a single disease type, but also reveals possible chain reactions between diseases, thereby predicting future pavement disease trends. This disease prediction function provides pavement managers with more long-term decision support and helps to formulate more scientific and sustainable pavement maintenance plans. More importantly, the adaptive correction mechanism of the model building module can ensure the continued effectiveness of the disease model by comparing real-time monitoring with preset data. Whenever the actual deformation data is inconsistent with the preset deformation data, the iterative correction process will be automatically triggered to adjust the model by continuously optimizing the distance matrix. This self-correction mechanism ensures that the model can always be dynamically updated according to the latest pavement data, avoiding maintenance decision errors caused by information lag in traditional methods. The intelligence and automation of the correction process further improve the response speed and accuracy of the model building module, allowing pavement maintenance work to be carried out quickly and accurately.

[0088] Specifically, when the evaluation module preprocesses the real-time image of each road section and extracts the state data of each road section after preprocessing, the evaluation module includes: the evaluation module is also configured to remove noise from the real-time image and perform sharpening processing on the real-time image after noise removal. The evaluation module is also configured to correct the sharpened real-time image based on affine transformation. The evaluation module is also configured to extract the texture data of the road section in the corrected real-time image.

[0089] It can be understood that by removing the noise from the real-time image, the image quality is significantly improved. Noise removal is a key step in image processing, which can remove random interference signals in the image, such as blur, light reflection or stray light. This process can effectively reduce the impact of environmental factors on image analysis and improve the accuracy and reliability of subsequent processing. The denoised image can clearly reflect the real state of the road section, providing a high-quality data basis for subsequent texture extraction and road condition analysis, ensuring the accuracy and reliability of the evaluation results. Secondly, based on the noise removal, the evaluation module further enhances the image details through sharpening. Sharpening is a technology that improves image clarity by enhancing the contrast of edges and details in the image. Through this process, the tiny details of the road surface are highlighted, providing more information for the detection of road lesions or damage. This operation is of great significance for road maintenance, because subtle diseases are usually manifested as tiny surface cracks or wear, and sharpening can make these details more obvious, thereby facilitating detection and diagnosis. Finally, the evaluation module uses affine transformation to correct the sharpened image to ensure the geometric accuracy of the image. Affine transformation is a technique that adjusts the geometric shape of an image by rotation, translation, scaling, and shearing, in order to eliminate image distortion caused by factors such as shooting angle and viewing distance. In road network maintenance, images may be distorted or twisted due to changes in road shape and shooting angle. The application of affine transformation can ensure the uniformity and consistency of all images, making subsequent analysis more accurate.

[0090] Specifically, when the evaluation module determines the status score of each road section according to the status data and the relationship between the deformation data within a preset time period and the preset status data, the evaluation module is further configured to obtain the defect type of the road section and the defect data of each defect type according to the relationship between the status data and the preset status data. The evaluation module is also configured to obtain the status score of the road section based on Formula I, the relationship between the deformation data within a preset time period, the defect type of the road section, and the defect data of each defect type, wherein Formula I is as follows: .

[0091] Wherein, S is the status score of the road section, N is the total number of defects in the road section, wi is the weight of the i-th damage type, Di is the degree measure of the i-th damage, α and β are weight coefficients, and both α and β are not zero, and F is the deformation score of the deformation data. Wherein, the evaluation module is also configured to obtain the preset deformation amount of the road section within a preset time period based on the road condition model. The evaluation module is also configured to obtain the deformation amount of the road section within a preset time period according to the deformation data within the preset time period, and determine the deformation score F of the deformation data based on Formula II, the preset deformation amount and the relationship between the deformation amount, where Formula II is as follows: .

[0092] Among them, ei is the weight coefficient of the i-th deformation type in the deformation data, H is the preset deformation amount of the deformation type, and h is the deformation amount of the deformation type.

