Road disease classification management method, system and equipment based on big data platform

Abstract

The invention provides a road disease classification management method, system and device based on a big data platform, and belongs to the technical field of road disease recognition. The method comprises the following steps: acquiring multi-source road detection information from in-transit inspection equipment; according to the multi-source road detection information and a preset disease recognition model, generating disease statistical information corresponding to each road disease inspection route; the disease statistical information at least comprises a disease statistical table and a disease distribution diagram; after a preset multi-dimensional classification standard from the user terminal is received, carrying out disease classification on the disease statistical information to determine a corresponding disease classification result; wherein the preset multi-dimensional classification standard is obtained based on one or more dimensions of a disease type, a disease grade, an influence range and repair difficulty; and sending the disease classification result to a preset expert system to determine a corresponding disease maintenance scheme and store the disease maintenance scheme to a big data platform so as to send the disease maintenance scheme and corresponding maintenance resource allocation information to a user terminal.

Description

Technical Field

[0001] This application relates to the technical field of road disease identification, and particularly relates to a road disease classification management method, system and device based on a big data platform. Background Art

[0002] With the acceleration of the urbanization process and the continuous increase in traffic flow, the occurrence frequency and types of road diseases are also increasing day by day. The traditional road disease management method mainly relies on manual inspections and simple data records, which has problems such as low efficiency, inaccurate information, and unscientific classification, and it is difficult to meet the needs of modern road maintenance management.

[0003] The development of big data technology provides new ideas and means for road disease management. By collecting, sorting and analyzing a large amount of road disease data, it is possible to achieve scientific classification, accurate diagnosis and efficient management of road diseases to a certain extent. However, the current road disease classification management scheme based on a big data platform is not yet mature. The existing scheme has weak capabilities in processing multi-source road detection information, its classification rules are relatively rigid, it cannot flexibly adjust the classification rules dynamically, and the intelligent decision-making depends on the basic classification results, with insufficient intelligent level, and a large amount of manpower still needs to be invested, affecting the user experience. Summary of the Invention

[0004] To solve the above problems, the embodiments of this application provide a road disease classification management method, system and device based on a big data platform, which improve the flexibility and intelligent level of road disease classification management, so as to efficiently carry out road maintenance.

[0005] On the one hand, the embodiments of this application provide a road disease classification management method based on a big data platform, and the method includes:

[0006] Obtain various multi-source road detection information from each in-transit inspection device;

[0007] Generate disease statistical information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model; the disease statistical information at least includes a disease statistical table and a disease distribution map;

[0008] After receiving a preset multi-dimensional classification criterion from a user terminal, classify the disease statistical information to determine a corresponding disease classification result; wherein, the preset multi-dimensional classification criterion is obtained based on one or more dimensions of disease type, disease level, influence range and repair difficulty;

[0009] Send the disease classification result to a preset expert system to determine a corresponding disease maintenance plan and store it in the big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

[0010] In one implementation of the present application, before obtaining the multi-source road detection information from each in-transit inspection device, the method further includes:

[0011] Determine the inspection release task corresponding to the in-transit inspection device; wherein, the inspection release task at least includes the inspection task execution time and the road disease inspection route;

[0012] According to the inspection release task and the historical inspection records, determine the data acquisition interval time corresponding to each section of the road disease inspection route; wherein, the data acquisition interval time is in a proportional relationship with the inspection interval duration;

[0013] Send the data acquisition interval time to the corresponding in-transit inspection device, so that the in-transit inspection device controls the image acquisition device and the ground penetrating radar to collect the multi-source road detection information according to the data acquisition interval time.

[0014] In one implementation of the present application, according to the multi-source road detection information and the preset disease recognition model, generate disease statistics information corresponding to each road disease inspection route, specifically including:

[0015] Input the multi-source road detection information into the preset disease recognition model, so as to extract point cloud feature data through the point cloud processing module, extract image data through the image processing module, and fuse the point cloud feature data and the image data through the fusion layer to obtain the joint feature vector corresponding to the multi-source road detection information;

[0016] Map the joint feature vector to the output space of the preset dimension through the preset disease recognition model, determine the corresponding disease type and disease level, and add the disease type and the disease level to the disease statistics information.

[0017] In one implementation of the present application, according to the multi-source road detection information and the preset disease recognition model, generate disease statistics information corresponding to each road disease inspection route, specifically including:

[0018] Statistically analyze each disease type and its corresponding disease type distribution information; the disease type distribution information at least includes the first disease quantity corresponding to each disease type and the first disease ratio between each disease type;

[0019] Determine the location distribution information and disease level distribution information of each road disease; the disease level distribution information at least includes the second disease data corresponding to each disease level and the second disease ratio between each disease level;

[0020] Add the disease type distribution information, the location distribution information, and the disease level distribution information to the disease statistics table;

[0021] Generate a corresponding disease heat map, location distribution map, and disease trend map according to the disease statistics table, and use them as the disease distribution map to determine the disease statistics information according to the disease statistics table and the disease distribution map, and display it on the user terminal.

[0022] In an implementation manner of the present application, before classifying the disease statistics information by disease type, the method further includes:

[0023] Determine one or more classification dimension combinations according to the disease statistics information and the historical disease repair records;

[0024] Send each of the classification dimension combinations to the user terminal so that the user can select a classification dimension combination as the preset multi-dimensional classification standard through the user terminal.

[0025] In an implementation manner of the present application, classifying the disease statistics information by disease type to determine a corresponding disease classification result specifically includes:

[0026] Allocate each road disease in the disease statistics information to a corresponding classification category according to the preset multi-dimensional classification standard;

[0027] Determine the location distribution information of each road disease in the same classification category;

[0028] Determine whether there is a conflict for each road disease according to the location distribution information, the corresponding historical traffic data, and a preset conflict judgment model. If so, generate a conflict disease pair; the preset conflict judgment model is established based on the road disease distance and the traffic flow impact value of the disease pair;

[0029] According to each conflict disease pair, divide each road disease with a conflict into different sets of diseases to be maintained; among them, there is no conflict among the road diseases in the same set of diseases to be maintained;

[0030] Determine the number of road diseases in each set of diseases to be maintained, generate a maintenance priority according to the number of road diseases, and generate a disease set sequence corresponding to each set of diseases to be maintained according to the maintenance priority to obtain the disease classification result.

[0031] In an implementation manner of the present application, after determining the number of road diseases in each set of diseases to be maintained, the method further includes:

[0032] Determine the set of diseases to be maintained with the number of road diseases less than a preset threshold as the set to be merged;

[0033] Based on each of the road diseases in the set to be merged, determine the set of non-conflicting diseases to be maintained in other classification categories, so as to merge the set to be merged with the set of non-conflicting diseases to be maintained, and generate the updated set of diseases to be maintained.

[0034] In an implementation manner of the present application, send the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform, specifically including:

[0035] Through the preset expert system, query each matching node and matching edge corresponding to the disease classification result from the pre-constructed knowledge graph; wherein, the pre-constructed knowledge graph uses disease types, disease causes, maintenance measures, maintenance materials, and road attributes as nodes, and the relationships between road disease entities as edges;

[0036] Perform reasoning based on each of the matching nodes, the matching edges, and the preset expert experience triples to obtain the disease maintenance plan corresponding to the disease classification result, and send the association relationship between the disease maintenance plan and the disease classification result to the big data platform.

[0037] On the other hand, an embodiment of the present application also provides a road disease classification management system based on a big data platform, and the system includes:

[0038] An acquisition module, configured to acquire various multi-source road detection information from each in-transit inspection device;

[0039] A generation module, configured to generate disease statistical information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model; the disease statistical information at least includes a disease statistical table and a disease distribution map;

[0040] A classification module, configured to perform disease classification on the disease statistical information after receiving a preset multi-dimensional classification criterion from a user terminal to determine the corresponding disease classification result; wherein, the preset multi-dimensional classification criterion is obtained based on one or more dimensions of disease type, disease level, influence range, and repair difficulty;

[0041] A sending module, configured to send the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

[0042] On yet another aspect, an embodiment of the present application also provides a road disease classification management device based on a big data platform, and the device includes:

[0043] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute a method for classifying and managing road diseases based on a big data platform as described above.

[0044] Compared with the prior art, the significant effects of this application are as follows:

[0045] Through the above technical solution, multi-source data of the road can be collected and a complete disease statistics can be carried out. By combining the user's personalized multi-dimensional classification criteria, the diseases can be flexibly classified, and then an expert system is used to generate a disease maintenance plan adapted to the personalized classification. This process does not require a large amount of manpower to assist in classification and intelligent decision-making, effectively improving the flexibility and intelligent level of road disease classification management, and enabling efficient road maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The drawings described herein are used to provide a further understanding of this application, and constitute a part of this application. The illustrative embodiments of this application and their descriptions are used to explain this application, and do not constitute an improper limitation of this application. In the drawings:

[0047] Figure 1 is a schematic flowchart of a method for classifying and managing road diseases based on a big data platform in an embodiment of this application;

[0048] Figure 2 is a schematic structural diagram of a system for classifying and managing road diseases based on a big data platform in an embodiment of this application;

[0049] Figure 3 is a schematic structural diagram of a device for classifying and managing road diseases based on a big data platform in an embodiment of this application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0051] The embodiments of this application provide a method, a system, and a device for classifying and managing road diseases based on a big data platform, which are used to solve the technical problem that the current classification and management of road diseases are not flexible and intelligent enough, affecting the user experience, so as to improve the flexibility and intelligent level of road disease classification management, and thus efficiently perform road maintenance.

[0052] The following will describe each embodiment of the present application in detail with reference to the accompanying drawings.

[0053] The embodiment of the present application provides a road disease classification management method based on a big data platform. As Figure 1 shown, the method may include steps S101 - S104:

[0054] S101, the server obtains various multi - source road detection information from each in - transit inspection device.

[0055] It should be noted that the server, as the execution entity of the road disease classification management method based on the big data platform, is only an exemplary existence. The execution entity is not limited to the server. For example, it can also be an edge computing device, etc. The present application does not make specific limitations in this regard.

[0056] The in - transit inspection devices include but are not limited to inspection vehicles and drones. Image acquisition devices such as high - definition industrial cameras, GPS / Beidou high - precision positioning modules, and 4G / 5G communication modules are installed on the bodies of the in - transit inspection devices. A ground - penetrating radar can also be installed on the inspection vehicle. The data of the inspection vehicle and the drone can be integrated on the server as multi - source road detection information.

[0057] Among them, the high - definition industrial camera is installed on the inspection vehicle or the drone and is used to collect high - definition images of the road surface. These images can identify diseases such as cracks, potholes, and settlements. The resolution of the camera is usually above 10 million pixels, which can capture fine disease characteristics. The camera collects images of the road surface by taking regular shots or triggered shots. These images are transmitted to the big data platform in real time through the 4G / 5G communication module for subsequent processing and analysis.