[0093] It is understandable that the evaluation module ensures the accuracy and reliability of image information by using real-time images and preset data, removing noise, image sharpening, and affine transformation correction. This processing process not only eliminates interference information in the image, but also improves the recognizability of road section features, thereby providing high-quality image data for subsequent data extraction and analysis. After extracting the road section texture data in the image, the evaluation module further analyzes the relationship between these textures and the road condition, and performs a comprehensive score through the formula model. Formula I takes the defect type, defect degree, and deformation data as key variables when calculating the road section status score, and assigns different weights to each damage type, thereby accurately reflecting the actual damage of the road section. Combining deformation data and road section use environment information, the evaluation module can assign a scientific and reasonable status score to each road section, which is convenient for decision makers to judge whether the road section needs immediate maintenance. In addition, the evaluation module further refines the impact of deformation data on the road section status through Formula II, and uses the relationship between the preset deformation variable and the actual deformation variable of the deformation type to conduct a detailed analysis of the deformation of the road section. The core of this step is to predict and evaluate the deformation changes of the road section within a certain period of time based on the preset deformation model, thereby improving the accuracy of the deformation score. This evaluation method that combines the disease model and deformation data not only takes into account the structural damage of the road section, but also integrates environmental factors and traffic impacts, which helps to more comprehensively and accurately evaluate the actual health status of the road section and provide more effective maintenance recommendations and decision-making basis. Through this comprehensive evaluation technology of multi-dimensional data, more scientific road network maintenance management can be achieved, avoiding the errors that may be caused by single-dimensional data analysis, thereby improving the recognition rate of road lesions and reducing resource waste.

[0094] Specifically, when the analysis module determines the maintenance level of each road section according to the relationship between the average daily traffic volume, the label of the road section and the status score, it includes: the analysis module is also configured with a preset status score. The analysis module is also configured to determine the maintenance level of the road section according to the relationship between the score difference between the status score and the preset status score and the average daily traffic volume, and adjust the maintenance level of the road section according to the label of the road section, wherein: the analysis module is also configured to determine the maintenance score of the road section according to the relationship between the score difference between the status score and the preset status score and the average daily traffic volume, and determine the maintenance level of the road section according to the relationship between the maintenance score and the first preset maintenance score and the second preset maintenance score pre-configured by the analysis module: when the maintenance score is lower than the first preset maintenance score, the analysis module determines that the maintenance level of the road section is low. When the maintenance score is higher than or equal to the first preset maintenance score, and the maintenance score is lower than the second preset maintenance score, the analysis module determines that the maintenance level of the road section is medium. When the maintenance score is higher than or equal to the second preset maintenance score, the analysis module determines that the maintenance level of the road section is high. The first preset maintenance score is lower than the second preset maintenance score, and the maintenance levels are ranked in order of high, medium, and low.

[0095] Specifically, when the analysis module determines the maintenance score of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic flow, it includes: the analysis module is also configured with a first preset score difference and a second preset score difference, and the basic score of the maintenance score is determined according to the relationship between the score difference and the first preset score difference and the second preset score difference: when the score difference is lower than the first preset score difference, the analysis module determines the basic score to be Q1; when the score difference is higher than or equal to the first preset score difference, and the score difference is lower than the second preset score difference, the analysis module determines the basic score to be Q2. When the score difference is higher than or equal to the second preset score difference, the analysis module determines the basic score to be Q3. Among them, the first preset score difference is less than the second preset score difference, and Q1<Q2<Q3. When the analysis module determines that the basic score is Qi, i=1,2,3, the analysis module is also configured to obtain the average of the average daily traffic flow of each road section, and determine the average as the preset average daily traffic flow of the road section. The analysis module is also configured to determine whether to adjust the basic score Qi based on the relationship between the average daily traffic flow and the preset average daily traffic flow, wherein: when the average daily traffic flow is lower than or equal to the preset average daily traffic flow, the analysis module determines the basic score Qi as the maintenance score of the road section; when the average daily traffic flow is higher than the preset average daily traffic flow, the analysis module determines the adjustment coefficient based on the flow difference between the average daily traffic flow and the preset average daily traffic flow, and determines the basic score Qi adjusted according to the adjustment coefficient as the maintenance score of the road section, wherein the value range of the adjustment coefficient is (0,1).