[0058] The ground - penetrating radar is installed on the inspection vehicle and is used to detect the disease conditions of the internal structure of the road, such as the base layer and the surface layer. The ground - penetrating radar emits high - frequency electromagnetic waves and detects the reflected signals of the underground structure to obtain the disease information inside the road. The ground - penetrating radar continuously emits and receives electromagnetic waves during the vehicle's driving process to generate a cross - sectional view of the underground structure. These cross - sectional views are transmitted to the big data platform in real time through the 4G / 5G communication module for subsequent processing and analysis.

[0059] The GPS / Beidou high-precision positioning module is installed on the inspection vehicle or drone to provide accurate location information of the diseases. The positioning module obtains the longitude, latitude and elevation information of the vehicle or drone in real time through satellite signals. During the data collection process, the positioning module synchronously records the accurate location information of each disease point. These location information are transmitted to the big data platform in real time through the 4G / 5G communication module and associated with the disease images and ground penetrating radar data. The 4G / 5G communication module is installed on the inspection vehicle or drone to transmit the collected disease data to the big data platform in real time. The communication module supports high-speed data transmission to ensure the real-time and integrity of the data. During the data collection process, the communication module transmits the data collected by the high-definition industrial camera, ground penetrating radar and positioning module to the big data platform in real time. During the data transmission process, the communication module ensures the stability and reliability of the data and supports the rapid transmission of large-scale data.

[0060] The data storage module of the road disease classification management system based on the big data platform corresponding to this application consists of a database management system, a storage engine, a distributed storage management module, and a data encryption and security module. The database management system can select the Transwarp Data Hub (TDH) of StarRocks. The storage engine can use NAND Flash to build a storage array. NAND Flash has a high storage density and fast write speed, which is suitable for large-capacity data storage. At the same time, in order to ensure the correctness of data storage, an error detection / correction (EDC / ECC) algorithm needs to be added. Distributed storage management can use the Transwarp Distributed Data Management System (TDDMS) of StarRocks. It provides unified distributed storage management, supports multiple storage engines, and realizes the efficient storage and management of data. The data encryption and security module can use the encryption technology of xSTORAGE to provide indestructible protection for the data and ensure the security of the data during storage and transmission.

[0061] In the embodiment of this application, before obtaining the multi-source road detection information from each in-transit inspection device, the method further includes:

[0062] Determine the inspection release task corresponding to the in-transit inspection device. Among them, the inspection release task at least includes the inspection task execution time and the road disease inspection route. According to the inspection release task and the historical inspection records, determine the data collection interval time corresponding to each section of the road disease inspection route. Among them, the data collection interval time is in a direct proportional relationship with the inspection interval duration. Send the data collection interval time to the corresponding in-transit inspection device so that the in-transit inspection device controls the image acquisition device and the ground penetrating radar to collect multi-source road detection information according to the data collection interval time.

[0063] Before the on - the - way inspection device performs an inspection, the server can issue an inspection release task, or the on - the - way inspection device can actively issue an inspection release task. This application does not make specific limitations on this. After the server determines the inspection release task of the on - the - way inspection device, it can flexibly adjust and control the working time of the data acquisition related devices of the on - the - way inspection device according to the historical inspection records related to the inspection release task, so as to effectively collect multi - source road detection information on the premise of saving power consumption costs.

[0064] Specifically, the server extracts the inspection task execution time and the road disease inspection route in the inspection release task, and then matches the historical inspection time of each road position on the road disease inspection route in the historical inspection records. According to the inspection task execution time of this task, the inspection interval duration between the historical inspection time and the inspection task execution time is calculated. According to the relationship formula between the inspection interval duration and the data acquisition interval time: t1 = k·t0, where t1 is the data acquisition interval time, k is a preset coefficient in the interval (0, 1), and t0 is the inspection interval duration, the data acquisition interval time is calculated. The server can send the data acquisition interval time and the corresponding road section of the data acquisition interval time to the on - the - way inspection device, so as to control the on - the - way inspection device to intermittently collect multi - source road detection information at the data acquisition interval time. For example, control the image acquisition device and the ground penetrating radar to collect data at an interval of 500 milliseconds (ms). The above - mentioned preset coefficient can be set by the user according to the actual usage scenario, and this application does not make specific limitations on this.

[0065] S102. The server generates disease statistical information corresponding to each road disease inspection route according to the multi - source road detection information and the preset disease recognition model.

[0066] The above - mentioned disease statistical information at least includes a disease statistical table and a disease distribution map.

[0067] This application uses a preset disease recognition model to process the multi - source road detection information, and then generates disease statistical information, which can be displayed to the user or used for further processing. Among them, after this application obtains the multi - source road detection information, it first performs data pre - processing, such as data cleaning, data filtering and other steps.

[0068] Data cleaning: Identify and correct errors and outliers in the data to ensure data accuracy and consistency. This includes handling missing values: Detect missing values in the data and choose methods such as filling, deleting, or interpolating according to specific situations. Handling outliers: Identify outliers in the data and correct or delete them according to business rules. Handling duplicate values: Detect and delete duplicate data records to ensure data uniqueness. Data filtering: Remove invalid and noisy data to improve data purity. This includes image denoising: Denoise the collected image data to improve image clarity and quality. Data screening: Filter out valid data according to preset rules and remove irrelevant and noisy data.

[0069] In an embodiment of the present application, generating the disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and the preset disease recognition model specifically includes:

[0070] Input the multi-source road detection information into the preset disease recognition model to extract point cloud feature data through the point cloud processing module, extract image data through the image processing module, and fuse the point cloud feature data and the image data through the fusion layer to obtain a joint feature vector corresponding to the multi-source road detection information. Map the joint feature vector to the output space of a preset dimension through the preset disease recognition model to determine the corresponding disease type and disease level, and add the disease type and disease level to the disease statistics information.