[0096] Specifically, when the analysis module adjusts the maintenance level of the road section according to the label of the road section, it includes: when the label of the road section is a healthy road section, the analysis module does not adjust the maintenance level of the road section. When the label of the road section is a diseased road section, the analysis module improves the maintenance level of the road section, wherein: if the maintenance level of the road section is a low level, the analysis module improves the maintenance level of the road section to a medium level. If the maintenance level of the road section is a medium level, the analysis module improves the maintenance level of the road section to a high level. If the maintenance level of the road section is a high level, the analysis module does not improve the maintenance level of the road section.

[0097] It can be seen that the analysis module can accurately evaluate the maintenance needs of each road section by combining multiple factors such as the difference between the status score and the preset score, the average daily traffic volume, etc. By setting different score differences and traffic volume standards, it can not only reflect the current actual situation of the road section, but also predict its future maintenance trend. This comprehensive consideration of factors helps managers to grasp the changes in the road section in real time and ensure that the maintenance plan can be adjusted in time when the road surface is damaged, so as to achieve the effect of both prevention and repair. In addition, when adjusting the maintenance level, the analysis module can flexibly improve the maintenance level according to the labels of different road sections (healthy sections or diseased sections) to meet the maintenance needs of different sections. In particular, the priority improvement of diseased sections can effectively avoid higher maintenance costs caused by further aggravation of the disease on the road section. This on-demand adjustment mechanism not only enhances the ability to respond to complex situations, but also improves the utilization efficiency of maintenance resources. By continuously adjusting and optimizing maintenance strategies, the long-term health and stable operation of the urban road network can be ensured, thereby providing citizens with a safer and more convenient traffic environment.

[0098] It is understandable that the analysis module determines the score difference by comparing the status score of the road section with the preset status score, and evaluates the maintenance needs in combination with the average daily traffic volume. The size of the score difference directly affects the calculation of the maintenance score. Using the set score difference threshold, the analysis module divides the score difference into different level ranges. It ensures that under different score differences, the maintenance priority can be flexibly adjusted according to the actual road conditions. Furthermore, the analysis module makes dynamic adjustments based on the difference between the average daily traffic volume and the preset average daily traffic volume. When the actual traffic volume of the road section exceeds the preset value, the analysis module calculates the adjustment coefficient based on the traffic volume difference and adjusts the basic score accordingly, so that the maintenance score is more in line with the actual traffic conditions. This traffic volume-based adjustment mechanism ensures that maintenance work is given priority in sections with high traffic loads to avoid accelerated road damage caused by excessive traffic volume. In addition, in order to ensure the accuracy and rationality of the maintenance work, the analysis module further adjusts the maintenance level in combination with the label information of the road section (healthy or diseased road section). For healthy sections, their existing maintenance level will be maintained to avoid unnecessary waste of resources; for diseased sections, their maintenance level will be upgraded according to the maintenance score to ensure that diseased sections can be treated more promptly and with priority. This mechanism can effectively improve the overall maintenance efficiency of the road network, avoid the expansion of road lesions caused by untimely maintenance, and thus improve the overall health level and service life of the road network.