[0071] That is to say, the preset disease recognition model includes a point cloud processing module and an image processing module, which respectively process the point cloud data and images included in the multi-source road detection information, extract the point cloud feature data and the image data and fuse them to obtain a joint feature vector. Among them, when the image processing module processes the image, it can use the YOLO sub-module to divide the image into multiple grids, each grid is responsible for detecting diseases in a specific area and outputting the category and location information of the diseases, and use PointRend to accurately segment the disease area and extract the detailed features of the diseases. PointRend improves the segmentation accuracy and efficiency by combining coarse segmentation and fine segmentation.

[0072] The preset disease recognition model is a machine learning model trained by a number of feature vector samples. After inputting the joint feature vector into the preset disease recognition model, the model processes the joint feature vector and maps it to an output space of a preset dimension, such as 10 dimensions. Subsequently, the corresponding disease type and disease level can be output, and the disease level is used to characterize the severity of the disease.

[0073] In an embodiment of the present application, generating the disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and the preset disease recognition model specifically includes:

[0074] Statistically analyze each disease type and its corresponding disease type distribution information. The disease type distribution information includes at least the first disease quantity corresponding to each disease type and the first disease ratio between each disease type. Determine the location distribution information and disease level distribution information of each road disease. The disease level distribution information includes at least the second disease data corresponding to each disease level and the second disease ratio between each disease level. Add the disease type distribution information, location distribution information, and disease level distribution information to the disease statistics table. According to the disease statistics table, generate corresponding disease heat maps, location distribution maps, and disease trend maps, and use them as disease distribution maps to determine disease statistics information based on the disease statistics table and disease distribution maps, and display it on the user terminal.

[0075] That is to say, the present application can classify and statistically analyze according to the type of disease, and generate the quantity and proportion of various diseases. Disease location statistics: Generate the distribution of diseases in different road sections according to the location information of diseases. Disease level statistics: Classify and statistically analyze according to the severity of diseases, and generate the quantity and proportion of diseases at different levels. According to the above-mentioned disease type distribution information, location distribution information, and disease level distribution information obtained by statistics, formulate a disease statistics table that can display disease types, quantities, locations, and disease levels. The format of the disease statistics table is like an Excel table.

[0076] At the same time, a disease distribution map will also be generated to visually display the distribution of diseases on the road, generate a disease heat map, and represent the density and severity of diseases through the depth of color. Generate a location distribution map of diseases, and display the specific locations and ranges of diseases in the form of points, lines, and surfaces. Generate a disease trend map to display the change trend of diseases over time, providing a basis for the prediction and prevention of diseases. The user terminal can be a user corresponding to the big data platform, such as devices like mobile phones and computers of road maintenance management department personnel. The present application does not make specific limitations on this.

[0077] S103. After the server receives the preset multi-dimensional classification criteria from the user terminal, it classifies the disease statistics information to determine the corresponding disease classification result.

[0078] Among them, the preset multi-dimensional classification criteria are obtained based on one or more dimensions of disease type, disease level, influence range, and repair difficulty.

[0079] In the embodiment of the present application, before classifying the disease statistics information, the method further includes:

[0080] Determine one or more classification dimension combinations according to the disease statistics information and historical disease repair records. Send each classification dimension combination to the user terminal so that the user can select a classification dimension combination as the preset multi-dimensional classification criteria through the user terminal.

[0081] Specifically, after determining the disease statistics information, the server can combine the historical disease repair records to obtain one or more classification dimension combinations. The historical disease repair records include pre-stored or user-set repair-related records, and the repair-related records contain the classification dimension combination rules selected for disease repair during the historical disease repair process. For example, during several historical disease repair processes, the binary classification dimension combination composed of disease type and disease level is used to repair road diseases in sequence, and the ternary classification dimension combination composed of disease type, disease level, and repair difficulty is used to repair road diseases in sequence. Then the classification dimension combinations include [disease type, disease level], [disease type, disease level, repair difficulty]. Among them, disease type, disease level, influence range, and repair difficulty can also be used as preset multi-dimensional classification criteria alone. Here, disease type, disease level, influence range, and repair difficulty are only stored as examples, and the classification dimensions can also include other dimensions. According to the specific usage scenario, they can be custom-added by the user, or supplemented after obtaining new classification dimensions of road diseases through continuous analysis of road diseases, or the classification dimensions can be optimized by combining data analysis and machine learning algorithms to further improve the classification accuracy and efficiency. This application does not make specific limitations on this.

[0082] This application can send one or more classification dimension combinations applicable to the above-mentioned disease statistics information to the user terminal, and the user operates the user terminal to select one of the classification dimension combinations as the preset multi-dimensional classification criterion, and then classify the disease statistics information.

[0083] The above disease types: According to the appearance characteristics and causes of diseases, diseases are divided into crack types (such as longitudinal cracks, transverse cracks, and reticular cracks), pothole types, settlement types, loose types, etc. Disease levels: According to the severity of diseases, diseases are divided into three levels: minor, medium, and severe. Influence range: According to the influence range of diseases on the road use function, diseases are divided into local influence and extensive influence. Repair difficulty: According to the complexity of disease repair and the required resources, diseases are divided into three levels: easy to repair, medium difficulty, and high difficulty.