[0099] In the above embodiment, the image acquisition module can capture the image data of each road section in the maintenance area in real time, providing basic visual information for subsequent lesion analysis and evaluation. The information acquisition module further supplements the detailed information of the road section, including the road surface type, use environment, construction time and deformation data, etc., which lays the foundation for establishing an accurate road condition model. Secondly, the evaluation module can accurately capture the changes in the road section by preprocessing the real-time image and extracting the status data. The image preprocessing includes steps such as noise removal, sharpening, and transformation, which not only improves the image quality, but also better identifies the subtle lesion features. Based on the extracted status data, the health status of each road section can be evaluated in real time, and the status score of each road section can be calculated by comparing it with the deformation data within a preset time period. This process transforms the inefficiency and error problems of traditional manual inspections into efficient data analysis, making maintenance work more scientific and accurate. In addition, the analysis module can automatically identify the disease status of the road section by matching the characteristic data of each lesion type in the lesion data, and clearly mark it as a diseased road section or a healthy road section. This intelligent marking method avoids the subjectivity of manual judgment, so that maintenance work can be performed based on real and objective data. At the same time, the analysis module also comprehensively considers the average daily traffic volume of each section, and dynamically calculates the maintenance level based on the relationship between traffic volume and the disease status and score of the section, so as to achieve differentiated maintenance strategies in different sections and different time periods, ensuring that maintenance resources are reasonably allocated and optimized. Finally, the message sending module transmits the maintenance level of each section to the road network maintenance platform in real time by connecting with the analysis module. This mechanism not only ensures that maintenance work can respond quickly to actual conditions, but also provides a comprehensive monitoring and feedback system for the long-term maintenance of the road network.

[0100] In another preferred embodiment based on the above embodiment, Figure 2 As shown, this embodiment provides a method for intelligent maintenance and management of urban road networks, including:

[0101] Step S100, obtaining real-time images of each road section in the area to be maintained, as well as the road surface type, use environment information, preset use time after construction, and deformation data of each road section within a preset time period.

[0102] Step S200: Acquire preset status data of the road section according to the relationship between the road surface type of the road section, usage environment information, preset usage time and a pre-established road condition model.

[0103] Step S300, preprocessing the real-time image of each road section, extracting the state data of each road section after preprocessing, and determining the state score of each road section according to the state data and the relationship between the deformation data within a preset time period and the preset state data.

[0104] Step S400: Acquire feature data of each lesion type in the lesion data, match the state data with the feature data, and determine the label of each road section according to the matching result.

[0105] Step S500: Obtain the average daily traffic volume in the environmental information of each road section, and determine the maintenance level of each road section according to the relationship between the average daily traffic volume, the label of the road section and the status score.

[0106] It can be understood that the urban road network intelligent maintenance management method and system in the above-mentioned embodiments of the present invention have the same beneficial effects and will not be repeated here.

[0107] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application 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 codes.

[0108] The present application 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 box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes 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 produce 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.

[0109] 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.

[0110] 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 in the computer or other programmable device. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] 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. An intelligent urban road network maintenance management system, characterized in that: include: An image acquisition module is configured to acquire real-time images of each road section in the area to be maintained; An information acquisition module is configured to acquire the road surface type, use environment information, preset use time after construction, and deformation data of each road section within a preset time period; A model building module is configured to obtain the pathological data of each road surface type and build a road surface disease model; An evaluation module is electrically connected to the image acquisition module, the information acquisition module and the model building module respectively, and is configured to obtain preset status data of the road section according to the relationship between the road surface type, the use environment information, the preset use time and the road condition model of the road section; the evaluation module is also configured to pre-process the real-time image of each of the road sections and extract the status data of each of the road sections after pre-processing; the evaluation module is also configured to determine the status score of each of the road sections according to the relationship between the status data and the deformation data within a preset time period and the preset status data; An analysis module is electrically connected to the image acquisition module, the information acquisition module, the model building module and the evaluation module respectively, and is configured to obtain feature data of each lesion type in the lesion data, and match the state data with the feature data, wherein: If the state data matches any of the feature data, the analysis module determines that the label of the road section is a damaged road section; If the state data and the characteristic data do not match each other, the analysis module determines that the label of the road section is a healthy road section; The analysis module is further configured to obtain the average daily traffic volume in the environmental information of each of the road sections, and determine the maintenance level of each of the road sections according to the relationship between the average daily traffic volume, the label of the road section and the status score; A message sending module, electrically connected to the analysis module, and configured to send the maintenance level of each road section to the road network maintenance platform; When the evaluation module preprocesses the real-time image of each road section and extracts the state data of each road section after preprocessing, it includes: The evaluation module is further configured to remove noise from the real-time image and perform sharpening processing on the real-time image after the noise is removed; The evaluation module is further configured to correct the real-time image after the sharpening process based on an affine transformation; The evaluation module is further configured to extract texture data of the road section in the corrected real-time image; When the evaluation module determines the status score of each of the road sections according to the status data and the relationship between the deformation data within a preset period and the preset status data, it includes: The evaluation module is further configured to obtain the defect type of the road section and defect data of each defect type according to the relationship between the state data and the preset state data; The evaluation module is further configured to obtain a status score of the road section based on Formula I, deformation data within a preset period, defect types of the road section, and a relationship between defect data of each defect type, wherein Formula I is as follows: ； Wherein, S is the state score of the road section, N is the total number of defects of the road section, wi is the weight of the i-th damage type, Di is the degree measure of the i-th damage, α and β are weight coefficients, and both α and β are not zero, and F is the deformation score of the deformation data; The evaluation module is further configured to obtain a preset deformation amount of the road section within a preset period of time based on the road condition model; the evaluation module is further configured to obtain the deformation amount of the road section within a preset period of time according to the deformation data within the preset period of time, and determine the deformation score F of the deformation data based on Formula II, the relationship between the preset deformation amount and the deformation amount, wherein Formula II is as follows: ； Among them, ei is the weight coefficient of the i-th deformation type in the deformation data, H is the preset deformation amount of the deformation type, and h is the deformation amount of the deformation type.

2. The urban road network intelligent maintenance management system according to claim 1, characterized in that: The model building module builds a road condition model based on the pathological data of each road type, including: The model building module is further configured to obtain the road surface material in each of the road surface types, and remove the road surface material and lesion data and duplicate data in the lesion data, wherein the lesion data includes: use environment data, road surface use data and deformation data; The model building module is further configured to establish a disease association equation according to the relationship between the road surface material and each of the environmental data and deformation data corresponding to the road surface material; The model building module is further configured to obtain a distance metric between each of the disease association equations, and to establish a distance matrix according to the distance metric; The model building module is also configured to iteratively merge the disease association equations according to the distance matrix, and to build the pavement condition model according to the disease association equations of the pavement materials after iterative merging.

3. The urban road network intelligent maintenance management system according to claim 2, characterized in that: The model building module builds the pavement condition model according to the iteratively merged disease association formulas of the pavement materials, including: The model building module is further configured to establish various disease types of the pavement material according to the disease association formulas of the pavement material after iterative merging; The model building module is further configured to cluster the disease association equations according to the disease types; The model building module is further configured to obtain a linear relationship between the disease types according to the relationship between the disease association equations after clustering; The model building module is also configured to build the pavement condition model according to the linear relationship between the disease types of the pavement materials.

4. The urban road network intelligent maintenance management system according to claim 3, characterized in that: When establishing the road condition model, the model building module further includes: The model building module is further configured to obtain the road surface material of any of the road surface types and the environmental data in the disease data, and obtain the preset deformation data of the road surface type according to the road surface material, environmental data, road surface use data and road surface disease model; The model building module is further configured to determine whether to modify the road condition model according to the relationship between the preset deformation data and the deformation data in the lesion data corresponding to the road type; When the preset deformation data is consistent with the deformation data, the model building module determines not to modify the road condition model; When the preset deformation data is inconsistent with the deformation data, the model building module determines to iteratively correct the distance matrix in the road condition model until the preset deformation data is consistent with the deformation data.