[0084] In the embodiment of this application, the above-mentioned classification of disease statistics information to determine the corresponding disease classification results specifically includes:

[0085] According to the preset multi-dimensional classification criteria, each road disease in the disease statistics information is assigned to the corresponding classification category. Determine the location distribution information of each road disease in the same classification category. According to the location distribution information, the corresponding historical traffic data, and the preset conflict judgment model, determine whether there is a conflict for each road disease. If so, generate a pair of conflicting diseases. The preset conflict judgment model is established based on the distance between road diseases and the influence value of the disease pair on traffic flow. According to each pair of conflicting diseases, classify each road disease with a conflict into different sets of diseases to be maintained. Among them, there is no conflict among the road diseases in the same set of diseases to be maintained. Determine the number of road diseases in each set of diseases to be maintained, so as to generate a maintenance priority according to the number of road diseases, and generate a disease set sequence corresponding to each set of diseases to be maintained according to the maintenance priority, and obtain the disease classification result.

[0086] That is to say, the server uses the preset multi-dimensional classification criteria to first classify each road disease in the disease statistics information. For example, if the preset multi-dimensional classification criteria are disease type and disease level, then classify {crack type, minor}, {crack type, medium}, {crack type, severe}, {pothole type, minor}... one by one to obtain the classification categories of each road disease. Subsequently, the location distribution information will also be extracted separately for the classification category, combined with the historical traffic data, and the preset conflict judgment model will be run to verify whether there is a conflict that affects traffic driving during road maintenance. The preset conflict judgment model is as follows:

[0087]

[0088] where w ij is the conflict judgment result between road disease i and road disease j, 1 indicates that there is a conflict, and 0 indicates that there is no conflict; d ij represents the distance between road disease i and road disease j, d th is the preset distance threshold, F i is the influence value of road disease i on traffic flow during the concentrated period of historical passing vehicles, F j is the influence value of road disease i on traffic flow during the concentrated period of historical passing vehicles, F max is the maximum traffic flow carrying capacity threshold corresponding to the section between road disease i and road disease j preset.

[0089] The above distance threshold and the maximum traffic flow carrying capacity threshold can be preset by the user, and the present application does not make specific limitations on this. F i and F j can be calculated according to t n is the average driving time period during the concentrated period of historical passing vehicles under normal conditions at the location where the road disease is extracted from the historical traffic data, td is the average driving time during the concentrated period of historical passing vehicles when there are road diseases at the location of the road diseases, Q n is the traffic flow during the concentrated period of historical passing vehicles under normal conditions.

[0090] According to the above processing, multiple pairs of conflicting diseases can be obtained, that is, binary groups composed of two road diseases. Subsequently, each road disease in the same classification category is grouped, and the road diseases that do not conflict with each other are divided into a set of diseases to be maintained. Subsequently, according to the number of road diseases in the set, maintenance priorities are marked for the set of diseases to be maintained respectively. For example, the more road diseases there are in the set, the higher the maintenance priority. According to the maintenance priority, the set names of each set of diseases to be maintained are added to the disease set sequence for subsequent maintenance processing according to this disease set sequence.

[0091] In addition, in an embodiment of the present application, after determining the number of road diseases in each set of diseases to be maintained, the method further includes:

[0092] Determine the set of diseases to be maintained with the number of road diseases less than the preset threshold as the set to be merged. Based on each road disease in the set to be merged, determine the non-conflicting set of diseases to be maintained in other classification categories, so as to perform a merging process on the set to be merged and the non-conflicting set of diseases to be maintained to generate an updated set of diseases to be maintained.

[0093] In other words, if the number of road diseases in a set of diseases to be maintained is relatively small, less than a preset threshold set in advance, then the set of diseases to be maintained can be merged with other sets of diseases to be maintained for subsequent centralized processing of these road diseases. Among them, the server respectively executes the above conflict judgment on each road disease in the set to be merged and the road diseases in the set of diseases to be maintained in other classification categories. When there are no conflicting road diseases between the set to be merged and a set of diseases to be maintained, at this time, the set of diseases to be maintained is used as the non-conflicting set of diseases to be maintained, and the road disease merging process is executed.

[0094] The above steps are executed by the disease classification module of the system, and the work process of the disease classification module is as follows:

[0095] Data input: Receive the preprocessed and feature-extracted road disease data from the data processing module. Feature matching: Match the preset classification criteria according to the feature information of the disease (such as type, degree, influence range, etc.). Classification execution: Distribute the disease data into the corresponding classification categories according to the matched classification criteria. Result output: Generate the disease classification result and store the result in the big data platform for use by the subsequent disease diagnosis and management decision-making module.

[0096] S104, the server sends the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

[0097] In the embodiment of the present application, the above-mentioned sending the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform specifically includes:

[0098] Through the preset expert system, query each matching node and matching edge corresponding to the disease classification result from the pre-constructed knowledge graph. Among them, the pre-constructed knowledge graph takes disease types, disease causes, maintenance measures, maintenance materials, and road attributes as nodes, and the relationships between road disease entities as edges. According to each matching result, matching edge, and the preset expert experience triple for reasoning, obtain the disease maintenance plan corresponding to the disease classification result, and send the association relationship between the disease maintenance plan and the disease classification result to the big data platform.

[0099] In other words, the present application can use an expert system for disease diagnosis. This function is the system disease diagnosis module, which uses the expert system and knowledge base to accurately diagnose diseases and determine the specific causes and solutions of diseases. This module improves the accuracy and efficiency of disease diagnosis through an automated and intelligent diagnosis process, providing scientific decision-making support for road maintenance management departments. The diagnostic basis of the disease diagnosis module includes the following aspects: Disease classification result: Classification information such as disease type, degree, influence range, and repair difficulty obtained from the disease classification module. Relevant data: including detailed images of diseases, location information, historical data, etc. Expert system and knowledge base: Using the preset expert system and knowledge base, combined with the disease classification result and relevant data, for comprehensive analysis and diagnosis.