5. The urban road network intelligent maintenance management system according to claim 1, characterized in that: The analysis module determines the maintenance level of each road section according to the relationship between the average daily traffic volume, the label of the road section and the status score, including: The analysis module is also configured with a preset status score; The analysis module is further configured to determine the maintenance level of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic volume, and adjust the maintenance level of the road section according to the label of the road section, wherein: The analysis module is further configured to determine the maintenance score of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic volume, and determine the maintenance level of the road section according to the relationship between the maintenance score and the first preset maintenance score and the second preset maintenance score preconfigured in the analysis module: When the maintenance score is lower than the first preset maintenance score, the analysis module determines that the maintenance level of the road section is a low level; When the maintenance score is higher than or equal to the first preset maintenance score, and the maintenance score is lower than the second preset maintenance score, the analysis module determines that the maintenance level of the road section is medium; When the maintenance score is higher than or equal to the second preset maintenance score, the analysis module determines that the maintenance level of the road section is a high level; Among them, the first preset maintenance score is lower than the second preset maintenance score, and the maintenance levels are arranged in order of high level, medium level and low level.

6. The urban road network intelligent maintenance management system according to claim 5, characterized in that: When the analysis module determines the maintenance score of the road section according to the relationship between the score difference between the state score and the preset state score and the average daily traffic flow, it includes: The analysis module is further configured with a first preset score difference and a second preset score difference, and determines the basic score of the maintenance score according to the relationship between the score difference and the first preset score difference and the second preset score difference: When the score difference is lower than the first preset score difference, the analysis module determines that the basic score is Q1; When the score difference is higher than or equal to the first preset score difference, and the score difference is lower than the second preset score difference, the analysis module determines that the basic score is Q2; When the score difference is higher than or equal to the second preset score difference, the analysis module determines that the basic score is Q3; Wherein, the first preset score difference is less than the second preset score difference, and Q1<Q2<Q3; When the analysis module determines that the basic score is Qi, i=1, 2, 3, the analysis module is further configured to obtain the average of the daily average traffic flow of each of the road sections, and determine the average as the preset daily average traffic flow of the road section; The analysis module is further configured to determine whether to adjust the basic score Qi according to the relationship between the average daily traffic flow and the preset average daily traffic flow, wherein: When the average daily traffic volume is lower than or equal to the preset average daily traffic volume, the analysis module determines the basic score Qi as the maintenance score of the road section; When the average daily traffic volume is higher than the preset average daily traffic volume, the analysis module determines an adjustment coefficient according to the traffic volume difference between the average daily traffic volume and the preset average daily traffic volume, and determines the basic score Qi adjusted according to the adjustment coefficient as the maintenance score of the road section, wherein the value range of the adjustment coefficient is (0,1).

7. The urban road network intelligent maintenance management system according to claim 6, characterized in that: When the analysis module adjusts the maintenance level of the road section according to the label of the road section, it includes: When the label of the road section is a healthy road section, the analysis module does not adjust the maintenance level of the road section; When the label of the road section is a damaged road section, the analysis module increases the maintenance level of the road section, wherein: If the maintenance level of the road section is low, the analysis module upgrades the maintenance level of the road section to medium; If the maintenance level of the road section is medium, the analysis module upgrades the maintenance level of the road section to high; If the maintenance level of the road section is high, the analysis module will not increase the maintenance level of the road section.

8. A method for intelligent maintenance and management of urban road networks, applicable to an intelligent maintenance and management system of urban road networks as claimed in any one of claims 1 to 7, characterized in that: include: Acquire real-time images of each road section in the area to be maintained, as well as the road surface type, use environment information, preset use time after construction, and deformation data of each road section within a preset time period; Acquiring preset state data of the road section according to the relationship between the road surface type, usage environment information, preset usage time and a pre-established road condition model of the road section; Preprocessing the real-time image of each road section, extracting the state data of each road section after preprocessing, and determining the state score of each road section according to the state data and the relationship between the deformation data within a preset time period and the preset state data; Acquire characteristic data of each lesion type in the lesion data, match the state data with the characteristic data, and determine a label of each of the road sections according to the matching result; The average daily traffic volume in the environmental information of each of the road sections is obtained, and the maintenance level of each of the road sections is determined according to the relationship between the average daily traffic volume, the label of the road section and the status score.

Images