[0100] The working process of the disease diagnosis module is as follows: Data input: Receive the disease classification result and relevant data from the disease classification module. Feature matching: According to the feature information of the disease, match the preset diagnostic rules and expert experience in the knowledge base. Comprehensive analysis: Combine the disease classification result and relevant data for comprehensive analysis to determine the specific cause of the disease. Solution generation: Generate detailed repair suggestions and maintenance plans according to the specific cause of the disease. Result output: Generate a detailed disease diagnosis report, including disease causes, repair suggestions, etc., and store the results in the big data platform for use by the subsequent management decision-making module.

[0101] The preset expert system is pre-built with a knowledge graph that defines various entities related to road diseases, such as disease types (cracks, potholes, etc.), disease causes (foundation settlement, vehicle overloading, etc.), maintenance measures (sealant injection, repair, etc.), maintenance materials (asphalt, cement, etc.), and road attributes (road grade, traffic flow, etc.), as the knowledge graph interface. The relationships between entities are determined, such as "causes" (disease causes lead to disease types), "applies to" (maintenance measures apply to disease types), "uses" (maintenance measures use maintenance materials), etc., as the edges of the knowledge graph. Through this knowledge graph, the matching nodes and matching edges of each disease in the disease classification results can be found. Then, the preset expert experience triples are used for reasoning. These expert experience triples can be pre-set by experts. The corresponding maintenance plans for each disease in the disease classification results are obtained through reasoning, and the disease maintenance plans can be stored in the big data platform for users to maintain road diseases according to the disease maintenance plans.

[0102] Meanwhile, the big data platform can also generate disease repair plans, maintenance budgets, resource allocation plans, etc. through the management decision-making module based on the disease classification and diagnosis results, providing scientific decision-making support for the road maintenance management department. Through the "one-screen" data display, this module can quickly and accurately understand the maintenance inspection information of the system business, diseases, vehicles, etc., and give early warnings about the road structure risks.

[0103] The diagnostic basis of the disease diagnosis module includes the following aspects: Disease classification results: Classification information such as disease types, degrees, influence ranges, and repair difficulties obtained from the disease classification module. Relevant data: including detailed images of diseases, location information, historical data, etc. Expert system and knowledge base: Using the preset expert system and knowledge base, combined with the disease classification results and relevant data, comprehensive analysis and diagnosis are carried out.

[0104] The working process of the disease diagnosis module is as follows: Data input: Receive the disease classification results and relevant data from the disease classification module. Feature matching: Match the preset diagnostic rules and expert experience in the knowledge base according to the feature information of the disease. Comprehensive analysis: Combine the disease classification results and relevant data for comprehensive analysis to determine the specific cause of the disease. Solution generation: Generate detailed repair suggestions and maintenance plans according to the specific cause of the disease. Result output: Generate a detailed disease diagnosis report, including disease causes, repair suggestions, etc., and store the results in the big data platform for subsequent use by the management decision-making module.

[0105] The decision-making support of the management decision-making module specifically includes the following aspects:

[0106] Disease Repair Plan: Generate a detailed disease repair plan based on the classification and diagnosis results of diseases, including repair time, repair methods, required materials and equipment, etc. Assign disease repair tasks to the corresponding maintenance teams and set a repair schedule. Allocate the required materials and equipment according to the needs of the repair tasks to ensure the smooth progress of the repair work.

[0107] Maintenance Budget: Generate a maintenance budget, including the budget for disease repair, daily maintenance, preventive maintenance, etc. Estimate the costs of various repair tasks according to the disease repair plan, including material costs, labor costs, equipment usage fees, etc. Compile a detailed maintenance budget by integrating various costs and optimize the costs.

[0108] Resource Allocation Plan: Develop a resource allocation plan based on the disease repair plan and maintenance budget to ensure the rational use of resources. Evaluate the existing resource situation, including personnel, equipment, materials, etc. Develop a resource allocation plan according to the disease repair plan to ensure the rational distribution of resources in terms of time and space.

[0109] The digital cockpit is an important part of the management decision-making module, providing intuitive decision-making support information through "one-screen" data display.

[0110] Data Display: Through a graphical interface, display maintenance inspection information such as system operations, diseases, and vehicles, and provide comparative analysis of real-time data and historical data. Disease Distribution Map: Display the distribution of diseases on different road sections, and indicate the severity of diseases through colors and icons. Disease Statistics Table: Display information such as the type, quantity, and location of diseases, and provide multi-dimensional statistical analysis. Vehicle Information: Display the location, status, and task execution status of inspection vehicles, and provide real-time monitoring and scheduling functions.

[0111] Risk Warning: Issue real-time warnings about road structure risks to remind the maintenance management department to take timely measures. Evaluate the risk level of the road structure according to the severity and development trend of diseases. When high-risk diseases are detected, issue warning messages in a timely manner to remind relevant departments to take corresponding measures.

[0112] The user interaction module is an important part of the road disease classification management system based on the big data platform, responsible for providing a user-friendly interaction interface to facilitate data entry, query, analysis, and decision-making operations for different user roles (such as road maintenance management personnel, inspection personnel, inspection equipment operators, etc.). Through an intuitive interface design and rich functional features, this module enhances the user experience and improves work efficiency.

[0113] The user interface design aims to provide a simple, intuitive, and easy-to-use operating environment, ensuring that different user roles can quickly get started and efficiently complete tasks. It includes a login interface for user authentication to ensure the security of the system. User input consists of username and password input fields. Verification: The system verifies the user's identity. Upon successful verification, it redirects to the main interface; otherwise, it prompts an error message. Main interface: Provides the main function entry points of the system and displays key information. It contains quick access to the main functions such as data entry, query, analysis, and decision-making. Dashboard: Displays key metrics and real-time data, such as the number of diseases, repair progress, vehicle status, etc. Notification bar: Shows system notifications and warning messages. Data entry interface: Facilitates users to enter disease data and supports multiple data types. Form design: Provides a simple and clear form, including fields such as disease type, location, severity, discovery time, etc. Image upload: Supports high-definition image upload to facilitate recording detailed disease conditions. Location positioning: Integrates GPS / Beidou positioning function to automatically obtain disease location information. Submit button: Submits data, and the system validates and stores the data. Data query interface: Provides a powerful data query function and supports multi-dimensional queries. Query conditions: Support queries by disease type, location, severity, discovery time, etc. Result display: Displays query results in the form of tables and maps, and supports paging and export functions. Detailed information: Click on an item in the query result to view the detailed information and images of the disease. Data analysis interface: Provides the analysis function for disease data, generating statistical reports and charts. Statistical reports: Generate disease statistics tables, showing information such as disease types, quantities, locations, etc. Chart display: Generate disease distribution maps, disease trend charts, etc., to visually display the disease situation. Export function: Supports exporting analysis results to formats such as Excel and PDF. Decision support interface: Provides decision support information such as disease repair plans, maintenance budgets, and resource allocation plans. Repair plan: Displays the disease repair plan, including repair time, methods, materials, and equipment. Maintenance budget: Displays the maintenance budget, including a detailed breakdown of each expense. Resource allocation: Displays the resource allocation plan, including the allocation of personnel, equipment, and materials.

[0114] The user interaction module supports multiple functional features to enhance the user experience and operation efficiency.

[0115] Zoom in and out functions: Support zooming in and out of maps and images, facilitating users to view details. Map operations: Adjust the display scale of the map through the mouse wheel or zoom in / out buttons. Image operations: Adjust the display scale of the image through the mouse wheel or zoom in / out buttons. Data entry interface: Provide a simple and clear data entry interface for users to quickly enter data. Form design: Form fields are clear, and input boxes have prompt messages to reduce user input errors. Auto-fill: Support auto-fill for some fields to improve the entry efficiency. Instant verification: Input boxes are instantaneously verified to ensure data accuracy. Convenient and fast operation: Provide quick operations and intelligent prompts to reduce the number of user operation steps. Quick buttons: Provide quick buttons for common functions to reduce menu operations. Intelligent prompts: Provide intelligent prompts for input boxes and operation steps to help users quickly complete tasks. Batch operations: Support batch entry, query, and export of data to improve work efficiency.

[0116] Through the above technical solutions, multi-source data of roads can be collected and a complete disease statistics can be conducted. By combining the user's personalized multi-dimensional classification criteria, diseases can be flexibly classified, and then an expert system is used to generate a disease maintenance plan adapted to the personalized classification. This process does not require a large amount of human assistance to complete classification and intelligent decision-making, effectively improving the flexibility and intelligent level of road disease classification management and enabling efficient road maintenance.

[0117] Figure 2 The structural schematic diagram of a road disease classification management system based on a big data platform provided by an embodiment of the present application is as follows Figure 2 shown. The road disease classification management system 200 based on the big data platform includes:

[0118] An acquisition module 201 for acquiring various multi-source road detection information from each in-transit inspection device. A generation module 202 for generating disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model. The disease statistics information at least includes a disease statistics table and a disease distribution map. A classification module 203 for classifying the disease statistics information to determine the corresponding disease classification result when receiving a preset multi-dimensional classification criterion from a user terminal. Among them, the preset multi-dimensional classification criterion is obtained based on one or more dimensions of disease type, disease level, influence range, and repair difficulty. A sending module 204 for sending the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

[0119] Figure 3 The structural schematic diagram of a road disease classification management device based on a big data platform provided by an embodiment of the present application is as followsFigure 3 As shown in

[0120] at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to:

[0121] Obtain multi-source road detection information from each in-transit inspection device. Generate disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease identification model. The disease statistics information at least includes a disease statistics table and a disease distribution map. After receiving a preset multi-dimensional classification criterion from a user terminal, classify the disease statistics information to determine a corresponding disease classification result. The preset multi-dimensional classification criterion is obtained based on one or more dimensions among disease type, disease level, influence range, and repair difficulty. Send the disease classification result to a preset expert system to determine a corresponding disease maintenance plan and store it in a big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

[0122] Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for system and device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and reference can be made to the corresponding parts of the method embodiments for the relevant content.

[0123] The systems and devices provided in the embodiments of this application correspond one-to-one with the methods. Therefore, the systems and devices also have beneficial technical effects similar to those of their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and devices will not be elaborated here.

[0124] It should also be noted that the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the said element.

[0125] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A road disease classification and management method based on a big data platform, characterized in that, The method includes: Obtaining various multi-source road detection information from each in-transit inspection device; Generating disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model; the disease statistics information at least includes a disease statistics table and a disease distribution map; After receiving a preset multi-dimensional classification criterion from a user terminal, classifying the disease statistics information to determine a corresponding disease classification result; wherein, the preset multi-dimensional classification criterion is obtained based on one or more dimensions of disease type, disease level, influence range, and repair difficulty; Sending the disease classification result to a preset expert system to determine a corresponding disease maintenance plan and storing it in a big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

2. The road disease classification management method based on a big data platform according to claim 1, characterized in that Before obtaining various multi-source road detection information from each in-transit inspection device, the method further includes: Determining an inspection release task corresponding to the in-transit inspection device; wherein, the inspection release task at least includes an inspection task execution time and the road disease inspection route; Determining the data acquisition interval time corresponding to each section of the road disease inspection route according to the inspection release task and historical inspection records; wherein, the data acquisition interval time is in a direct proportional relationship with the inspection interval duration; Sending the data acquisition interval time to the corresponding in-transit inspection device, so that the in-transit inspection device controls an image acquisition device and a ground penetrating radar to acquire the multi-source road detection information according to the data acquisition interval time.

3. A method for classifying and managing road diseases based on a big data platform according to claim 2, characterized in that, Generating disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model, specifically including: Inputting the multi-source road detection information into the preset disease recognition model to extract point cloud feature data through a point cloud processing module, extract image data through an image processing module, and fuse the point cloud feature data and the image data through a fusion layer to obtain a joint feature vector corresponding to the multi-source road detection information; Mapping the joint feature vector to an output space of a preset dimension through the preset disease recognition model to determine the corresponding disease type and disease level, and adding the disease type and the disease level to the disease statistics information.

4. A method for classifying and managing road diseases based on a big data platform according to claim 3, characterized in that, Generating disease statistics information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model, specifically including: Counting each disease type and its corresponding disease type distribution information; the disease type distribution information at least includes the first disease quantity corresponding to each disease type and the first disease ratio between each disease type; Determining the location distribution information and disease level distribution information of each road disease; the disease level distribution information at least includes the second disease data corresponding to each disease level and the second disease ratio between each disease level; Adding the disease type distribution information, the location distribution information, and the disease level distribution information to the disease statistics table; Generate corresponding disease heat maps, location distribution maps, and disease trend maps according to the disease statistics table, and use them as the disease distribution maps to determine the disease statistical information based on the disease statistics table and the disease distribution maps, and display it on the user terminal.

5. A method for classifying and managing road diseases based on a big data platform according to claim 1, characterized in that, Before classifying the disease statistical information by disease type, the method further includes: Determine one or more classification dimension combinations according to the disease statistical information and historical disease repair records; Send each of the classification dimension combinations to the user terminal so that the user can select a classification dimension combination as the preset multi-dimensional classification criterion through the user terminal.

6. The method for classifying and managing road diseases based on a big data platform according to claim 1, characterized in that, Classify the disease statistical information by disease type to determine the corresponding disease classification result, specifically including: According to the preset multi-dimensional classification criterion, allocate each road disease in the disease statistical information to the corresponding classification category; Determine the location distribution information of each road disease in the same classification category; According to the location distribution information, the corresponding historical traffic data, and a preset conflict judgment model, determine whether there is a conflict for each road disease. If so, generate a conflict disease pair; the preset conflict judgment model is established based on the road disease distance and the traffic flow impact value of the disease pair; According to each conflict disease pair, divide each road disease with a conflict into different sets of diseases to be maintained; among them, there is no conflict among the road diseases in the same set of diseases to be maintained; Determine the number of road diseases in each set of diseases to be maintained, generate a maintenance priority according to the number of road diseases, and generate a disease set sequence corresponding to each set of diseases to be maintained according to the maintenance priority to obtain the disease classification result.

7. A method for classifying and managing road diseases based on a big data platform according to claim 6, characterized in that, After determining the number of road diseases in each set of diseases to be maintained, the method further includes: Determine the set of diseases to be maintained with the number of road diseases less than a preset threshold as the set to be merged; Based on each road disease in the set to be merged, determine the non-conflicting set of diseases to be maintained in other classification categories, and perform a merging process on the set to be merged and the non-conflicting set of diseases to be maintained to generate an updated set of diseases to be maintained.

8. A method for classifying and managing road diseases based on a big data platform according to claim 1, characterized in that, Send the disease classification result to a preset expert system to determine the corresponding disease maintenance plan and store it in the big data platform, specifically including: Through the preset expert system, query each matching node and matching edge corresponding to the disease classification result from a pre-constructed knowledge graph; the pre-constructed knowledge graph uses disease types, disease causes, maintenance measures, maintenance materials, and road attributes as nodes, and the relationships between road disease entities as edges; Infer according to each matching node, the matching edge, and a preset expert experience triple to obtain the disease maintenance plan corresponding to the disease classification result, and send the association relationship between the disease maintenance plan and the disease classification result to the big data platform.

9. A road disease classification and management system based on a big data platform, characterized in that, The system includes: An acquisition module for acquiring various multi-source road detection information from each in-transit inspection device; A generation module, configured to generate disease statistical information corresponding to each road disease inspection route according to the multi-source road detection information and a preset disease recognition model; the disease statistical information at least includes a disease statistical table and a disease distribution map; A classification module, configured to classify the disease statistical information to determine a corresponding disease classification result after receiving a preset multi-dimensional classification criterion from a user terminal; wherein, the preset multi-dimensional classification criterion is obtained based on one or more dimensions of disease type, disease level, influence range, and repair difficulty; A sending module, configured to send the disease classification result to a preset expert system to determine a corresponding disease maintenance plan and store it in a big data platform, so as to send the disease maintenance plan and its corresponding maintenance resource allocation information to the user terminal.

10. A road disease classification and management device based on a big data platform, characterized in that, The device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a method for classifying and managing road diseases based on a big data platform as described in any one of claims 1-8 above.

Images